U2-Net: Going deeper with nested U-structure for salient object detection

•A novel ReSidual U-block (RSU) is designed to capture multi-scale deep features.•A nested U-structure, called U2-Net, that uses RSU is developed for salient object detection.•Both large (176.3 MB) and small (4.7 MB) instances of U2-Net get competitive results. In this paper, we design a simple yet...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Pattern recognition Ročník 106; s. 107404
Hlavní autori:	Qin, Xuebin, Zhang, Zichen, Huang, Chenyang, Dehghan, Masood, Zaiane, Osmar R., Jagersand, Martin
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier Ltd 01.10.2020
Predmet:	Convolutional neural network Multi-scale feature extraction Nested U-structure Network architecture design Salient object detection Nested U-structure Network architecture design Salient object detection Convolutional neural network Multi-scale feature extraction
ISSN:	0031-3203, 1873-5142
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	•A novel ReSidual U-block (RSU) is designed to capture multi-scale deep features.•A nested U-structure, called U2-Net, that uses RSU is developed for salient object detection.•Both large (176.3 MB) and small (4.7 MB) instances of U2-Net get competitive results. In this paper, we design a simple yet powerful deep network architecture, U2-Net, for salient object detection (SOD). The architecture of our U2-Net is a two-level nested U-structure. The design has the following advantages: (1) it is able to capture more contextual information from different scales thanks to the mixture of receptive fields of different sizes in our proposed ReSidual U-blocks (RSU), (2) it increases the depth of the whole architecture without significantly increasing the computational cost because of the pooling operations used in these RSU blocks. This architecture enables us to train a deep network from scratch without using backbones from image classification tasks. We instantiate two models of the proposed architecture, U2-Net (176.3 MB, 30 FPS on GTX 1080Ti GPU) and U2-Net† (4.7 MB, 40 FPS), to facilitate the usage in different environments. Both models achieve competitive performance on six SOD datasets. The code is available: https://github.com/NathanUA/U-2-Net.
AbstractList	•A novel ReSidual U-block (RSU) is designed to capture multi-scale deep features.•A nested U-structure, called U2-Net, that uses RSU is developed for salient object detection.•Both large (176.3 MB) and small (4.7 MB) instances of U2-Net get competitive results. In this paper, we design a simple yet powerful deep network architecture, U2-Net, for salient object detection (SOD). The architecture of our U2-Net is a two-level nested U-structure. The design has the following advantages: (1) it is able to capture more contextual information from different scales thanks to the mixture of receptive fields of different sizes in our proposed ReSidual U-blocks (RSU), (2) it increases the depth of the whole architecture without significantly increasing the computational cost because of the pooling operations used in these RSU blocks. This architecture enables us to train a deep network from scratch without using backbones from image classification tasks. We instantiate two models of the proposed architecture, U2-Net (176.3 MB, 30 FPS on GTX 1080Ti GPU) and U2-Net† (4.7 MB, 40 FPS), to facilitate the usage in different environments. Both models achieve competitive performance on six SOD datasets. The code is available: https://github.com/NathanUA/U-2-Net.
ArticleNumber	107404
Author	Qin, Xuebin Dehghan, Masood Zhang, Zichen Jagersand, Martin Huang, Chenyang Zaiane, Osmar R.
Author_xml	– sequence: 1 givenname: Xuebin orcidid: 0000-0002-9042-7192 surname: Qin fullname: Qin, Xuebin email: xuebin@ualberta.ca – sequence: 2 givenname: Zichen surname: Zhang fullname: Zhang, Zichen email: zichen2@ualberta.ca – sequence: 3 givenname: Chenyang orcidid: 0000-0003-2811-6008 surname: Huang fullname: Huang, Chenyang email: chuang8@ualberta.ca – sequence: 4 givenname: Masood surname: Dehghan fullname: Dehghan, Masood email: masood1@ualberta.ca – sequence: 5 givenname: Osmar R. surname: Zaiane fullname: Zaiane, Osmar R. email: zaiane@ualberta.ca – sequence: 6 givenname: Martin surname: Jagersand fullname: Jagersand, Martin email: mj7@ualberta.ca
BookMark	eNqFkMtOwzAQRS1UJErhD1j4B1LGjyRNF0ioglKpgg1dW449KY5KXNkuiL8nUVixgNWVZnSuZs4lmXS-Q0JuGMwZsOK2nR91Mn4_58CHUSlBnpEpW5Qiy5nkEzIFECwTHMQFuYyxBWBlv5iSzY5nz5iWdO1dt6cW8YiBfrr0RjuMCS3dZTGFk0mngLTxgUZ9cNgl6usWTeqJ1Ifz3RU5b_Qh4vVPzsju8eF19ZRtX9ab1f02M1wUKcPa1BoqWVoo8oZBbTC3ZYVVWXDNrAUwlW2gkaJegBRMN3nOscgNkwwbXooZkWOvCT7GgI06Bveuw5dioAYdqlWjDjXoUKOOHlv-woxLejg8Be0O_8F3I4z9Yx8Og4qml2DQutB_r6x3fxd8A6Qaf9E
CitedBy_id	crossref_primary_10_1109_TII_2024_3409437 crossref_primary_10_1061_JBENF2_BEENG_7032 crossref_primary_10_1109_TIP_2025_3592522 crossref_primary_10_1016_j_apacoust_2022_109014 crossref_primary_10_1007_s00371_024_03640_8 crossref_primary_10_3390_electronics12071618 crossref_primary_10_1016_j_compbiomed_2022_105942 crossref_primary_10_1038_s41598_023_40175_9 crossref_primary_10_1016_j_ces_2023_119425 crossref_primary_10_1109_ACCESS_2023_3282778 crossref_primary_10_1109_TASLP_2022_3140561 crossref_primary_10_1007_s11042_023_16646_6 crossref_primary_10_1109_TIM_2024_3449979 crossref_primary_10_1016_j_neucom_2021_04_078 crossref_primary_10_1109_TGRS_2025_3582578 crossref_primary_10_1109_LGRS_2023_3342215 crossref_primary_10_1007_s11263_024_02049_z crossref_primary_10_1109_JSEN_2024_3506831 crossref_primary_10_1109_JSTARS_2025_3577343 crossref_primary_10_1016_j_eswa_2021_114848 crossref_primary_10_26599_OCEAN_2025_9470005 crossref_primary_10_1587_transinf_2020EDP7235 crossref_primary_10_3390_rs15071931 crossref_primary_10_1109_TMI_2023_3317072 crossref_primary_10_1016_j_autcon_2023_105138 crossref_primary_10_1038_s41559_024_02438_0 crossref_primary_10_1016_j_asoc_2024_112685 crossref_primary_10_1109_TVCG_2024_3502395 crossref_primary_10_3390_s23104592 crossref_primary_10_1007_s11042_023_14892_2 crossref_primary_10_1016_j_mvr_2024_104680 crossref_primary_10_1080_01431161_2021_1934592 crossref_primary_10_1088_1742_6596_2637_1_012003 crossref_primary_10_1109_TCYB_2022_3163152 crossref_primary_10_1016_j_patcog_2024_111072 crossref_primary_10_4218_etrij_2023_0115 crossref_primary_10_1016_j_procs_2024_09_644 crossref_primary_10_1093_mnras_stad1375 crossref_primary_10_1007_s11760_023_02700_1 crossref_primary_10_1016_j_patcog_2022_108594 crossref_primary_10_1109_TVCG_2022_3209481 crossref_primary_10_1038_s41598_025_98230_6 crossref_primary_10_1016_j_mineng_2025_109413 crossref_primary_10_1007_s10043_025_00946_3 crossref_primary_10_1109_JSTARS_2025_3567508 crossref_primary_10_1109_JIOT_2024_3470130 crossref_primary_10_3390_rs16142637 crossref_primary_10_1038_s41598_024_61105_3 crossref_primary_10_1007_s00371_023_02834_w crossref_primary_10_1109_ACCESS_2023_3305942 crossref_primary_10_1213_XAA_0000000000002040 crossref_primary_10_1111_cgf_15251 crossref_primary_10_1080_2150704X_2024_2391082 crossref_primary_10_1007_s42452_025_06791_y crossref_primary_10_1109_TVT_2022_3141384 crossref_primary_10_1007_s10681_023_03258_2 crossref_primary_10_3233_JIFS_232366 crossref_primary_10_1109_TNNLS_2022_3233025 crossref_primary_10_1007_s11801_025_4059_z crossref_primary_10_1109_ACCESS_2024_3525303 crossref_primary_10_1016_j_ymssp_2025_112774 crossref_primary_10_1155_2022_4189781 crossref_primary_10_3389_fonc_2023_1064548 crossref_primary_10_1016_j_imavis_2023_104694 crossref_primary_10_1007_s10489_024_06003_x crossref_primary_10_1016_j_media_2021_102339 crossref_primary_10_1109_TCSVT_2023_3300731 crossref_primary_10_1007_s11263_024_02058_y crossref_primary_10_1016_j_knosys_2022_108372 crossref_primary_10_1109_ACCESS_2021_3138920 crossref_primary_10_1016_j_eswa_2022_119394 crossref_primary_10_1109_TNNLS_2023_3341246 crossref_primary_10_1364_AO_532573 crossref_primary_10_1109_TIP_2025_3557563 crossref_primary_10_3390_rs14246339 crossref_primary_10_1007_s00371_023_02836_8 crossref_primary_10_3390_electronics12244962 crossref_primary_10_1007_s10489_023_04648_8 crossref_primary_10_1109_TCE_2024_3424671 crossref_primary_10_1016_j_compbiomed_2024_108594 crossref_primary_10_3390_e25040681 crossref_primary_10_1007_s00371_022_02561_8 crossref_primary_10_1002_mp_17791 crossref_primary_10_1016_j_engappai_2023_106453 crossref_primary_10_1016_j_patcog_2024_111036 crossref_primary_10_1109_ACCESS_2023_3338629 crossref_primary_10_1109_JSTARS_2024_3437737 crossref_primary_10_1109_TGRS_2022_3148994 crossref_primary_10_1109_TIM_2021_3128961 crossref_primary_10_1007_s00530_025_01867_6 crossref_primary_10_1016_j_jenvman_2022_115732 crossref_primary_10_1109_ACCESS_2025_3548128 crossref_primary_10_1038_s41598_024_82026_1 crossref_primary_10_1016_j_eswa_2023_122851 crossref_primary_10_1007_s13246_025_01542_0 crossref_primary_10_12677_SEA_2023_122030 crossref_primary_10_1007_s42360_023_00660_7 crossref_primary_10_1109_ACCESS_2025_3542834 crossref_primary_10_3390_microorganisms12010201 crossref_primary_10_1002_pros_24844 crossref_primary_10_1016_j_measurement_2024_114640 crossref_primary_10_1016_j_measurement_2024_114642 crossref_primary_10_1007_s40747_024_01681_z crossref_primary_10_3390_rs15235462 crossref_primary_10_1016_j_compag_2025_110746 crossref_primary_10_1109_ACCESS_2024_3352649 crossref_primary_10_1007_s10489_023_05141_y crossref_primary_10_1002_ima_22836 crossref_primary_10_1109_TASE_2025_3554653 crossref_primary_10_1016_j_bspc_2023_105536 crossref_primary_10_3390_info15120788 crossref_primary_10_1007_s10462_022_10332_z crossref_primary_10_1109_TVCG_2023_3247459 crossref_primary_10_1364_AO_468984 crossref_primary_10_1016_j_eswa_2025_127404 