Background Prior-Based Salient Object Detection via Deep Reconstruction Residual

Detection of salient objects from images is gaining increasing research interest in recent years as it can substantially facilitate a wide range of content-based multimedia applications. Based on the assumption that foreground salient regions are distinctive within a certain context, most convention...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on circuits and systems for video technology Vol. 25; no. 8; pp. 1309 - 1321
Main Authors:	Junwei Han, Dingwen Zhang, Xintao Hu, Lei Guo, Jinchang Ren, Feng Wu
Format:	Journal Article
Language:	English
Published:	IEEE 01.08.2015
Subjects:	deep reconstruction residual Encoding Feature extraction Image reconstruction Noise reduction Object detection Robustness salient object detection stacked denoising autoencoder Training stacked denoising autoencoder (SDAE) Background prior deep reconstruction residual salient object detection
ISSN:	1051-8215, 1558-2205
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Detection of salient objects from images is gaining increasing research interest in recent years as it can substantially facilitate a wide range of content-based multimedia applications. Based on the assumption that foreground salient regions are distinctive within a certain context, most conventional approaches rely on a number of hand-designed features and their distinctiveness is measured using local or global contrast. Although these approaches have been shown to be effective in dealing with simple images, their limited capability may cause difficulties when dealing with more complicated images. This paper proposes a novel framework for saliency detection by first modeling the background and then separating salient objects from the background. We develop stacked denoising autoencoders with deep learning architectures to model the background where latent patterns are explored and more powerful representations of data are learned in an unsupervised and bottom-up manner. Afterward, we formulate the separation of salient objects from the background as a problem of measuring reconstruction residuals of deep autoencoders. Comprehensive evaluations of three benchmark datasets and comparisons with nine state-of-the-art algorithms demonstrate the superiority of this paper.
AbstractList	Detection of salient objects from images is gaining increasing research interest in recent years as it can substantially facilitate a wide range of content-based multimedia applications. Based on the assumption that foreground salient regions are distinctive within a certain context, most conventional approaches rely on a number of hand-designed features and their distinctiveness is measured using local or global contrast. Although these approaches have been shown to be effective in dealing with simple images, their limited capability may cause difficulties when dealing with more complicated images. This paper proposes a novel framework for saliency detection by first modeling the background and then separating salient objects from the background. We develop stacked denoising