crossref_primary_10_1016_j_isci_2025_111974 crossref_primary_10_1016_j_isprsjprs_2025_07_029 crossref_primary_10_1063_5_0099159 crossref_primary_10_1016_j_conbuildmat_2023_134668 crossref_primary_10_1109_JSTARS_2025_3561160 crossref_primary_10_3390_s25103140 crossref_primary_10_1016_j_patcog_2022_109256 crossref_primary_10_1109_TIM_2025_3554859 crossref_primary_10_1016_j_aei_2025_103249 crossref_primary_10_1111_mice_13113 crossref_primary_10_1007_s00521_021_06845_3 crossref_primary_10_1016_j_knosys_2025_113588 crossref_primary_10_7717_peerj_cs_2932 crossref_primary_10_1016_j_patrec_2024_11_028 crossref_primary_10_1016_j_optcom_2025_131748 crossref_primary_10_1016_j_compag_2024_109462 crossref_primary_10_3390_rs15204977 crossref_primary_10_1109_TITS_2024_3506659 crossref_primary_10_3390_rs13234941 crossref_primary_10_1109_JOE_2024_3467309 crossref_primary_10_1177_20552076221136362 crossref_primary_10_1109_ACCESS_2024_3463804 crossref_primary_10_1109_JSEN_2024_3355388 crossref_primary_10_1109_TIP_2024_3381833 crossref_primary_10_3390_geomatics5010009 crossref_primary_10_1016_j_ijcard_2024_131945 crossref_primary_10_1016_j_bspc_2024_107140 crossref_primary_10_1016_j_compbiomed_2024_108386 crossref_primary_10_1016_j_cviu_2024_104148 crossref_primary_10_1109_TGRS_2023_3242987 crossref_primary_10_3389_frobt_2024_1387491 crossref_primary_10_1109_TGRS_2024_3502768 crossref_primary_10_1109_TIM_2022_3165270 crossref_primary_10_1007_s00371_022_02508_z crossref_primary_10_1016_j_displa_2023_102496 crossref_primary_10_1109_TII_2024_3366221 crossref_primary_10_1016_j_ultrasmedbio_2022_08_003 crossref_primary_10_1109_ACCESS_2021_3112174 crossref_primary_10_1016_j_patcog_2025_111506 crossref_primary_10_1109_TGRS_2024_3379380 crossref_primary_10_1016_j_compbiomed_2022_105546 crossref_primary_10_1109_TIM_2023_3310088 crossref_primary_10_1016_j_cviu_2025_104436 crossref_primary_10_1109_ACCESS_2023_3263179 crossref_primary_10_1016_j_bspc_2024_107393 crossref_primary_10_1016_j_measurement_2025_116777 crossref_primary_10_1007_s00371_024_03442_y crossref_primary_10_3390_ijgi11040256 crossref_primary_10_1016_j_engappai_2023_107741 crossref_primary_10_1109_TIP_2025_3587588 crossref_primary_10_1109_ACCESS_2021_3134196 crossref_primary_10_1016_j_compag_2025_110132 crossref_primary_10_1016_j_istruc_2023_105640 crossref_primary_10_1109_ACCESS_2024_3496723 crossref_primary_10_3390_rs15051232 crossref_primary_10_1016_j_media_2025_103510 crossref_primary_10_1016_j_eswa_2023_121568 crossref_primary_10_3390_rs15051235 crossref_primary_10_1016_j_neunet_2025_107972 crossref_primary_10_1016_j_patcog_2023_110085 crossref_primary_10_1109_ACCESS_2022_3223424 crossref_primary_10_1016_j_jvcir_2025_104452 crossref_primary_10_3390_f15020288 crossref_primary_10_1109_ACCESS_2025_3568866 crossref_primary_10_1364_OL_559616 crossref_primary_10_3390_rs17142450 crossref_primary_10_1109_ACCESS_2024_3394048 crossref_primary_10_1016_j_displa_2024_102792 crossref_primary_10_1038_s41598_025_13890_8 crossref_primary_10_1145_3589002 crossref_primary_10_3233_JIFS_231440 crossref_primary_10_1177_20552076241259664 crossref_primary_10_1007_s11265_022_01816_w crossref_primary_10_3390_s22249834 crossref_primary_10_1007_s10489_022_04416_0 crossref_primary_10_1016_j_neunet_2024_106353 crossref_primary_10_1016_j_engappai_2025_111579 crossref_primary_10_20965_jrm_2025_p0292 crossref_primary_10_3390_atmos15070752 crossref_primary_10_1177_13694332241260136 crossref_primary_10_3390_rs15215264 crossref_primary_10_1007_s11042_023_14596_7 crossref_primary_10_1177_00405175251335188 crossref_primary_10_1016_j_neucom_2023_126530 crossref_primary_10_1038_s41598_022_19013_x crossref_primary_10_1371_journal_pone_0299392 crossref_primary_10_3390_e22101174 crossref_primary_10_1007_s00034_025_03269_5 crossref_primary_10_3390_math9192498 crossref_primary_10_1109_TIP_2024_3497802 crossref_primary_10_1049_ipr2_12115 crossref_primary_10_3390_drones9050342 crossref_primary_10_1016_j_knosys_2025_113385 crossref_primary_10_1016_j_compbiomed_2024_108184 crossref_primary_10_1016_j_measurement_2024_116208 crossref_primary_10_3390_s25082589 crossref_primary_10_1109_TMM_2023_3325962 crossref_primary_10_3390_rs17142473 crossref_primary_10_1016_j_patcog_2024_110330 crossref_primary_10_1007_s00371_024_03375_6 crossref_primary_10_1007_s10044_024_01307_7 crossref_primary_10_3724_j_gyjzG25062002 crossref_primary_10_1134_S00051179220100034 crossref_primary_10_1016_j_atech_2025_100811 crossref_primary_10_1109_TIM_2024_3457951 crossref_primary_10_1007_s00521_022_08059_7 crossref_primary_10_1007_s10489_024_05274_8 crossref_primary_10_1109_TIP_2024_3504282 crossref_primary_10_1007_s11760_023_02905_4 crossref_primary_10_1016_j_neucom_2023_126560 crossref_primary_10_1109_TMM_2023_3330082 crossref_primary_10_1016_j_jvcir_2023_104040 crossref_primary_10_1007_s11517_024_03123_x crossref_primary_10_3390_rs16040643 crossref_primary_10_1007_s00170_024_13275_7 crossref_primary_10_1109_TMM_2023_3325731 crossref_primary_10_1016_j_cmpb_2020_105837 crossref_primary_10_1007_s00530_025_01727_3 crossref_primary_10_1016_j_compag_2022_107542 crossref_primary_10_1016_j_compbiomed_2024_109046 crossref_primary_10_1016_j_jobe_2025_112927 crossref_primary_10_1109_LSP_2025_3560237 crossref_primary_10_1016_j_compag_2025_110338 crossref_primary_10_1109_JSEN_2022_3178119 crossref_primary_10_1016_j_bspc_2023_105711 crossref_primary_10_1016_j_dsp_2022_103425 crossref_primary_10_3233_THC_230690 crossref_primary_10_3390_plants12183209 crossref_primary_10_3390_rs13112220 crossref_primary_10_1002_jsid_1185 crossref_primary_10_1007_s00138_024_01552_0 crossref_primary_10_1002_mp_16615 crossref_primary_10_1155_2023_8212790 crossref_primary_10_1080_14680629_2025_2549572 crossref_primary_10_1007_s11063_023_11333_x crossref_primary_10_1016_j_compmedimag_2025_102573 crossref_primary_10_1016_j_patcog_2024_110554 crossref_primary_10_1109_JSTARS_2025_3571455 crossref_primary_10_1007_s00107_025_02318_9 crossref_primary_10_1061_JPCFEV_CFENG_4952 crossref_primary_10_1038_s41597_025_05670_w crossref_primary_10_1186_s40494_024_01221_5 crossref_primary_10_1016_j_optlastec_2023_109331 crossref_primary_10_1109_JSTARS_2024_3429491 crossref_primary_10_1007_s11265_022_01801_3 crossref_primary_10_1016_j_bspc_2021_103165 crossref_primary_10_3390_s24165305 crossref_primary_10_1109_TMC_2022_3185134 crossref_primary_10_1109_TMM_2023_3331196 crossref_primary_10_1016_j_bspc_2023_104608 crossref_primary_10_1016_j_knosys_2020_106647 crossref_primary_10_1109_JBHI_2023_3323533 crossref_primary_10_1007_s11554_023_01394_5 crossref_primary_10_3390_electronics13061006 crossref_primary_10_1016_j_ijdrr_2025_105655 crossref_primary_10_1016_j_apacoust_2021_108499 crossref_primary_10_1109_TAES_2025_3544613 crossref_primary_10_1016_j_bspc_2024_107171 crossref_primary_10_1109_JIOT_2025_3539867 crossref_primary_10_1049_ipr2_13012 crossref_primary_10_1002_mp_17730 crossref_primary_10_1002_mp_17735 crossref_primary_10_1109_TASE_2024_3506617 crossref_primary_10_1016_j_patcog_2022_109099 crossref_primary_10_3390_electronics12143129 crossref_primary_10_1088_2631_8695_addb9c crossref_primary_10_1007_s00500_021_06388_8 crossref_primary_10_1109_ACCESS_2022_3175864 crossref_primary_10_1016_j_neunet_2025_107553 crossref_primary_10_1016_j_engstruct_2024_119262 crossref_primary_10_1108_IJCST_04_2024_0096 crossref_primary_10_1007_s00371_024_03607_9 crossref_primary_10_1016_j_compag_2024_109817 crossref_primary_10_1007_s10278_023_00947_1 crossref_primary_10_1109_TITS_2024_3384018 crossref_primary_10_1007_s11761_023_00373_9 crossref_primary_10_1016_j_patcog_2024_110650 crossref_primary_10_1109_LRA_2023_3257707 crossref_primary_10_1007_s11263_023_01801_1 crossref_primary_10_1016_j_bspc_2024_107426 crossref_primary_10_1016_j_dsp_2025_105534 crossref_primary_10_1016_j_ultrasmedbio_2023_08_003 crossref_primary_10_1109_TITS_2024_3510116 crossref_primary_10_1016_j_compbiomed_2023_107844 crossref_primary_10_1109_ACCESS_2023_3347812 crossref_primary_10_1109_JSEN_2023_3286373 crossref_primary_10_1109_TGRS_2024_3503589 crossref_primary_10_32604_cmc_2025_060793 crossref_primary_10_1109_TGRS_2024_3503588 crossref_primary_10_3390_electronics12061378 crossref_primary_10_1016_j_datak_2025_102411 crossref_primary_10_1016_j_engappai_2025_110507 crossref_primary_10_1109_JOE_2023_3252760 crossref_primary_10_3390_app13116512 crossref_primary_10_1016_j_imavis_2025_105670 crossref_primary_10_1016_j_neunet_2023_01_031 crossref_primary_10_1007_s00371_024_03636_4 crossref_primary_10_1109_ACCESS_2024_3388090 crossref_primary_10_1109_LSP_2021_3128374 crossref_primary_10_1016_j_dsp_2025_105547 crossref_primary_10_1186_s12886_025_03908_0 crossref_primary_10_1016_j_solener_2023_112282 crossref_primary_10_1109_ACCESS_2024_3373619 crossref_primary_10_1002_ima_70041 crossref_primary_10_1364_AO_553741 crossref_primary_10_1016_j_renene_2025_122926 crossref_primary_10_1016_j_neucom_2023_127206 crossref_primary_10_1155_2022_4792532 crossref_primary_10_1016_j_patcog_2021_107994 crossref_primary_10_1186_s40494_024_01470_4 crossref_primary_10_1109_ACCESS_2023_3289952 crossref_primary_10_1109_TCSVT_2021_3093890 crossref_primary_10_1109_ACCESS_2023_3289957 crossref_primary_10_1049_ipr2_12631 crossref_primary_10_1177_13694332241242975 crossref_primary_10_3390_a15080281 crossref_primary_10_1016_j_eswa_2024_123518 crossref_primary_10_1109_TASE_2024_3370147 crossref_primary_10_1016_j_patrec_2025_03_012 crossref_primary_10_1016_j_bspc_2025_107961 crossref_primary_10_1007_s00371_021_02222_2 crossref_primary_10_1109_LSP_2025_3545306 crossref_primary_10_3390_rs15082119 crossref_primary_10_1016_j_istruc_2023_02_010 crossref_primary_10_1016_j_neucom_2025_131125 crossref_primary_10_3390_pr12071337 crossref_primary_10_1109_TGRS_2021_3073840 crossref_primary_10_1016_j_imavis_2021_104243 crossref_primary_10_1117_1_JEI_33_4_043047 crossref_primary_10_3390_rs14184647 crossref_primary_10_1016_j_csbj_2023_06_017 crossref_primary_10_1016_j_eswa_2025_129349 crossref_primary_10_1109_TGRS_2025_3588415 crossref_primary_10_1088_1361_6501_adbeed crossref_primary_10_1038_s41598_025_98938_5 crossref_primary_10_3389_fenvs_2025_1566224 crossref_primary_10_1080_15732479_2024_2363832 crossref_primary_10_1007_s00784_024_06061_y crossref_primary_10_3390_buildings13020285 crossref_primary_10_1016_j_patcog_2024_110648 crossref_primary_10_1038_s41598_024_71194_9 crossref_primary_10_3390_rs13163187 crossref_primary_10_1038_s41598_024_67113_7 crossref_primary_10_3788_AOS250859 crossref_primary_10_1016_j_imavis_2022_104536 crossref_primary_10_1038_s41598_023_31551_6 crossref_primary_10_1109_LGRS_2022_3187760 crossref_primary_10_1111_mice_12710 crossref_primary_10_3390_jmmp8020066 crossref_primary_10_3390_math11244890 crossref_primary_10_1016_j_patcog_2024_110615 crossref_primary_10_1016_j_cviu_2025_104471 crossref_primary_10_1016_j_engappai_2024_108591 crossref_primary_10_3390_info14070366 crossref_primary_10_1016_j_patcog_2021_108414 crossref_primary_10_3390_ani12091223 crossref_primary_10_1007_s00521_022_07612_8 crossref_primary_10_1016_j_compbiomed_2023_106792 crossref_primary_10_1145_3647999 crossref_primary_10_1016_j_ymssp_2023_110484 crossref_primary_10_1049_ipr2_12888 crossref_primary_10_1109_ACCESS_2024_3378097 crossref_primary_10_1109_ACCESS_2024_3463713 crossref_primary_10_1186_s40644_022_00457_3 crossref_primary_10_1088_1361_6501_ad4ab5 crossref_primary_10_1109_JOE_2022_3190517 crossref_primary_10_1109_TII_2025_3558324 crossref_primary_10_1140_epjs_s11734_025_01950_z crossref_primary_10_3390_insects15070557 crossref_primary_10_1016_j_measurement_2023_112497 crossref_primary_10_1109_JSTARS_2024_3472908 crossref_primary_10_1109_ACCESS_2025_3555321 crossref_primary_10_1190_geo2020_0945_1 crossref_primary_10_1109_TGRS_2024_3394901 crossref_primary_10_1016_j_compag_2025_110058 crossref_primary_10_1016_j_imavis_2025_105487 crossref_primary_10_1007_s11063_024_11662_5 crossref_primary_10_1109_JSTSP_2020_3043064 crossref_primary_10_1016_j_patcog_2022_108943 crossref_primary_10_1016_j_cviu_2022_103514 crossref_primary_10_1007_s00371_025_03899_5 crossref_primary_10_1038_s41598_024_75715_4 crossref_primary_10_1109_TASLP_2022_3184889 crossref_primary_10_1371_journal_pone_0311228 crossref_primary_10_1016_j_compeleceng_2022_108525 crossref_primary_10_1016_j_engappai_2024_109459 crossref_primary_10_1016_j_measurement_2025_118966 crossref_primary_10_3390_rs16224305 crossref_primary_10_3390_rs17183162 crossref_primary_10_3390_rs17040707 crossref_primary_10_1007_s11263_025_02431_5 crossref_primary_10_3390_app13148526 crossref_primary_10_1016_j_patcog_2025_112092 crossref_primary_10_1016_j_compbiomed_2023_107665 crossref_primary_10_1016_j_engappai_2024_109467 crossref_primary_10_3390_agriculture14020244 crossref_primary_10_7717_peerj_cs_2146 crossref_primary_10_1109_LSP_2021_3128375 crossref_primary_10_3390_s24175505 crossref_primary_10_1049_ipr2_12425 crossref_primary_10_1109_JSTARS_2024_3441644 crossref_primary_10_1016_j_imavis_2022_104508 crossref_primary_10_1016_j_engappai_2025_111829 crossref_primary_10_1016_j_knosys_2022_108901 crossref_primary_10_1109_JBHI_2022_3153793 crossref_primary_10_1007_s41365_024_01528_9 crossref_primary_10_1007_s11042_024_18291_z crossref_primary_10_1016_j_autcon_2024_105934 crossref_primary_10_1016_j_compbiomed_2024_108819 crossref_primary_10_1016_j_compag_2025_110078 crossref_primary_10_1109_ACCESS_2023_3346933 crossref_primary_10_3390_electronics12132880 crossref_primary_10_1016_j_cemconcomp_2025_106272 crossref_primary_10_1016_j_fbio_2023_102848 crossref_primary_10_1109_ACCESS_2024_3438551 crossref_primary_10_1109_TCSVT_2022_3185252 crossref_primary_10_1007_s11760_023_02765_y crossref_primary_10_3390_s25123646 crossref_primary_10_1016_j_engappai_2025_110974 crossref_primary_10_1109_ACCESS_2023_3264014 crossref_primary_10_1109_ACCESS_2023_3294476 crossref_primary_10_1016_j_cviu_2024_103975 crossref_primary_10_1016_j_eswa_2024_125759 crossref_primary_10_1016_j_powtec_2024_120583 crossref_primary_10_3390_rs15235441 crossref_primary_10_1016_j_jag_2023_103242 crossref_primary_10_1109_JTEHM_2023_3289990 crossref_primary_10_1016_j_compbiomed_2023_107203 crossref_primary_10_1109_LSP_2023_3329307 crossref_primary_10_3390_coatings12111730 crossref_primary_10_1177_00368504251318202 crossref_primary_10_1016_j_neunet_2023_03_041 crossref_primary_10_1007_s12530_023_09489_x crossref_primary_10_1038_s41598_022_14879_3 crossref_primary_10_1109_LGRS_2023_3235117 crossref_primary_10_3724_SP_J_1089_2022_18927 crossref_primary_10_1109_ACCESS_2023_3298826 crossref_primary_10_1016_j_scitotenv_2023_169113 crossref_primary_10_1016_j_eswa_2024_125505 crossref_primary_10_1016_j_engappai_2025_110917 crossref_primary_10_1109_ACCESS_2024_3465534 crossref_primary_10_1109_TCSVT_2024_3417607 crossref_primary_10_3390_rs13010060 crossref_primary_10_1007_s11770_024_1085_8 crossref_primary_10_1016_j_aei_2025_103743 crossref_primary_10_1016_j_bspc_2024_106983 crossref_primary_10_1080_10447318_2025_2537795 crossref_primary_10_1109_TGRS_2023_3339970 crossref_primary_10_1016_j_engappai_2024_108782 crossref_primary_10_1016_j_optlastec_2025_113684 crossref_primary_10_1007_s10489_024_05359_4 crossref_primary_10_1371_journal_pone_0299732 crossref_primary_10_1016_j_powtec_2024_119582 crossref_primary_10_1109_ACCESS_2025_3551604 crossref_primary_10_1109_ACCESS_2023_3322371 crossref_primary_10_3390_diagnostics15141744 crossref_primary_10_1016_j_eswa_2024_124446 crossref_primary_10_3390_rs17060952 crossref_primary_10_3390_rs14174211 crossref_primary_10_1016_j_patcog_2021_108231 crossref_primary_10_1109_TIP_2024_3393365 crossref_primary_10_3390_rs17111902 crossref_primary_10_1109_ACCESS_2023_3254430 crossref_primary_10_1109_JSTARS_2024_3397488 crossref_primary_10_1016_j_ijfatigue_2024_108667 crossref_primary_10_2196_45299 crossref_primary_10_1007_s00371_024_03295_5 crossref_primary_10_1016_j_jvcir_2021_103231 crossref_primary_10_1016_j_compag_2024_109436 crossref_primary_10_1109_TPAMI_2023_3305630 crossref_primary_10_1016_j_ins_2023_119460 crossref_primary_10_1016_j_neucom_2025_129691 crossref_primary_10_1007_s11042_024_19357_8 crossref_primary_10_1038_s41598_023_27883_y crossref_primary_10_1109_LGRS_2023_3249764 crossref_primary_10_1038_s41746_025_01753_5 crossref_primary_10_1016_j_compbiomed_2022_106090 crossref_primary_10_1088_1361_6501_acb80b crossref_primary_10_1016_j_compbiomed_2025_109841 crossref_primary_10_1016_j_neucom_2021_08_039 crossref_primary_10_1080_10739149_2025_2479482 crossref_primary_10_1007_s00521_023_08545_6 crossref_primary_10_3389_fncom_2023_1113381 crossref_primary_10_1109_TGRS_2024_3389750 crossref_primary_10_1111_mice_13437 crossref_primary_10_1109_JBHI_2024_3446623 crossref_primary_10_1016_j_bspc_2023_105330 crossref_primary_10_1007_s11517_025_03333_x crossref_primary_10_1016_j_compbiomed_2024_108616 crossref_primary_10_1016_j_engappai_2024_109890 crossref_primary_10_1016_j_patcog_2021_108469 crossref_primary_10_1016_j_bspc_2023_105329 crossref_primary_10_1016_j_patcog_2022_108523 crossref_primary_10_1016_j_patcog_2023_109514 crossref_primary_10_3390_rs15204931 crossref_primary_10_1007_s10618_025_01129_z crossref_primary_10_1007_s11760_024_03034_2 crossref_primary_10_1109_TAP_2025_3553767 crossref_primary_10_1109_LSP_2023_3283541 crossref_primary_10_1038_s41598_023_36298_8 crossref_primary_10_3390_diagnostics11071246 crossref_primary_10_1007_s10554_025_03342_9 crossref_primary_10_1007_s11042_023_15343_8 crossref_primary_10_1016_j_isprsjprs_2024_10_016 crossref_primary_10_1111_mice_13401 crossref_primary_10_1007_s10044_024_01379_5 crossref_primary_10_1109_LGRS_2021_3068132 crossref_primary_10_1109_TMM_2024_3354622 crossref_primary_10_1016_j_envsoft_2025_106629 crossref_primary_10_1038_s41598_025_10506_z crossref_primary_10_1016_j_compbiolchem_2025_108496 crossref_primary_10_1109_TGRS_2025_3598446 crossref_primary_10_3390_app14125007 crossref_primary_10_1016_j_engappai_2024_108751 crossref_primary_10_3390_rs15204900 crossref_primary_10_1111_phor_12530 crossref_primary_10_3390_s23157008 crossref_primary_10_1016_j_patcog_2025_112232 crossref_primary_10_1007_s11760_025_04740_1 crossref_primary_10_3390_rs15123094 crossref_primary_10_3390_s22218245 crossref_primary_10_3390_s23167284 crossref_primary_10_1016_j_eswa_2024_124698 crossref_primary_10_1016_j_asoc_2021_108326 crossref_primary_10_1016_j_inffus_2024_102445 crossref_primary_10_3390_app13053168 crossref_primary_10_1016_j_jksuci_2022_04_011 crossref_primary_10_1016_j_jvcir_2023_103856 crossref_primary_10_1016_j_patcog_2022_108782 crossref_primary_10_1109_JBHI_2024_3445112 crossref_primary_10_3389_fnagi_2022_1073909 crossref_primary_10_1007_s11042_023_14875_3 crossref_primary_10_1016_j_optlastec_2025_112554 crossref_primary_10_1109_JBHI_2025_3556709 crossref_primary_10_1007_s11042_024_19368_5 crossref_primary_10_1109_LGRS_2024_3372807 crossref_primary_10_3390_app15105432 crossref_primary_10_1016_j_knosys_2024_112132 crossref_primary_10_1016_j_knosys_2022_108996 crossref_primary_10_3390_s24227159 crossref_primary_10_3390_plants10061257 crossref_primary_10_3390_rs15071821 crossref_primary_10_1080_24751839_2024_2367387 crossref_primary_10_1016_j_imavis_2024_104956 crossref_primary_10_1007_s11082_023_05766_w crossref_primary_10_1177_08953996241299998 crossref_primary_10_1016_j_procs_2024_09_167 crossref_primary_10_1016_j_engappai_2024_108530 crossref_primary_10_1016_j_compbiomed_2025_110806 crossref_primary_10_1109_TCSVT_2023_3336068 crossref_primary_10_32604_cmc_2023_038059 