autoencoders with deep learning architectures to model the background where latent patterns are explored and more powerful representations of data are learned in an unsupervised and bottom-up manner. Afterward, we formulate the separation of salient objects from the background as a problem of measuring reconstruction residuals of deep autoencoders. Comprehensive evaluations of three benchmark datasets and comparisons with nine state-of-the-art algorithms demonstrate the superiority of this paper.
Author	Dingwen Zhang Jinchang Ren Xintao Hu Lei Guo Junwei Han Feng Wu
Author_xml	– sequence: 1 surname: Junwei Han fullname: Junwei Han email: junweihan2010@gmail.com organization: Sch. of Autom., Northwestern Polytech. Univ., Xi'an, China – sequence: 2 surname: Dingwen Zhang fullname: Dingwen Zhang organization: Sch. of Autom., Northwestern Polytech. Univ., Xi'an, China – sequence: 3 surname: Xintao Hu fullname: Xintao Hu organization: Sch. of Autom., Northwestern Polytech. Univ., Xi'an, China – sequence: 4 surname: Lei Guo fullname: Lei Guo organization: Sch. of Autom., Northwestern Polytech. Univ., Xi'an, China – sequence: 5 surname: Jinchang Ren fullname: Jinchang Ren organization: Dept. of Electron. & Electr. Eng., Univ. of Strathclyde, Glasgow, UK – sequence: 6 surname: Feng Wu fullname: Feng Wu organization: Sch. of Inf. Sci., Univ. of Sci. & Technol. of China, Hefei, China
BookMark	eNp9kM1OwzAMgCMEEtvgBeDSF-iw0yZpj2z8SpM2bYNrlSYuyijtlHRIvD0dmzhwwBf_yJ9lfUN22rQNMXaFMEaE_GY9Xb2uxxwwHfMkw1ThCRugEFnMOYjTvgaBccZRnLNhCBvoN7NUDdhios37m293jY0W3rU-nuhANlrp2lHTRfNyQ6aL7qjrk2ub6NPpvqNttCTTNqHzu8N8ScHZna4v2Fml60CXxzxiLw_36-lTPJs_Pk9vZ7HhUnUxok60NdJCmivQUHHOM1DGgijBosi1ktJIxcuUjAS0iLkBaQSVicbKJiOWHe4a34bgqSqM6_T-lc5rVxcIxd5M8WOm2JspjmZ6lP9Bt959aP_1P3R9gBwR_QIyz1TSxzeObXH-
CODEN	ITCTEM
CitedBy_id	crossref_primary_10_1109_TCSVT_2022_3183641 crossref_primary_10_1109_TCYB_2017_2761775 crossref_primary_10_1016_j_jvcir_2019_102717 crossref_primary_10_1016_j_jvcir_2019_102716 crossref_primary_10_1016_j_jvcir_2019_06_005 crossref_primary_10_1080_01431161_2023_2229494 crossref_primary_10_1109_TVLSI_2019_2961602 crossref_primary_10_1007_s13042_020_01207_2 crossref_primary_10_1109_TNNLS_2015_2461554 crossref_primary_10_1109_TGRS_2024_3421950 crossref_primary_10_1109_ACCESS_2020_2996022 crossref_primary_10_1016_j_patrec_2018_07_030 crossref_primary_10_1109_MNET_001_1900260 crossref_primary_10_1109_TCE_2024_3430354 crossref_primary_10_1007_s11042_017_4563_7 crossref_primary_10_1109_TMM_2022_3216476 crossref_primary_10_1109_ACCESS_2020_2966628 crossref_primary_10_1109_TCSVT_2019_2941017 crossref_primary_10_1109_ACCESS_2019_2902658 crossref_primary_10_1109_TCDS_2019_2963682 crossref_primary_10_1109_TIP_2020_3023774 crossref_primary_10_1016_j_jvcir_2019_102705 crossref_primary_10_1109_TCSVT_2016_2595321 crossref_primary_10_1016_j_jvcir_2019_102709 crossref_primary_10_1016_j_jvcir_2019_102708 crossref_primary_10_1109_ACCESS_2019_2932047 crossref_primary_10_1007_s11390_017_1737_8 crossref_primary_10_1109_TVT_2019_2894437 crossref_primary_10_1109_TCYB_2019_2932005 crossref_primary_10_1109_ACCESS_2019_2899940 crossref_primary_10_7717_peerj_6201 crossref_primary_10_1016_j_jvcir_2017_06_009 crossref_primary_10_1109_TIP_2020_3011554 crossref_primary_10_1109_ACCESS_2019_2904039 crossref_primary_10_1038_s41598_019_53460_3 crossref_primary_10_1016_j_jag_2023_103301 crossref_primary_10_1016_j_jvcir_2019_102610 crossref_primary_10_1109_TMM_2019_2907060 crossref_primary_10_1016_j_jvcir_2019_102613 crossref_primary_10_1109_TMM_2021_3138246 crossref_primary_10_1016_j_jvcir_2019_102612 crossref_primary_10_1016_j_neucom_2019_10_063 crossref_primary_10_1109_JSTARS_2017_2655112 crossref_primary_10_1016_j_jvcir_2019_02_001 crossref_primary_10_1007_s11045_016_0416_1 crossref_primary_10_1016_j_soildyn_2023_107834 crossref_primary_10_1109_TIP_2021_3106798 crossref_primary_10_1145_3158674 crossref_primary_10_1109_TCSVT_2022_3232487 crossref_primary_10_1007_s40747_020_00188_7 crossref_primary_10_1016_j_sigpro_2019_107331 crossref_primary_10_1007_s00607_019_00737_0 crossref_primary_10_1088_0967_3334_37_12_2214 crossref_primary_10_1109_TIP_2017_2700725 crossref_primary_10_1016_j_jvcir_2019_102720 crossref_primary_10_1109_JSTARS_2020_3019582 crossref_primary_10_1109_TNNLS_2017_2761401 crossref_primary_10_1016_j_jvcir_2019_102723 crossref_primary_10_1016_j_jvcir_2019_102600 crossref_primary_10_1016_j_jvcir_2019_102728 crossref_primary_10_1109_TII_2019_2913762 crossref_primary_10_1109_TVT_2019_2901284 crossref_primary_10_1109_TVT_2019_2907269 crossref_primary_10_1016_j_jvcir_2019_02_011 crossref_primary_10_1016_j_jvcir_2019_02_012 crossref_primary_10_1016_j_jvcir_2019_02_010 crossref_primary_10_1016_j_jvcir_2019_102609 crossref_primary_10_1016_j_jvcir_2019_102608 crossref_primary_10_1109_TCYB_2015_2404432 crossref_primary_10_1109_TCSVT_2019_2906226 crossref_primary_10_1109_TMM_2020_3038311 crossref_primary_10_1109_TCSVT_2024_3412093 crossref_primary_10_1016_j_jvcir_2019_102632 crossref_primary_10_1109_ACCESS_2019_2924238 crossref_primary_10_1016_j_jvcir_2019_102631 crossref_primary_10_1109_ACCESS_2019_2904749 crossref_primary_10_1016_j_jvcir_2019_102630 crossref_primary_10_1109_TGRS_2023_3295992 crossref_primary_10_1109_TPAMI_2016_2567393 crossref_primary_10_1016_j_jvcir_2019_102634 crossref_primary_10_1109_TGRS_2019_2893115 crossref_primary_10_1016_j_jvcir_2019_102633 crossref_primary_10_1109_TIP_2020_3014734 crossref_primary_10_1109_TNNLS_2016_2602855 crossref_primary_10_1109_TVT_2019_2905598 crossref_primary_10_3390_rs14040851 crossref_primary_10_1016_j_jvcir_2019_102637 crossref_primary_10_1109_ACCESS_2020_2982588 crossref_primary_10_1109_TMM_2020_3025166 crossref_primary_10_1016_j_engappai_2018_10_011 crossref_primary_10_1109_JSTARS_2020_3014784 crossref_primary_10_1109_TIP_2016_2617462 crossref_primary_10_1016_j_neucom_2021_07_088 crossref_primary_10_1109_LGRS_2020_2981507 crossref_primary_10_1016_j_asoc_2019_01_024 crossref_primary_10_1109_TIP_2016_2605920 crossref_primary_10_1155_2021_2472676 crossref_primary_10_3390_app10103350 crossref_primary_10_1016_j_jvcir_2019_102629 crossref_primary_10_1109_ACCESS_2019_2900719 crossref_primary_10_1016_j_ijleo_2020_165341 crossref_primary_10_1109_TIP_2017_2703081 