crossref_primary_10_1007_s11263_025_02560_x crossref_primary_10_1109_TIM_2024_3522705 crossref_primary_10_1109_TCSVT_2022_3166914 crossref_primary_10_1016_j_infrared_2024_105489 crossref_primary_10_1088_2057_1976_ad6f12 crossref_primary_10_1016_j_cie_2024_110301 crossref_primary_10_1016_j_postharvbio_2024_113130 crossref_primary_10_1016_j_istruc_2025_110086 crossref_primary_10_1109_TMM_2023_3293994 crossref_primary_10_1016_j_displa_2023_102601 crossref_primary_10_1016_j_eswa_2023_120812 crossref_primary_10_1016_j_neucom_2025_129648 crossref_primary_10_1109_TCSVT_2023_3283705 crossref_primary_10_1177_03611981251320388 crossref_primary_10_3390_rs16010009 crossref_primary_10_1007_s11517_024_03205_w crossref_primary_10_1109_TGRS_2024_3443280 crossref_primary_10_1109_ACCESS_2024_3523200 crossref_primary_10_3389_fcvm_2025_1606159 crossref_primary_10_3390_bioengineering11101047 crossref_primary_10_1016_j_compmedimag_2023_102307 crossref_primary_10_1016_j_eswa_2024_125562 crossref_primary_10_3390_app14114371 crossref_primary_10_1007_s10489_023_04636_y crossref_primary_10_1049_ipr2_13145 crossref_primary_10_1002_mp_17482 crossref_primary_10_1109_TAP_2025_3577780 crossref_primary_10_1016_j_measurement_2024_115432 crossref_primary_10_1186_s13636_021_00226_3 crossref_primary_10_1109_TETCI_2024_3375022 crossref_primary_10_1007_s11517_022_02563_7 crossref_primary_10_1109_JSTARS_2023_3339241 crossref_primary_10_1016_j_jvcir_2024_104237 crossref_primary_10_1016_j_inffus_2025_103165 crossref_primary_10_1109_LGRS_2022_3166347 crossref_primary_10_3390_rs13173527 crossref_primary_10_1016_j_jfoodeng_2024_112126 crossref_primary_10_3390_s25185783 crossref_primary_10_1109_TGRS_2024_3421950 crossref_primary_10_1093_comjnl_bxae112 crossref_primary_10_1016_j_eswa_2023_120987 crossref_primary_10_1109_TITS_2022_3166208 crossref_primary_10_1007_s44295_025_00070_7 crossref_primary_10_1016_j_neucom_2024_129110 crossref_primary_10_1109_JSTARS_2025_3582803 crossref_primary_10_3390_s25061720 crossref_primary_10_1016_j_mtcomm_2025_112727 crossref_primary_10_1109_TGRS_2025_3550867 crossref_primary_10_1002_jsfa_14355 crossref_primary_10_1016_j_inffus_2025_103399 crossref_primary_10_1109_JSTARS_2024_3474849 crossref_primary_10_1007_s11263_024_02024_8 crossref_primary_10_1109_ACCESS_2023_3268114 crossref_primary_10_1016_j_eswa_2025_126853 crossref_primary_10_1016_j_compbiomed_2024_108431 crossref_primary_10_1007_s00500_023_07936_0 crossref_primary_10_1109_ACCESS_2024_3524316 crossref_primary_10_1016_j_matchar_2025_115198 crossref_primary_10_1016_j_jclepro_2024_143024 crossref_primary_10_3390_rs14164001 crossref_primary_10_1109_JIOT_2023_3343758 crossref_primary_10_1515_jisys_2024_0185 crossref_primary_10_1007_s00530_024_01640_1 crossref_primary_10_1016_j_engappai_2023_106142 crossref_primary_10_1016_j_procs_2025_04_301 crossref_primary_10_1080_01431161_2022_2107411 crossref_primary_10_1007_s00259_023_06418_7 crossref_primary_10_1109_TCPMT_2024_3428595 crossref_primary_10_1016_j_ins_2023_01_106 crossref_primary_10_1016_j_patcog_2024_111193 crossref_primary_10_1109_TIM_2024_3460882 crossref_primary_10_1109_JSEN_2023_3305681 crossref_primary_10_1109_TMM_2023_3270629 crossref_primary_10_1109_TGRS_2025_3579272 crossref_primary_10_1016_j_jvcir_2024_104257 crossref_primary_10_1109_ACCESS_2025_3563459 crossref_primary_10_1109_TCSI_2024_3521933 crossref_primary_10_1016_j_cam_2023_115551 crossref_primary_10_1109_JSTARS_2025_3540394 crossref_primary_10_3390_app15116358 crossref_primary_10_3390_coatings12101551 crossref_primary_10_1016_j_eswa_2022_119218 crossref_primary_10_3390_fire6050192 crossref_primary_10_3390_s23115344 crossref_primary_10_1016_j_compbiomed_2021_104673 crossref_primary_10_1016_j_neucom_2024_128045 crossref_primary_10_1109_LSP_2022_3151549 crossref_primary_10_3390_app15105225 crossref_primary_10_1109_TNSRE_2024_3394738 crossref_primary_10_1016_j_compbiomed_2024_109300 crossref_primary_10_1016_j_neucom_2022_05_023 crossref_primary_10_1109_JBHI_2023_3259802 crossref_primary_10_1109_JSEN_2022_3229031 crossref_primary_10_1109_TPAMI_2024_3350450 crossref_primary_10_1016_j_compbiomed_2021_104688 crossref_primary_10_1007_s11760_022_02310_3 crossref_primary_10_1007_s13246_024_01457_2 crossref_primary_10_1016_j_asoc_2025_112841 crossref_primary_10_1109_TGRS_2024_3497579 crossref_primary_10_1007_s11760_024_03477_7 crossref_primary_10_1016_j_bspc_2023_105605 crossref_primary_10_1016_j_jvcir_2024_104271 crossref_primary_10_1109_TVCG_2023_3332950 crossref_primary_10_1109_JSEN_2024_3381928 crossref_primary_10_1088_1361_6579_ac6049 crossref_primary_10_1109_TIM_2023_3302376 crossref_primary_10_3390_insects14020099 crossref_primary_10_1007_s00371_022_02597_w crossref_primary_10_1109_TCSVT_2024_3449070 crossref_primary_10_3390_electronics10222756 crossref_primary_10_3390_s25185743 crossref_primary_10_1016_j_compbiomed_2021_105107 crossref_primary_10_1016_j_infrared_2024_105310 crossref_primary_10_12677_AAM_2023_1211478 crossref_primary_10_1051_jnwpu_20244220335 crossref_primary_10_1007_s10489_022_03917_2 crossref_primary_10_1038_s41598_024_74690_0 crossref_primary_10_1109_TGRS_2023_3338611 crossref_primary_10_1016_j_apenergy_2025_126548 crossref_primary_10_7717_peerj_cs_1751 crossref_primary_10_1109_LGRS_2021_3093101 crossref_primary_10_1109_ACCESS_2020_3025372 crossref_primary_10_1109_TIM_2023_3252632 crossref_primary_10_5194_amt_17_3029_2024 crossref_primary_10_1007_s11042_023_17678_8 crossref_primary_10_1109_LGRS_2025_3596932 crossref_primary_10_1109_TITS_2024_3413675 crossref_primary_10_3390_rs15123121 crossref_primary_10_1109_TGRS_2023_3243769 crossref_primary_10_1016_j_bspc_2022_104243 crossref_primary_10_1007_s40747_025_02015_3 crossref_primary_10_1111_mice_13018 crossref_primary_10_1016_j_bspc_2024_105970 crossref_primary_10_3390_s25133904 crossref_primary_10_1080_00140139_2024_2449113 crossref_primary_10_1016_j_compag_2024_109560 crossref_primary_10_1016_j_eswa_2023_121407 crossref_primary_10_3390_s23073691 crossref_primary_10_1016_j_eswa_2023_122736 crossref_primary_10_1007_s11042_023_15505_8 crossref_primary_10_1109_JBHI_2024_3512584 crossref_primary_10_3390_rs14122884 crossref_primary_10_1080_17538947_2024_2346258 crossref_primary_10_1016_j_softx_2025_102110 crossref_primary_10_1109_TCSVT_2023_3269951 crossref_primary_10_3390_photonics12060588 crossref_primary_10_1016_j_ascom_2024_100881 crossref_primary_10_1016_j_mtcomm_2024_110480 crossref_primary_10_1109_JSTARS_2025_3555849 crossref_primary_10_1109_TETCI_2024_3462854 crossref_primary_10_1007_s10462_025_11207_9 crossref_primary_10_1109_LGRS_2024_3437743 crossref_primary_10_1007_s11042_023_15823_x crossref_primary_10_1117_1_JOM_5_2_024504 crossref_primary_10_1186_s13007_025_01392_7 crossref_primary_10_3390_rs14061523 crossref_primary_10_1016_j_media_2025_103480 crossref_primary_10_1016_j_compbiomed_2024_108250 crossref_primary_10_1016_j_compbiomed_2024_108010 crossref_primary_10_3389_fmats_2021_761229 crossref_primary_10_3390_s22103960 crossref_primary_10_12677_csa_2025_155138 crossref_primary_10_1016_j_media_2021_102205 crossref_primary_10_12677_met_2024_135046 crossref_primary_10_1007_s00371_024_03421_3 crossref_primary_10_1038_s41598_024_63538_2 crossref_primary_10_1109_JSTARS_2021_3123398 crossref_primary_10_2478_amns_2023_2_01579 crossref_primary_10_1049_ipr2_70184 crossref_primary_10_1109_TPAMI_2025_3562237 crossref_primary_10_1186_s13007_023_01045_7 crossref_primary_10_1109_TAP_2025_3533739 crossref_primary_10_1038_s41598_023_42190_2 crossref_primary_10_1109_TETCI_2023_3259433 crossref_primary_10_1016_j_neucom_2021_09_020 crossref_primary_10_1016_j_sigpro_2020_107896 crossref_primary_10_1109_TIM_2021_3126847 crossref_primary_10_3390_agriculture15161752 crossref_primary_10_1016_j_bspc_2025_108635 crossref_primary_10_3390_machines10121172 crossref_primary_10_3390_app14167234 crossref_primary_10_1088_1361_6560_acf641 crossref_primary_10_1016_j_solener_2025_113646 crossref_primary_10_1109_JIOT_2022_3158886 crossref_primary_10_1109_ACCESS_2025_3555654 crossref_primary_10_1007_s10851_023_01156_9 crossref_primary_10_1016_j_media_2023_103066 crossref_primary_10_1109_TIM_2022_3216399 crossref_primary_10_3389_fnins_2021_687832 crossref_primary_10_1016_j_bspc_2025_107772 crossref_primary_10_1038_s41598_024_74445_x crossref_primary_10_1016_j_compbiomed_2024_108039 crossref_primary_10_1155_2022_7780756 crossref_primary_10_1109_JBHI_2024_3487630 crossref_primary_10_1109_TIM_2023_3325447 crossref_primary_10_1109_JSEN_2024_3409769 crossref_primary_10_3390_bioengineering11070682 crossref_primary_10_1364_OE_575920 crossref_primary_10_3390_rs15215168 crossref_primary_10_1002_ima_70207 crossref_primary_10_1109_ACCESS_2023_3344813 crossref_primary_10_1002_ima_22926 crossref_primary_10_1016_j_conbuildmat_2023_134134 crossref_primary_10_1002_ima_22929 crossref_primary_10_1016_j_jksuci_2023_101838 crossref_primary_10_1109_ACCESS_2024_3426518 crossref_primary_10_1109_TIM_2024_3420348 crossref_primary_10_1109_TIM_2024_3421436 crossref_primary_10_3390_s25103035 crossref_primary_10_1016_j_biosystemseng_2024_05_011 crossref_primary_10_1109_TGRS_2024_3439401 crossref_primary_10_1007_s10489_024_05507_w crossref_primary_10_1016_j_ultrasmedbio_2024_05_027 crossref_primary_10_1109_TCSVT_2023_3260025 crossref_primary_10_1186_s40494_023_01009_z crossref_primary_10_1016_j_eswa_2025_126690 crossref_primary_10_1016_j_snb_2025_137800 crossref_primary_10_1049_ipr2_12475 crossref_primary_10_1109_TASLP_2023_3313442 crossref_primary_10_1016_j_cageo_2025_105999 crossref_primary_10_3390_app14114724 crossref_primary_10_1121_10_0024348 crossref_primary_10_1016_j_patcog_2022_109166 crossref_primary_10_3389_fmars_2022_1003568 crossref_primary_10_3390_s25072207 crossref_primary_10_1016_j_knosys_2025_114127 