crossref_primary_10_1007_s11432_015_5420_9 crossref_primary_10_1007_s11042_019_08211_x crossref_primary_10_1109_TMM_2017_2763780 crossref_primary_10_1108_SR_05_2019_0124 crossref_primary_10_1109_TNNLS_2016_2582532 crossref_primary_10_1109_TCYB_2019_2934986 crossref_primary_10_1109_TIP_2017_2781424 crossref_primary_10_1109_TMM_2019_2900166 crossref_primary_10_1007_s11760_020_01737_w crossref_primary_10_1016_j_dsp_2022_103827 crossref_primary_10_1016_j_neucom_2018_09_009 crossref_primary_10_1109_TNNLS_2020_3006467 crossref_primary_10_1016_j_jvcir_2017_11_006 crossref_primary_10_1109_TCSVT_2023_3325229 crossref_primary_10_1109_TCSVT_2023_3287684 crossref_primary_10_1109_TPAMI_2019_2900649 crossref_primary_10_1109_TIP_2021_3124668 crossref_primary_10_1016_j_comnet_2019_04_016 crossref_primary_10_1109_JPROC_2017_2675998 crossref_primary_10_1109_TNNLS_2020_3015965 crossref_primary_10_1016_j_jvcir_2019_03_014 crossref_primary_10_1109_TCSVT_2016_2564878 crossref_primary_10_1016_j_jvcir_2019_03_012 crossref_primary_10_1016_j_jvcir_2019_03_013 crossref_primary_10_1109_TIP_2016_2601784 crossref_primary_10_1109_TCSVT_2017_2710120 crossref_primary_10_1109_TCYB_2016_2524406 crossref_primary_10_1109_TCYB_2017_2761361 crossref_primary_10_1109_ACCESS_2019_2901943 crossref_primary_10_1109_TIP_2017_2762594 crossref_primary_10_1016_j_jvcir_2019_102647 crossref_primary_10_1109_TNNLS_2020_2986823 crossref_primary_10_1109_TCSVT_2020_2988768 crossref_primary_10_1016_j_jvcir_2019_102645 crossref_primary_10_1016_j_neucom_2017_10_052 crossref_primary_10_1016_j_neucom_2017_04_066 crossref_primary_10_1109_TPAMI_2018_2881114 crossref_primary_10_1016_j_neucom_2019_12_123 crossref_primary_10_1109_TVT_2019_2903144 crossref_primary_10_1007_s00371_022_02660_6 crossref_primary_10_1109_LSP_2016_2600592 crossref_primary_10_1016_j_jvcir_2019_03_005 crossref_primary_10_3390_electronics12132880 crossref_primary_10_3390_s17040905 crossref_primary_10_1109_ACCESS_2019_2934160 crossref_primary_10_1109_TGRS_2016_2601622 crossref_primary_10_1109_TIM_2021_3132082 crossref_primary_10_1109_TIP_2019_2922072 crossref_primary_10_1007_s41095_020_0172_x crossref_primary_10_1016_j_jvcir_2019_01_020 crossref_primary_10_1016_j_jvcir_2019_01_021 crossref_primary_10_1109_ACCESS_2019_2946861 crossref_primary_10_1109_LSP_2016_2617340 crossref_primary_10_1145_3632181 crossref_primary_10_1007_s11042_017_5223_7 crossref_primary_10_1109_JBHI_2017_2734329 crossref_primary_10_1016_j_neucom_2016_05_017 crossref_primary_10_1109_TNNLS_2015_2488637 crossref_primary_10_1016_j_neucom_2020_12_067 crossref_primary_10_1109_TCSVT_2018_2823769 crossref_primary_10_1016_j_neucom_2019_12_057 crossref_primary_10_1049_iet_ipr_2018_5479 crossref_primary_10_1007_s11042_017_4616_y crossref_primary_10_1109_TIP_2017_2658957 crossref_primary_10_3389_fnbot_2019_00073 crossref_primary_10_1109_TMM_2022_3167805 crossref_primary_10_1016_j_image_2019_115768 crossref_primary_10_1109_TIP_2017_2652730 crossref_primary_10_1109_TGRS_2016_2642125 crossref_primary_10_1109_TCSVT_2024_3486050 crossref_primary_10_1109_TPAMI_2018_2846598 crossref_primary_10_1109_TIP_2025_3572760 crossref_primary_10_1109_ACCESS_2019_2902121 crossref_primary_10_1109_ACCESS_2019_2943365 crossref_primary_10_1007_s11042_018_7106_y crossref_primary_10_1016_j_jvcir_2019_01_035 crossref_primary_10_1016_j_neucom_2017_03_016 crossref_primary_10_1016_j_jvcir_2019_01_037 crossref_primary_10_1016_j_jvcir_2019_01_038 crossref_primary_10_1016_j_neunet_2020_04_012 crossref_primary_10_1016_j_jvcir_2017_12_006 crossref_primary_10_1016_j_ijepes_2019_105651 crossref_primary_10_1109_ACCESS_2019_2958058 crossref_primary_10_1109_TCSVT_2019_2904463 crossref_primary_10_1109_TNNLS_2015_2495161 crossref_primary_10_1016_j_patcog_2016_01_027 crossref_primary_10_1109_TBME_2019_2955722 crossref_primary_10_1109_TNNLS_2016_2628878 crossref_primary_10_1007_s10043_016_0219_5 crossref_primary_10_1007_s11042_016_3616_7 crossref_primary_10_1109_TGRS_2016_2523563 crossref_primary_10_3390_s18113774 crossref_primary_10_1109_TIP_2016_2627801 crossref_primary_10_1016_j_neucom_2020_11_041 crossref_primary_10_1007_s11045_015_0371_2 crossref_primary_10_1109_TMM_2018_2856126 crossref_primary_10_1162_neco_a_01038 crossref_primary_10_1016_j_patcog_2017_11_024 crossref_primary_10_1007_s40747_023_01072_w crossref_primary_10_1109_TGRS_2024_3504845 crossref_primary_10_1109_ACCESS_2019_2910572 crossref_primary_10_1007_s11042_020_09458_5 crossref_primary_10_1016_j_patcog_2019_03_023 crossref_primary_10_1109_TNNLS_2020_3044176 crossref_primary_10_1109_TGRS_2023_3256373 crossref_primary_10_1007_s11042_021_11447_1 crossref_primary_10_1109_LGRS_2019_2945886 crossref_primary_10_1016_j_jvcir_2018_03_017 crossref_primary_10_1016_j_patcog_2018_08_007 crossref_primary_10_1016_j_jvcir_2019_01_040 crossref_primary_10_1109_TMM_2016_2568138 crossref_primary_10_1002_acs_2985 crossref_primary_10_1109_TCYB_2018_2881482 crossref_primary_10_1109_ACCESS_2020_2980290 crossref_primary_10_1109_TNNLS_2015_2464316 crossref_primary_10_1109_ACCESS_2020_2968744 crossref_primary_10_1109_TCSVT_2016_2642341 crossref_primary_10_1016_j_neucom_2019_04_062 crossref_primary_10_1109_TCYB_2025_3584808 crossref_primary_10_1109_TCSVT_2016_2515338 crossref_primary_10_1109_TIP_2018_2835143 crossref_primary_10_1109_ACCESS_2019_2918728 crossref_primary_10_1007_s11042_016_3615_8 crossref_primary_10_1109_ACCESS_2019_2903121 crossref_primary_10_3390_sym10120734 crossref_primary_10_1109_TNNLS_2015_2495148 crossref_primary_10_1109_LSP_2015_2413944 crossref_primary_10_1109_JSTARS_2022_3150843 crossref_primary_10_1007_s11045_015_0370_3 crossref_primary_10_1016_j_neucom_2018_02_004 crossref_primary_10_1016_j_jvcir_2019_02_029 crossref_primary_10_1016_j_neucom_2020_10_019 crossref_primary_10_1016_j_jvcir_2019_02_022 crossref_primary_10_1016_j_neucom_2017_01_039 crossref_primary_10_1002_acs_2991 crossref_primary_10_1109_ACCESS_2021_3132787 crossref_primary_10_1016_j_ijleo_2017_03_029 crossref_primary_10_1109_TIP_2019_2922818 crossref_primary_10_1109_TAMD_2015_2409835 crossref_primary_10_1007_s11042_023_17614_w crossref_primary_10_1016_j_cogsys_2018_06_014 crossref_primary_10_1109_TCSVT_2023_3349209 crossref_primary_10_1109_TCSVT_2020_3013119 crossref_primary_10_1109_TMM_2020_2997192 crossref_primary_10_1109_LGRS_2018_2838151 