crossref_primary_10_1109_TGRS_2024_3362836 crossref_primary_10_1155_2024_1866665 crossref_primary_10_3390_rs14112611 crossref_primary_10_3390_app13095430 crossref_primary_10_1007_s00371_024_03639_1 crossref_primary_10_1109_TIP_2022_3232209 crossref_primary_10_1007_s11263_024_02020_y crossref_primary_10_1016_j_isprsjprs_2022_11_009 crossref_primary_10_1016_j_patcog_2022_109170 crossref_primary_10_1016_j_cmpb_2025_109065 crossref_primary_10_1016_j_eswa_2024_123903 crossref_primary_10_3390_app13052975 crossref_primary_10_1109_TGRS_2024_3359684 crossref_primary_10_1016_j_compag_2025_110270 crossref_primary_10_1109_JSTARS_2024_3422793 crossref_primary_10_1007_s00530_024_01509_3 crossref_primary_10_1007_s11760_025_04639_x crossref_primary_10_3103_S1060992X24700899 crossref_primary_10_1145_3528223_3530068 crossref_primary_10_3390_app13169402 crossref_primary_10_1227_ons_0000000000001023 crossref_primary_10_1177_20552076241307573 crossref_primary_10_3390_universe10100381 crossref_primary_10_1007_s12274_023_6104_1 crossref_primary_10_1109_ACCESS_2022_3197752 crossref_primary_10_1007_s10586_024_04292_y crossref_primary_10_1016_j_engappai_2025_110300 crossref_primary_10_1016_j_atech_2023_100383 crossref_primary_10_1016_j_bspc_2023_105833 crossref_primary_10_1088_1361_6560_ad1210 crossref_primary_10_1109_ACCESS_2024_3387413 crossref_primary_10_1088_1742_6596_3072_1_012004 crossref_primary_10_1177_14759217221140976 crossref_primary_10_3390_electronics13040680 crossref_primary_10_1002_acm2_14390 crossref_primary_10_1016_j_bspc_2024_107074 crossref_primary_10_1016_j_patrec_2023_12_025 crossref_primary_10_1109_JSEN_2024_3484468 crossref_primary_10_1016_j_ijleo_2022_169944 crossref_primary_10_1109_TCSVT_2022_3212088 crossref_primary_10_3390_f15010127 crossref_primary_10_1007_s12559_022_10094_4 crossref_primary_10_3389_fcomp_2024_1420965 crossref_primary_10_1016_j_neunet_2023_09_041 crossref_primary_10_1016_j_engappai_2025_110550 crossref_primary_10_1109_LRA_2023_3281906 crossref_primary_10_3390_rs17142359 crossref_primary_10_1109_ACCESS_2025_3532505 crossref_primary_10_3390_s23198337 crossref_primary_10_1007_s00371_025_03958_x crossref_primary_10_1155_aa_3232269 crossref_primary_10_1109_TGRS_2021_3131221 crossref_primary_10_32604_cmes_2022_020428 crossref_primary_10_1145_3711869 crossref_primary_10_1016_j_neucom_2022_03_006 crossref_primary_10_1016_j_bbe_2024_04_001 crossref_primary_10_1038_s41598_024_84575_x crossref_primary_10_1007_s00259_024_06618_9 crossref_primary_10_32604_cmes_2023_043832 crossref_primary_10_1109_JSEN_2024_3471175 crossref_primary_10_1016_j_neunet_2025_107207 crossref_primary_10_1016_j_cageo_2024_105628 crossref_primary_10_1007_s10916_021_01751_6 crossref_primary_10_1007_s11042_024_19503_2 crossref_primary_10_1109_TCSVT_2023_3286405 crossref_primary_10_1109_TPAMI_2024_3519674 crossref_primary_10_1016_j_measurement_2024_114371 crossref_primary_10_1016_j_heliyon_2024_e33892 crossref_primary_10_3390_rs13183707 crossref_primary_10_1016_j_ndteint_2024_103053 crossref_primary_10_1109_JBHI_2025_3535579 crossref_primary_10_1364_AO_426189 crossref_primary_10_1016_j_eswa_2023_120370 crossref_primary_10_1049_ipr2_13136 crossref_primary_10_1016_j_jvcir_2025_104522 crossref_primary_10_1109_TIM_2023_3323004 crossref_primary_10_1063_5_0216945 crossref_primary_10_1002_mp_17854 crossref_primary_10_3390_electronics12143009 crossref_primary_10_1371_journal_pone_0299471 crossref_primary_10_3390_s25175324 crossref_primary_10_1109_TAI_2024_3357437 crossref_primary_10_1109_LGRS_2022_3168391 crossref_primary_10_1109_LSP_2023_3313444 crossref_primary_10_1029_2024JH000355 crossref_primary_10_1016_j_cie_2025_111139 crossref_primary_10_1109_LSP_2022_3188178 crossref_primary_10_1109_TMM_2025_3535369 crossref_primary_10_3390_rs14030661 crossref_primary_10_1109_ACCESS_2022_3203405 crossref_primary_10_3390_bioengineering11060595 crossref_primary_10_34133_plantphenomics_0218 crossref_primary_10_3390_math12070940 crossref_primary_10_3390_s24051708 crossref_primary_10_1109_TGRS_2022_3197149 crossref_primary_10_1109_TMM_2022_3210366 crossref_primary_10_1007_s00521_022_07069_9 crossref_primary_10_1109_ACCESS_2024_3504399 crossref_primary_10_1016_j_engappai_2024_108277 crossref_primary_10_1016_j_imavis_2024_105039 crossref_primary_10_1016_j_softx_2024_101857 crossref_primary_10_1016_j_bspc_2025_107815 crossref_primary_10_1109_TPAMI_2022_3166451 crossref_primary_10_1186_s12880_025_01661_w crossref_primary_10_3390_jcm12010055 crossref_primary_10_1109_TGRS_2025_3562185 crossref_primary_10_3389_fonc_2021_717039 crossref_primary_10_1109_TGRS_2024_3480122 crossref_primary_10_3390_rs15174353 crossref_primary_10_1109_ACCESS_2022_3210190 crossref_primary_10_1038_s41598_025_85632_9 crossref_primary_10_1016_j_matchar_2024_114003 crossref_primary_10_3390_app13084842 crossref_primary_10_1109_TMM_2024_3414669 crossref_primary_10_1016_j_inffus_2023_02_019 crossref_primary_10_1016_j_bspc_2024_106223 crossref_primary_10_1007_s00521_023_08916_z crossref_primary_10_1049_itr2_12562 crossref_primary_10_1061_JAEIED_AEENG_1936 crossref_primary_10_1109_JSTARS_2024_3365729 crossref_primary_10_1109_TCSVT_2024_3471875 crossref_primary_10_1109_LGRS_2022_3218688 crossref_primary_10_1016_j_dsp_2023_103924 crossref_primary_10_1016_j_radonc_2024_110699 crossref_primary_10_1038_s41598_022_24660_1 crossref_primary_10_3390_app15158681 crossref_primary_10_1109_TPAMI_2022_3179526 crossref_primary_10_1007_s00371_025_03970_1 crossref_primary_10_1007_s11042_023_15217_z crossref_primary_10_1016_j_inffus_2025_103707 crossref_primary_10_1109_JBHI_2024_3447689 crossref_primary_10_1007_s11467_024_1394_7 crossref_primary_10_1016_j_cviu_2023_103751 crossref_primary_10_1002_cpe_7127 crossref_primary_10_1109_TIM_2024_3381277 crossref_primary_10_3389_fbioe_2023_1133090 crossref_primary_10_1016_j_istruc_2024_106863 crossref_primary_10_1016_j_jcis_2023_12_092 crossref_primary_10_3389_fmars_2024_1411527 crossref_primary_10_1016_j_engappai_2025_110880 crossref_primary_10_1038_s41598_024_84901_3 crossref_primary_10_1016_j_imavis_2024_105292 crossref_primary_10_1016_j_compag_2024_108866 crossref_primary_10_1177_1088467X251344933 crossref_primary_10_1177_03611981251329046 crossref_primary_10_1016_j_eswa_2024_123620 crossref_primary_10_3390_rs15174337 crossref_primary_10_1016_j_isprsjprs_2023_07_026 crossref_primary_10_1109_TVCG_2021_3109460 crossref_primary_10_1007_s11042_023_17517_w crossref_primary_10_1016_j_jag_2025_104387 crossref_primary_10_3389_fphys_2023_1296185 crossref_primary_10_3389_fpls_2022_964058 crossref_primary_10_1364_AO_504482 crossref_primary_10_3390_s25072158 crossref_primary_10_1016_j_dsp_2022_103841 crossref_primary_10_1016_j_cja_2023_10_015 crossref_primary_10_1016_j_measurement_2024_115092 crossref_primary_10_1017_qpb_2024_11 crossref_primary_10_1016_j_neucom_2023_127105 crossref_primary_10_3390_s23146450 crossref_primary_10_1016_j_cj_2023_04_012 crossref_primary_10_3389_fonc_2022_901475 crossref_primary_10_5753_jbcs_2025_4278 crossref_primary_10_3390_f15101711 crossref_primary_10_1016_j_media_2024_103307 crossref_primary_10_1109_TITS_2023_3293822 crossref_primary_10_1016_j_isprsjprs_2022_12_026 crossref_primary_10_1016_j_knosys_2021_106753 crossref_primary_10_1007_s10489_022_03604_2 crossref_primary_10_1109_TGRS_2025_3544549 crossref_primary_10_1109_TSM_2025_3546296 crossref_primary_10_32604_cmc_2023_035716 crossref_primary_10_1007_s11042_024_20542_y crossref_primary_10_1109_JSEN_2025_3593256 crossref_primary_10_1109_TGRS_2023_3340244 crossref_primary_10_1109_ACCESS_2024_3416450 crossref_primary_10_1109_LSP_2025_3545005 crossref_primary_10_1007_s00371_024_03713_8 crossref_primary_10_1016_j_bspc_2022_103813 crossref_primary_10_1016_j_eswa_2025_129477 crossref_primary_10_1111_age_13303 crossref_primary_10_1016_j_bspc_2025_107850 crossref_primary_10_1109_JSEN_2024_3416436 crossref_primary_10_1016_j_knosys_2024_112648 crossref_primary_10_1109_TMM_2024_3402620 crossref_primary_10_1016_j_ecoinf_2023_102215 crossref_primary_10_1088_1361_6560_acccd0 crossref_primary_10_1016_j_cviu_2023_103917 crossref_primary_10_1109_TIM_2024_3497186 crossref_primary_10_1016_j_rsase_2024_101221 crossref_primary_10_1016_j_cviu_2023_103915 crossref_primary_10_1371_journal_pone_0307206 crossref_primary_10_1007_s00259_022_06053_8 crossref_primary_10_1109_ACCESS_2024_3441837 crossref_primary_10_1109_TIP_2023_3318959 crossref_primary_10_1016_j_oceaneng_2023_115123 crossref_primary_10_1002_mp_15600 crossref_primary_10_1007_s00371_025_04070_w crossref_primary_10_1007_s13534_024_00439_3 crossref_primary_10_1002_acm2_13912 crossref_primary_10_1109_ACCESS_2025_3577221 crossref_primary_10_1007_s10845_023_02317_8 crossref_primary_10_3390_horticulturae11050451 crossref_primary_10_1016_j_compbiomed_2023_106698 crossref_primary_10_1109_TGRS_2021_3093977 crossref_primary_10_1177_20552076241289007 crossref_primary_10_3389_fphy_2024_1257512 crossref_primary_10_1016_j_measurement_2024_115067 crossref_primary_10_1109_TGRS_2021_3091312 crossref_primary_10_1109_TIP_2022_3228497 crossref_primary_10_3390_horticulturae8020145 crossref_primary_10_1088_2631_8695_ad5e36 crossref_primary_10_3390_agronomy14102325 crossref_primary_10_1016_j_autcon_2025_106403 crossref_primary_10_1007_s42044_025_00286_0 crossref_primary_10_1016_j_engappai_2025_111708 crossref_primary_10_1016_j_isprsjprs_2024_01_022 crossref_primary_10_1109_TMM_2024_3369870 crossref_primary_10_3390_jof7100850 crossref_primary_10_1109_TETCI_2023_3309626 crossref_primary_10_1016_j_ghm_2024_01_001 crossref_primary_10_1007_s11042_025_20731_3 crossref_primary_10_1109_TGRS_2024_3400868 crossref_primary_10_3389_fbioe_2021_696251 crossref_primary_10_3390_app15147770 crossref_primary_10_15625_2615_9783_23027 crossref_primary_10_1109_TIM_2024_3375414 crossref_primary_10_3389_feart_2023_1182145 crossref_primary_10_1016_j_specom_2024_103150 crossref_primary_10_7717_peerj_cs_2494 crossref_primary_10_1016_j_engappai_2023_107094 crossref_primary_10_1049_ipr2_12558 crossref_primary_10_3390_a17030109 crossref_primary_10_3390_rs14235911 crossref_primary_10_1016_j_displa_2025_103102 crossref_primary_10_3389_fphy_2025_1579280 crossref_primary_10_1016_j_compbiolchem_2025_108572 crossref_primary_10_1109_TASE_2025_3547613 crossref_primary_10_1109_TIM_2023_3267365 crossref_primary_10_1016_j_bspc_2024_106851 crossref_primary_10_1088_1361_6560_acdbb4 crossref_primary_10_1016_j_compbiomed_2023_107326 crossref_primary_10_1016_j_neucom_2024_128784 crossref_primary_10_1016_j_jmst_2025_04_045 crossref_primary_10_1049_cvi2_12093 crossref_primary_10_1109_TCSVT_2023_3241196 crossref_primary_10_1080_02564602_2023_2238683 crossref_primary_10_1109_ACCESS_2023_3241250 crossref_primary_10_1016_j_imavis_2023_104748 crossref_primary_10_14358_PERS_21_00081R2 crossref_primary_10_1016_j_ejmp_2025_104969 crossref_primary_10_1016_j_eswa_2023_122093 crossref_primary_10_1007_s10032_024_00476_9 crossref_primary_10_1002_int_23018 crossref_primary_10_3390_rs16050803 crossref_primary_10_1016_j_patrec_2024_03_020 crossref_primary_10_3390_a17100429 crossref_primary_10_1109_TIM_2023_3267355 crossref_primary_10_1117_1_JEI_31_6_063040 crossref_primary_10_3390_ai5020030 crossref_primary_10_1016_j_cmpb_2025_108635 crossref_primary_10_1007_s12145_023_01050_3 crossref_primary_10_1080_09540091_2024_2306962 crossref_primary_10_1016_j_compbiomed_2023_107578 crossref_primary_10_1016_j_patcog_2022_108625 crossref_primary_10_1038_s41598_024_84680_x crossref_primary_10_1109_TASLP_2024_3459430 crossref_primary_10_1109_TGRS_2024_3469992 crossref_primary_10_3390_app132011350 crossref_primary_10_1186_s40658_022_00472_0 crossref_primary_10_1109_TMI_2024_3474028 crossref_primary_10_1002_sdtp_14635 crossref_primary_10_1002_suco_70155 crossref_primary_10_1364_OE_559651 crossref_primary_10_1007_s11548_023_02879_1 crossref_primary_10_1109_JBHI_2024_3467256 crossref_primary_10_1049_sil2_6606572 crossref_primary_10_1007_s11042_024_19796_3 crossref_primary_10_1109_TIM_2023_3343788 crossref_primary_10_1109_ACCESS_2025_3602064 crossref_primary_10_3390_rs17122053 crossref_primary_10_1109_TIP_2025_3558674 crossref_primary_10_1186_s12859_023_05196_1 crossref_primary_10_1016_j_imavis_2022_104442 crossref_primary_10_1016_j_scitotenv_2024_169992 crossref_primary_10_1016_j_eswa_2024_123222 crossref_primary_10_3390_s23208511 crossref_primary_10_1007_s00445_023_01695_4 crossref_primary_10_1109_JBHI_2023_3237875 crossref_primary_10_1109_ACCESS_2023_3272352 crossref_primary_10_1109_JOE_2024_3503664 crossref_primary_10_1109_ACCESS_2025_3584647 crossref_primary_10_3390_app131910583 crossref_primary_10_3390_buildings15132207 crossref_primary_10_1016_j_cmpb_2024_108353 crossref_primary_10_3390_math11061389 crossref_primary_10_1109_TGRS_2024_3400032 crossref_primary_10_1109_TCSVT_2021_3104226 crossref_primary_10_1007_s11042_024_18163_6 crossref_primary_10_1007_s12559_022_10036_0 crossref_primary_10_1007_s10845_024_02434_y crossref_primary_10_1109_ACCESS_2023_3300895 crossref_primary_10_1186_s13059_025_03648_w crossref_primary_10_32604_cmes_2022_022143 crossref_primary_10_1016_j_measurement_2025_117176 crossref_primary_10_3389_fonc_2023_1177788 crossref_primary_10_1109_TMI_2023_3294248 crossref_primary_10_1016_j_ijrmms_2024_105820 crossref_primary_10_1016_j_jag_2025_104812 crossref_primary_10_1007_s12559_025_10410_8 crossref_primary_10_1016_j_jag_2023_103326 crossref_primary_10_3390_buildings13123114 crossref_primary_10_1016_j_engappai_2023_106168 crossref_primary_10_1007_s13349_024_00798_6 crossref_primary_10_1016_j_compbiomed_2024_108503 crossref_primary_10_1109_TMM_2024_3413529 crossref_primary_10_1109_TMM_2024_3521715 crossref_primary_10_1016_j_compbiomed_2021_104774 crossref_primary_10_1016_j_indcrop_2025_121308 crossref_primary_10_3390_rs14092207 crossref_primary_10_3390_drones8090445 crossref_primary_10_1088_1361_6560_acf3c9 crossref_primary_10_3390_electronics10243103 crossref_primary_10_1109_TITS_2024_3436015 crossref_primary_10_1364_OE_567001 crossref_primary_10_1016_j_jag_2023_103556 crossref_primary_10_1016_j_media_2023_102747 crossref_primary_10_1016_j_patcog_2024_110903 crossref_primary_10_1016_j_patcog_2021_108364 crossref_primary_10_1016_j_rineng_2025_105304 crossref_primary_10_1109_TCE_2024_3367790 crossref_primary_10_3390_app122311967 crossref_primary_10_1109_TCSVT_2021_3102268 crossref_primary_10_1109_TUFFC_2023_3263514 crossref_primary_10_1007_s10489_022_04212_w crossref_primary_10_3390_sym14061081 crossref_primary_10_3390_rs15245744 crossref_primary_10_1109_JOE_2023_3344154 crossref_primary_10_1007_s12204_023_2614_y crossref_primary_10_1109_JSTARS_2024_3374290 crossref_primary_10_1109_ACCESS_2025_3584832 crossref_primary_10_1109_LSP_2024_3400055 crossref_primary_10_1109_TITS_2024_3404654 crossref_primary_10_1109_TMM_2023_3347094 crossref_primary_10_1109_TRS_2025_3591065 crossref_primary_10_1016_j_compbiomed_2024_109617 crossref_primary_10_3390_rs16091525 crossref_primary_10_1007_s42947_025_00574_9 crossref_primary_10_1016_j_engappai_2024_109984 crossref_primary_10_1177_01617346231162925 crossref_primary_10_3390_drones7030189 crossref_primary_10_1088_1361_6501_acf23a crossref_primary_10_1016_j_neunet_2023_11_028 crossref_primary_10_1109_ACCESS_2025_3538978 crossref_primary_10_1007_s11227_022_04661_7 crossref_primary_10_1109_TITS_2023_3258480 crossref_primary_10_32604_cmc_2024_058063 crossref_primary_10_1186_s13636_024_00341_x crossref_primary_10_1109_JBHI_2023_3236989 crossref_primary_10_1109_TIV_2022_3216734 crossref_primary_10_1109_TETCI_2022_3174868 crossref_primary_10_3390_electronics11244200 crossref_primary_10_1016_j_aei_2025_103641 crossref_primary_10_1016_j_asoc_2025_112891 crossref_primary_10_1016_j_physleta_2024_129839 crossref_primary_10_3389_fonc_2024_1461542 crossref_primary_10_1007_s00500_024_09700_4 crossref_primary_10_1016_j_asoc_2025_113975
Cites_doi	10.1016/j.patcog.2017.11.024 10.1109/TIP.2016.2602079 10.1016/j.patcog.2019.03.023 10.1016/j.patcog.2016.10.025
ContentType	Journal Article
Copyright	2020 Elsevier Ltd
Copyright_xml	– notice: 2020 Elsevier Ltd
DBID	AAYXX CITATION
DOI	10.1016/j.patcog.2020.107404
DatabaseName	CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	1873-5142
ExternalDocumentID	10_1016_j_patcog_2020_107404 S0031320320302077
GroupedDBID	--K --M -D8 -DT -~X .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 29O 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABFRF ABHFT ABJNI ABMAC ABTAH ABXDB ABYKQ ACBEA ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADMXK ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FD6 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM KZ1 LG9 LMP LY1 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UNMZH VOH WUQ XJE XPP ZMT ZY4 ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD
ID	FETCH-LOGICAL-c236t-ebcba0947d065f10bce5d79e9762a1dd00c9df0f43b80431af552e65c141ef273
ISICitedReferencesCount	1614
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000541777200007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0031-3203
IngestDate	Tue Nov 18 21:51:59 EST 2025 Sat Nov 29 07:25:19 EST 2025 Fri Feb 23 02:47:44 EST 2024
IsPeerReviewed	true
IsScholarly	true
Keywords	Nested U-structure Network architecture design Salient object detection Convolutional neural network Multi-scale feature extraction
Language	English
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c236t-ebcba0947d065f10bce5d79e9762a1dd00c9df0f43b80431af552e65c141ef273
ORCID	0000-0003-2811-6008 0000-0002-9042-7192
ParticipantIDs	crossref_primary_10_1016_j_patcog_2020_107404 crossref_citationtrail_10_1016_j_patcog_2020_107404 elsevier_sciencedirect_doi_10_1016_j_patcog_2020_107404
PublicationCentury	2000
PublicationDate	October 2020 2020-10-00
PublicationDateYYYYMMDD	2020-10-01
PublicationDate_xml	– month: 10 year: 2020 text: October 2020
PublicationDecade	2020
PublicationTitle	Pattern recognition
PublicationYear	2020
Publisher	Elsevier Ltd
Publisher_xml	– name: Elsevier Ltd
References	Deng, Hu, Zhu, Xu, Qin, Han, Heng (bib0005) 2018 Krizhevsky, Sutskever, Hinton (bib0006) 2012 Lu, Tan, Lim (bib0018) 2013; 36 Feng, Lu, Ding (bib0034) 2019 Lu, Lim (bib0019) 2012 Hou, Cheng, Hu, Borji, Tu, Torr (bib0024) 2017 Long, Shelhamer, Darrell (bib0001) 2015 Zhang, Dai, Lu, He, Wang (bib0021) 2018 Ronneberger, Fischer, Brox (bib0035) 2015 Zhang, Huo, Liu, Pan, Shan, Han (bib0017) 2019; 92 Qin, Zhang, Huang, Gao, Dehghan, Jagersand (bib0014) 2019 Yang, Zhang, Lu, Ruan, Yang (bib0037) 2013 Margolin, Zelnik-Manor, Tal (bib0041) 2014 He, Zhang, Ren, Sun (bib0008) 2016 Zhao, Shi, Qi, Wang, Jia (bib0029) 2017 Li, Yu (bib0002) 2016; 25 Chen, Tan, Wang, Hu (bib0025) 2018 Huang, Liu, van der Maaten, Weinberger (bib0010) 2017 Zeng, Zhuge, Lu, Zhang, Qian, Yu (bib0033) 2019 Newell, Yang, Deng (bib0043) 2016 Wang, Zhang, Wang, Lu, Yang, Ruan, Borji (bib0004) 2018 K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition Xie, Girshick, Dollár, Tu, He (bib0009) 2017 Zhang, Wang, Lu, Wang, Ruan (bib0022) 2017 Zhang, Wang, Qi, Lu, Wang (bib0030) 2018 Liu, Han, Yang (bib0031) 2018 Zhang, Wang, Lu, Wang, Yin (bib0023) 2017 Li, Hou, Koch, Rehg, Yuille (bib0038) 2014 (2014). Wang, Borji, Zhang, Zhang, Lu (bib0028) 2017 Liu, Hou, Cheng, Feng, Jiang (bib0013) 2019 Zhang, Ehinger, Wei, Zhang, Yang (bib0015) 2017; 64 Wu, Su, Huang (bib0027) 2019 Deng, Dong, Socher, Li, Li, Fei-Fei (bib0011) 2009 Achanta, Hemami, Estrada, Susstrunk (bib0040) 2009 Wu, Feng, Guan, Wang, Lu, Ding (bib0026) 2019 Luo, Mishra, Achkar, Eichel, Li, Jodoin (bib0003) 2017 