crossref_primary_10_1049_iet_ipr_2017_1173 crossref_primary_10_1109_ACCESS_2019_2960162 crossref_primary_10_1109_TCSVT_2019_2958871 crossref_primary_10_1016_j_jvcir_2019_02_033 crossref_primary_10_1016_j_jvcir_2019_02_034 crossref_primary_10_1109_TVT_2018_2883046 crossref_primary_10_1007_s11045_016_0407_2 crossref_primary_10_1016_j_jvcir_2019_02_032 crossref_primary_10_1109_TCSVT_2021_3102268 crossref_primary_10_1080_09540091_2019_1650330 crossref_primary_10_1109_TIP_2019_2945679 crossref_primary_10_1007_s11042_021_10744_z crossref_primary_10_3233_JIFS_191292 crossref_primary_10_1007_s11045_016_0396_1 crossref_primary_10_1007_s11042_019_08004_2 crossref_primary_10_1016_j_neucom_2017_02_064 crossref_primary_10_1109_TCSVT_2023_3268217 crossref_primary_10_3390_s23042005 crossref_primary_10_1016_j_neucom_2016_11_064 crossref_primary_10_1109_TVCG_2016_2600594 crossref_primary_10_1109_TCSVT_2017_2706264 crossref_primary_10_1109_TBDATA_2020_3009983 crossref_primary_10_1109_TMM_2017_2769801 crossref_primary_10_1109_TCSVT_2018_2804438 crossref_primary_10_1016_j_neucom_2016_04_036 crossref_primary_10_1109_TCSVT_2019_2896438 crossref_primary_10_1016_j_neucom_2017_05_032 crossref_primary_10_1109_TMM_2021_3129052 crossref_primary_10_1016_j_neucom_2021_03_056 crossref_primary_10_1007_s11045_016_0429_9 crossref_primary_10_1109_TGRS_2019_2900302 crossref_primary_10_1016_j_neucom_2016_09_062 crossref_primary_10_1016_j_jvcir_2019_01_013 crossref_primary_10_1016_j_jvcir_2019_01_014 crossref_primary_10_1016_j_jvcir_2019_01_015 crossref_primary_10_1016_j_jvcir_2019_01_016 crossref_primary_10_1016_j_jvcir_2019_01_017 crossref_primary_10_1016_j_jvcir_2019_01_018 crossref_primary_10_1007_s12559_017_9529_6 crossref_primary_10_1016_j_jvcir_2019_01_019 crossref_primary_10_1049_iet_ipr_2018_5722 crossref_primary_10_1109_TGRS_2017_2702596 crossref_primary_10_1007_s00500_021_06388_8 crossref_primary_10_1109_TCSVT_2020_3014663 crossref_primary_10_1016_j_neucom_2019_05_069 crossref_primary_10_1109_TNNLS_2015_2477537 crossref_primary_10_1016_j_artmed_2021_102155
Cites_doi	10.1109/CVPR.2013.151 10.1109/CVPR.2013.416 10.1109/TPAMI.2010.70 10.1109/CVPR.2011.5995344 10.1109/CVPR.2012.6247706 10.1016/j.ins.2014.05.021 10.1109/34.730558 10.5244/C.25.110 10.1109/TPAMI.2011.272 10.1109/TPAMI.2012.277 10.7551/mitpress/7496.003.0016 10.1167/9.12.15 10.1109/CVPR.2007.383267 10.1109/TCSVT.2013.2242594 10.1023/B:VISI.0000022288.19776.77 10.1109/ICCV.2013.221 10.1145/1618452.1618470 10.1109/TNNLS.2014.2308519 10.1109/ICCV.2009.5459462 10.1109/TPAMI.2013.50 10.1109/TIP.2012.2216276 10.1109/CVPR.2007.383017 10.1167/8.7.32 10.1109/TSMCB.2012.2214210 10.1109/CVPRW.2010.5543739 10.1109/CVPR.2013.407 10.1016/j.patrec.2013.04.009 10.1126/science.1127647 10.1109/TPAMI.2004.1273918 10.1109/TIP.2011.2169274 10.1145/2072298.2071952 10.1109/TCSVT.2013.2290579 10.1007/s11263-014-0703-y 10.1109/CVPR.2009.5206596 10.1109/TCSVT.2013.2290573 10.1109/CVPR.2014.39
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION
DOI	10.1109/TCSVT.2014.2381471
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-2205
EndPage	1321
ExternalDocumentID	10_1109_TCSVT_2014_2381471 6987333
Genre	orig-research
GrantInformation_xml	– fundername: National Science Foundation of China grantid: 61103061; 91120005; 61473231
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 AAYXX CITATION
ID	FETCH-LOGICAL-c267t-11a3adc6d04970a0f222807cd05b0d159a766c672b4ec601d119c06c5eb3a1fd3
IEDL.DBID	RIE
ISICitedReferencesCount	405
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000359213400005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1051-8215
IngestDate	Tue Nov 18 21:53:44 EST 2025 Sat Nov 29 01:44:07 EST 2025 Tue Aug 26 16:40:00 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	8
Keywords	stacked denoising autoencoder (SDAE) Background prior deep reconstruction residual salient object detection
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c267t-11a3adc6d04970a0f222807cd05b0d159a766c672b4ec601d119c06c5eb3a1fd3
PageCount	13
ParticipantIDs	crossref_citationtrail_10_1109_TCSVT_2014_2381471 crossref_primary_10_1109_TCSVT_2014_2381471 ieee_primary_6987333
PublicationCentury	2000
PublicationDate	2015-Aug. 2015-8-00
PublicationDateYYYYMMDD	2015-08-01
PublicationDate_xml	– month: 08 year: 2015 text: 2015-Aug.
PublicationDecade	2010
PublicationTitle	IEEE transactions on circuits and systems for video technology
PublicationTitleAbbrev	TCSVT
PublicationYear	2015
Publisher	IEEE
Publisher_xml	– name: IEEE
References	shen (ref11) 2012 ref12 ref15 ref14 ref17 ref16 ref19 harel (ref42) 2006 ref51 ref50 ref46 ref45 ref48 ref44 hou (ref10) 2008 ref8 ref7 ng (ref26) 2011 ref9 ref4 ref3 ref6 ref5 sun (ref47) 2014; 24 ref40 wei (ref18) 2012 chang (ref37) 2011 sun (ref1) 2011 ref35 ref34 erhan (ref21) 2010; 11 ref36 li (ref49) 2009 ref33 ref39 ref38 bengio (ref20) 2007 bengio (ref30) 2013 liu (ref13) 2011; 33 chen (ref2) 2009; 28 ref24 ref23 vincent (ref25) 2010; 11 wang (ref32) 2012 ref22 borji (ref41) 2012 ref28 goodfellow (ref31) 2013 ref27 ref29 hou (ref43) 2008
References_xml	– ident: ref34 doi: 10.1109/CVPR.2013.151 – ident: ref35 doi: 10.1109/CVPR.2013.416 – start-page: 681 year: 2008 ident: ref43 article-title: Dynamic visual attention: Searching for coding length increments publication-title: Advances in neural information processing systems – start-page: 681 year: 2008 ident: ref10 article-title: Dynamic visual attention: Searching for coding length increments publication-title: Advances in neural information processing systems – start-page: 1511 year: 2011 ident: ref1 article-title: Scale and object aware image retargeting for thumbnail browsing publication-title: Proc IEEE Int Conf Comput Vis – volume: 33 start-page: 353 year: 2011 ident: ref13 article-title: Learning to detect a salient object publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2010.70 – ident: ref17 doi: 10.1109/CVPR.2011.5995344 – ident: ref7 doi: 10.1109/CVPR.2012.6247706 – ident: ref3 doi: 10.1016/j.ins.2014.05.021 – ident: ref5 doi: 10.1109/34.730558 – ident: ref38 doi: 10.5244/C.25.110 – volume: 11 start-page: 625 year: 2010 ident: ref21 article-title: Why does unsupervised pre-training help deep learning? publication-title: J Mach Learn Res – ident: ref33 doi: 