Liang, Zhou, Tong, Bai, Wang (bib0016) 2018; 76 Xie, Tu (bib0020) 2015 Zhang, Zhang, Lin, Lu, He (bib0032) 2019 Wang, Lu, Wang, Feng, Wang, Yin, Ruan (bib0036) 2017 Movahedi, Elder (bib0039) 2010 Tang, Peng, Geng, Wu, Zhang, Metaxas (bib0044) 2018 Yan, Xu, Shi, Jia (bib0012) 2013 Fan, Cheng, Liu, Li, Borji (bib0042) 2017 He (10.1016/j.patcog.2020.107404_bib0008) 2016 Huang (10.1016/j.patcog.2020.107404_bib0010) 2017 Wu (10.1016/j.patcog.2020.107404_bib0027) 2019 Movahedi (10.1016/j.patcog.2020.107404_bib0039) 2010 Luo (10.1016/j.patcog.2020.107404_bib0003) 2017 Hou (10.1016/j.patcog.2020.107404_bib0024) 2017 Lu (10.1016/j.patcog.2020.107404_bib0019) 2012 Zhang (10.1016/j.patcog.2020.107404_bib0021) 2018 Wang (10.1016/j.patcog.2020.107404_bib0004) 2018 Achanta (10.1016/j.patcog.2020.107404_bib0040) 2009 Tang (10.1016/j.patcog.2020.107404_bib0044) 2018 Qin (10.1016/j.patcog.2020.107404_bib0014) 2019 Zeng (10.1016/j.patcog.2020.107404_bib0033) 2019 Xie (10.1016/j.patcog.2020.107404_bib0009) 2017 Zhang (10.1016/j.patcog.2020.107404_bib0015) 2017; 64 Zhang (10.1016/j.patcog.2020.107404_bib0023) 2017 Ronneberger (10.1016/j.patcog.2020.107404_bib0035) 2015 Wang (10.1016/j.patcog.2020.107404_bib0036) 2017 Fan (10.1016/j.patcog.2020.107404_bib0042) 2017 Krizhevsky (10.1016/j.patcog.2020.107404_bib0006) 2012 Li (10.1016/j.patcog.2020.107404_bib0038) 2014 Wu (10.1016/j.patcog.2020.107404_bib0026) 2019 Liu (10.1016/j.patcog.2020.107404_bib0013) 2019 Wang (10.1016/j.patcog.2020.107404_bib0028) 2017 Li (10.1016/j.patcog.2020.107404_bib0002) 2016; 25 Long (10.1016/j.patcog.2020.107404_bib0001) 2015 Zhao (10.1016/j.patcog.2020.107404_bib0029) 2017 Yang (10.1016/j.patcog.2020.107404_bib0037) 2013 Newell (10.1016/j.patcog.2020.107404_bib0043) 2016 Chen (10.1016/j.patcog.2020.107404_bib0025) 2018 Zhang (10.1016/j.patcog.2020.107404_bib0030) 2018 Deng (10.1016/j.patcog.2020.107404_bib0011) 2009 Zhang (10.1016/j.patcog.2020.107404_bib0017) 2019; 92 Margolin (10.1016/j.patcog.2020.107404_bib0041) 2014 Liang (10.1016/j.patcog.2020.107404_bib0016) 2018; 76 10.1016/j.patcog.2020.107404_bib0007 Zhang (10.1016/j.patcog.2020.107404_bib0022) 2017 Deng (10.1016/j.patcog.2020.107404_bib0005) 2018 Lu (10.1016/j.patcog.2020.107404_bib0018) 2013; 36 Feng (10.1016/j.patcog.2020.107404_bib0034) 2019 Xie (10.1016/j.patcog.2020.107404_bib0020) 2015 Yan (10.1016/j.patcog.2020.107404_bib0012) 2013 Zhang (10.1016/j.patcog.2020.107404_bib0032) 2019 Liu (10.1016/j.patcog.2020.107404_bib0031) 2018
References_xml	– start-page: 6024 year: 2019 end-page: 6033 ident: bib0032 article-title: CapSal: leveraging captioning to boost semantics for salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 1741 year: 2018 end-page: 1750 ident: bib0021 article-title: A bi-directional message passing model for salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 202 year: 2017 end-page: 211 ident: bib0022 article-title: Amulet: aggregating multi-level convolutional features for salient object detection publication-title: Proceedings of the IEEE International Conference on Computer Vision – reference: (2014). – start-page: 280 year: 2014 end-page: 287 ident: bib0038 article-title: The secrets of salient object segmentation publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 3907 year: 2019 end-page: 3916 ident: bib0027 article-title: Cascaded partial decoder for fast and accurate salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – reference: K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, – start-page: 1597 year: 2009 end-page: 1604 ident: bib0040 article-title: Frequency-tuned salient region detection publication-title: 2009 IEEE Conference on Computer Vision and Pattern Recognition – start-page: 8150 year: 2019 end-page: 8159 ident: bib0026 article-title: A mutual learning method for salient object detection with intertwined multi-supervision publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 6593 year: 2017 end-page: 6601 ident: bib0003 article-title: Non-local deep features for salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 64 start-page: 39 year: 2017 end-page: 50 ident: bib0015 article-title: A novel graph-based optimization framework for salient object detection publication-title: Pattern Recognit. – start-page: 6074 year: 2019 end-page: 6083 ident: bib0033 article-title: Multi-source weak supervision for saliency detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 234 year: 2015 end-page: 241 ident: bib0035 article-title: U-Net: convolutional networks for biomedical image segmentation publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention – start-page: 234 year: 2018 end-page: 250 ident: bib0025 article-title: Reverse attention for salient object detection publication-title: Proceedings of the European Conference on Computer Vision (ECCV) – start-page: 3089 year: 2018 end-page: 3098 ident: bib0031 article-title: PiCANet: learning pixel-wise contextual attention for saliency detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 483 year: 2016 end-page: 499 ident: bib0043 article-title: Stacked hourglass networks for human pose estimation publication-title: European Conference on Computer Vision – start-page: 248 year: 2009 end-page: 255 ident: bib0011 article-title: ImageNet: a large-scale hierarchical image database publication-title: 2009 IEEE Conference on Computer Vision and Pattern Recognition – start-page: 339 year: 2018 end-page: 354 ident: bib0044 article-title: Quantized densely connected U-Nets for efficient landmark localization publication-title: Proceedings of the European Conference on Computer Vision (ECCV) – start-page: 136 year: 2017 end-page: 145 ident: bib0036 article-title: Learning to detect salient objects with image-level supervision publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 3431 year: 2015 end-page: 3440 ident: bib0001 article-title: Fully convolutional networks for semantic segmentation publication-title: Proceedings of the IEEE Conference on Computer Vision and pattern Recognition – start-page: 4548 year: 2017 end-page: 4557 ident: bib0042 article-title: Structure-measure: a new way to evaluate foreground maps publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 5987 year: 2017 end-page: 5995 ident: bib0009 article-title: Aggregated residual transformations for deep neural networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 1395 year: 2015 end-page: 1403 ident: bib0020 article-title: Holistically-nested edge detection publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 212 year: 2017 end-page: 221 ident: bib0023 article-title: Learning uncertain convolutional features for accurate saliency detection publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 1097 year: 2012 end-page: 1105 ident: bib0006 article-title: ImageNet classification with deep convolutional neural networks publication-title: Advances in Neural Information Processing Systems – start-page: 49 year: 2010 end-page: 56 ident: bib0039 article-title: Design and perceptual validation of performance measures for salient object segmentation publication-title: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops – start-page: 4039 year: 2017 end-page: 4048 ident: bib0028 article-title: A stagewise refinement model for detecting salient objects in images publication-title: Proceedings of the IEEE International Conference on Computer Vision – start-page: 2881 year: 2017 end-page: 2890 ident: bib0029 article-title: Pyramid scene parsing network publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 3917 year: 2019 end-page: 3926 ident: bib0013 article-title: A simple pooling-based design for real-time salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 76 start-page: 476 year: 2018 end-page: 490 ident: bib0016 article-title: Material based salient object detection from hyperspectral images publication-title: Pattern Recognit. – start-page: 2261 year: 2017 end-page: 2269 ident: bib0010 article-title: Densely connected convolutional networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 1155 year: 2013 end-page: 1162 ident: bib0012 article-title: Hierarchical saliency detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 92 start-page: 119 year: 2019 end-page: 134 ident: bib0017 article-title: Salient object detection employing a local tree-structured low-rank representation and foreground consistency publication-title: Pattern Recognit. – start-page: 248 year: 2014 end-page: 255 ident: bib0041 article-title: How to evaluate foreground maps publication-title: 2014 IEEE Conference on Computer Vision and Pattern Recognition – start-page: 7479 year: 2019 end-page: 7489 ident: bib0014 article-title: BASNet: boundary-aware salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 25 start-page: 5012 year: 2016 end-page: 5024 ident: bib0002 article-title: Visual saliency detection based on multiscale deep CNN features publication-title: IEEE Trans. Image Process. – start-page: 1623 year: 2019 end-page: 1632 ident: bib0034 article-title: Attentive feedback network for boundary-aware salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 3166 year: 2013 end-page: 3173 ident: bib0037 article-title: Saliency detection via graph-based manifold ranking publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 5300 year: 2017 end-page: 5309 ident: bib0024 article-title: Deeply supervised salient object detection with short connections publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 714 year: 2018 end-page: 722 ident: bib0030 article-title: Progressive attention guided recurrent network for salient object detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 770 year: 2016 end-page: 778 ident: bib0008 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 