10.1109/TPAMI.2011.272 – ident: ref27 doi: 10.1109/TPAMI.2012.277 – start-page: 29 year: 2012 ident: ref18 article-title: Geodesic saliency using background priors publication-title: Proc 12th Eur Conf Comput Vis – year: 2007 ident: ref20 article-title: Scaling learning algorithms towards AI publication-title: Large-Scale Kernel Machines doi: 10.7551/mitpress/7496.003.0016 – ident: ref14 doi: 10.1167/9.12.15 – ident: ref15 doi: 10.1109/CVPR.2007.383267 – ident: ref9 doi: 10.1109/TCSVT.2013.2242594 – ident: ref36 doi: 10.1023/B:VISI.0000022288.19776.77 – ident: ref44 doi: 10.1109/ICCV.2013.221 – volume: 28 year: 2009 ident: ref2 article-title: Sketch2Photo: Internet image montage publication-title: ACM Trans Graph doi: 10.1145/1618452.1618470 – ident: ref22 doi: 10.1109/TNNLS.2014.2308519 – ident: ref6 doi: 10.1109/ICCV.2009.5459462 – start-page: 3093 year: 2009 ident: ref49 article-title: Incremental sparse saliency detection publication-title: Proc 16th IEEE Int Conf Image Process – ident: ref24 doi: 10.1109/TPAMI.2013.50 – start-page: 287 year: 2012 ident: ref32 article-title: An analysis of Gaussian-binary restricted Boltzmann machines for natural images publication-title: Proc ESANN – start-page: 1319 year: 2013 ident: ref31 article-title: Maxout networks publication-title: Proc IEEE Int Conf Mach Learn – year: 2013 ident: ref30 article-title: Practical recommendations for gradient-based training of deep architectures publication-title: Proc Neural Netw Tricks of the Trade – ident: ref39 doi: 10.1109/TIP.2012.2216276 – ident: ref50 doi: 10.1109/CVPR.2007.383017 – ident: ref8 doi: 10.1167/8.7.32 – ident: ref45 doi: 10.1109/TSMCB.2012.2214210 – ident: ref40 doi: 10.1109/CVPRW.2010.5543739 – ident: ref19 doi: 10.1109/CVPR.2013.407 – start-page: 414 year: 2012 ident: ref41 article-title: Salient object detection: A benchmark publication-title: Proc 12th Eur Conf Comput Vis – ident: ref29 doi: 10.1016/j.patrec.2013.04.009 – start-page: 853 year: 2012 ident: ref11 article-title: A unified approach to salient object detection via low rank matrix recovery publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref23 doi: 10.1126/science.1127647 – ident: ref46 doi: 10.1109/TPAMI.2004.1273918 – ident: ref48 doi: 10.1109/TIP.2011.2169274 – ident: ref12 doi: 10.1145/2072298.2071952 – start-page: 545 year: 2006 ident: ref42 article-title: Graph-based visual saliency publication-title: Advances in neural information processing systems – ident: ref28 doi: 10.1109/TCSVT.2013.2290579 – ident: ref4 doi: 10.1007/s11263-014-0703-y – volume: 11 start-page: 3371 year: 2010 ident: ref25 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J Mach Learn Res – ident: ref16 doi: 10.1109/CVPR.2009.5206596 – volume: 24 start-page: 780 year: 2014 ident: ref47 article-title: Unsupervised object extraction by contour delineation and texture discrimination based on oriented edge features publication-title: IEEE Trans Circuits Syst Video Technol doi: 10.1109/TCSVT.2013.2290573 – start-page: 72 year: 2011 ident: ref26 article-title: Sparse autoencoder – ident: ref51 doi: 10.1109/CVPR.2014.39 – start-page: 914 year: 2