321 year: 2012 end-page: 332 ident: bib0019 article-title: Saliency modeling from image histograms publication-title: European Conference on Computer Vision – start-page: 3127 year: 2018 end-page: 3135 ident: bib0004 article-title: Detect globally, refine locally: a novel approach to saliency detection publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 684 year: 2018 end-page: 690 ident: bib0005 article-title: R3net: recurrent residual refinement network for saliency detection publication-title: Proceedings of the 27th International Joint Conference on Artificial Intelligence – volume: 36 start-page: 195 year: 2013 end-page: 201 ident: bib0018 article-title: Robust and efficient saliency modeling from image co-occurrence histograms publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1155 year: 2013 ident: 10.1016/j.patcog.2020.107404_bib0012 article-title: Hierarchical saliency detection – start-page: 339 year: 2018 ident: 10.1016/j.patcog.2020.107404_bib0044 article-title: Quantized densely connected U-Nets for efficient landmark localization – start-page: 684 year: 2018 ident: 10.1016/j.patcog.2020.107404_bib0005 article-title: R3net: recurrent residual refinement network for saliency detection – start-page: 714 year: 2018 ident: 10.1016/j.patcog.2020.107404_bib0030 article-title: Progressive attention guided recurrent network for salient object detection – start-page: 1623 year: 2019 ident: 10.1016/j.patcog.2020.107404_bib0034 article-title: Attentive feedback network for boundary-aware salient object detection – start-page: 8150 year: 2019 ident: 10.1016/j.patcog.2020.107404_bib0026 article-title: A mutual learning method for salient object detection with intertwined multi-supervision – volume: 76 start-page: 476 year: 2018 ident: 10.1016/j.patcog.2020.107404_bib0016 article-title: Material based salient object detection from hyperspectral images publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2017.11.024 – start-page: 136 year: 2017 ident: 10.1016/j.patcog.2020.107404_bib0036 article-title: Learning to detect salient objects with image-level supervision – start-page: 483 year: 2016 ident: 10.1016/j.patcog.2020.107404_bib0043 article-title: Stacked hourglass networks for human pose estimation – start-page: 280 year: 2014 ident: 10.1016/j.patcog.2020.107404_bib0038 article-title: The secrets of salient object segmentation – start-page: 3907 year: 2019 ident: 10.1016/j.patcog.2020.107404_bib0027 article-title: Cascaded partial decoder for fast and accurate salient object detection – volume: 25 start-page: 5012 issue: 11 year: 2016 ident: 10.1016/j.patcog.2020.107404_bib0002 article-title: Visual saliency detection based on multiscale deep CNN features publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2016.2602079 – start-page: 248 year: 2009 ident: 10.1016/j.patcog.2020.107404_bib0011 article-title: ImageNet: a large-scale hierarchical image database – start-page: 6593 year: 2017 ident: 10.1016/j.patcog.2020.107404_bib0003 article-title: Non-local deep features for salient object detection – start-page: 234 year: 2018 ident: 10.1016/j.patcog.2020.107404_bib0025 article-title: Reverse attention for salient object detection – volume: 92 start-page: 119 year: 2019 ident: 10.1016/j.patcog.2020.107404_bib0017 article-title: Salient object detection employing a local tree-structured low-rank representation and foreground consistency publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2019.03.023 – start-page: 5987 year: 2017 ident: 10.1016/j.patcog.2020.107404_bib0009 article-title: Aggregated residual transformations for deep neural networks – start-page: 5300 year: 2017 ident: 10.1016/j.patcog.2020.107404_bib0024 article-title: Deeply supervised salient object detection with short connections – volume: 36 start-page: 195 issue: 1 year: 2013 ident: 10.1016/j.patcog.2020.107404_bib0018 article-title: Robust and efficient saliency modeling from image co-occurrence histograms publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 3127 year: 2018 ident: 10.1016/j.patcog.2020.107404_bib0004 article-title: Detect globally, refine locally: a novel approach to saliency detection – start-page: 1741 year: 2018 ident: 10.1016/j.patcog.2020.107404_bib0021 article-title: A bi-directional message passing model for salient object detection – start-page: 770 year: 2016 ident: 10.1016/j.patcog.2020.107404_bib0008 article-title: Deep residual learning for image recognition – start-page: 234 year: 2015 ident: 10.1016/j.patcog.2020.107404_bib0035 article-title: U-Net: convolutional networks for biomedical image segmentation – start-page: 1597 year: 2009 ident: 10.1016/j.patcog.2020.107404_bib0040 article-title: Frequency-tuned salient region detection – start-page: 2881 year: 2017 ident: 10.1016/j.patcog.2020.107404_bib0029 article-title: Pyramid scene parsing network – start-page: 3089 year: 2018 ident: 10.1016/j.patcog.2020.107404_bib0031 article-title: PiCANet: learning pixel-wise contextual attention for saliency detection – start-page: 3166 year: 2013 ident: 10.1016/j.patcog.2020.107404_bib0037 article-title: Saliency detection via graph-based manifold ranking – start-page: 6074 year: 2019 ident: 10.1016/j.patcog.2020.107404_bib0033 article-title: Multi-source weak supervision for saliency detection – volume: 64 start-page: 39 year: 2017 ident: 10.1016/j.patcog.2020.107404_bib0015 article-title: A novel graph-based optimization framework for salient object detection publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2016.10.025 – start-page: 1395 year: 2015 ident: 10.1016/j.patcog.2020.107404_bib0020 article-title: Holistically-nested edge detection – start-page: 7479 year: 2019 ident: 10.1016/j.patcog.2020.107404_bib0014 article-title: BASNet: boundary-aware salient object detection – start-page: 3431 year: 2015 ident: 10.1016/j.patcog.2020.107404_bib0001 article-title: Fully convolutional networks for semantic segmentation – start-page: 3917 year: 2019 ident: 10.1016/j.patcog.2020.107404_bib0013 article-title: A simple pooling-based design for real-time salient object detection – start-page: 321 year: 2012 ident: 10.1016/j.patcog.2020.107404_bib0019 article-title: Saliency modeling from image histograms – start-page: 2261 year: 2017 ident: 10.1016/j.patcog.2020.107404_bib0010 article-title: Densely connected convolutional networks – start-page: 212 year: 2017 ident: 10.1016/j.patcog.2020.107404_bib0023 article-title: Learning uncertain convolutional features for accurate saliency detection – start-page: 4548 year: 2017 ident: 10.1016/j.patcog.2020.107404_bib0042 article-title: Structure-measure: a new way to evaluate foreground maps – start-page: 4039 year: 2017 ident: 10.1016/j.patcog.2020.107404_bib0028 article-title: A stagewise refinement model for detecting salient objects in images – start-page: 49 year: 2010 ident: 10.1016/j.patcog.2020.107404_bib0039 article-title: Design and perceptual validation of performance measures for salient object segmentation – start-page: 248 year: 2014 ident: 10.1016/j.patcog.2020.107404_bib0041 article-title: How to evaluate foreground maps – start-page: 1097 year: 2012 ident: 10.1016/j.patcog.2020.107404_bib0006 article-title: ImageNet classification with deep convolutional neural networks – ident: 10.1016/j.patcog.2020.107404_bib0007 – start-page: 202 year: 2017 ident: 10.1016/j.patcog.2020.107404_bib0022 article-title: Amulet: aggregating multi-level convolutional features for salient object detection – start-page: 6024 year: 2019 ident: 10.1016/j.patcog.2020.107404_bib0032 article-title: CapSal: leveraging captioning to boost semantics for salient object detection
SSID	ssj0017142
Score	2.7402358
Snippet	•A novel ReSidual U-block (RSU) is designed to capture multi-scale deep features.•A nested U-structure, called U2-Net, that uses RSU is developed for salient...
SourceID	crossref elsevier
SourceType	Enrichment Source Index Database Publisher
StartPage	107404
SubjectTerms	Convolutional neural network Multi-scale feature extraction Nested U-structure Network architecture design Salient object detection
Title	U2-Net: Going deeper with nested U-structure for salient object detection
URI	https://dx.doi.org/10.1016/j.patcog.2020.107404
Volume	106
WOSCitedRecordID	wos000541777200007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-5142 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017142 issn: 0031-3203 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3JTsMwELXYDlzYEbt84IZcZa0bbgixCiqQKKq4RLZjFxBKK1oQ_D3jjJOWRSwHLlFlxZMo8zp-Mx7PELIdSR4LHgpmIlNnkYxjJjylwEvRGfgTQmHFm-sz3mw22u3kwgX0-0U7AZ7njZeXpPevqoYxULY9OvsHdVdCYQB-g9LhCmqH668U3wpYUxcBv6OujQNkWvf0IwZc8yK6udNiWDbWbh7YNMM-kPEiJ0DaqAzMGBQJWvkoc70oCnHawy8u42i4f3-JdQjaT1reVYNVJPrGJpvmQ_i44X0YfBVu3bRMWt92bjEaey76roV9GY8A57PMbKtsbOizMPDCdzbWG7WSNgkUmw5_MuAYS7iv9WAh6nZq9gG14e3v62V_WMeq7MIyce0-RSmplZKilHEyGfA4Afs3uXdy0D6tdpy4H2Fleff25THLIhfw89t8TWNGqMnVHJlxPgXdQyzMkzGdL5DZsl8HdeZ7kZwgNHZpAQyKwKAWGBSBQUeAQQEY1AGDIjBoBYwl0jo8uNo_Zq6VBlNBWB8wLZUU4MnzDCin8T2pdJzxRAMZDYSfZZ6nksx4Jgplw5ZbEiaOA12PlR_52gDFXSYTeTfXK4RGJvBtRSHfqAD-30JGCsQ1EruBJ0RSXyVh-WVS5erM23YnD-l3elklrJrVwzorP9zPy4-eOq6IHDAFJH07c-2PT1on00OYb5AJUIPeJFPqeXDXf9xyMHoDTCaLEg
linkProvider	Elsevier
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=U2-Net%3A+Going+deeper+with+nested+U-structure+for+salient+object+detection&rft.jtitle=Pattern+recognition&rft.au=Qin%2C+Xuebin&rft.au=Zhang%2C+Zichen&rft.au=Huang%2C+Chenyang&rft.au=Dehghan%2C+Masood&rft.date=2020-10-01&rft.issn=0031-3203&rft.volume=106&rft.spage=107404&rft_id=info:doi/10.1016%2Fj.patcog.2020.107404&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_patcog_2020_107404
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon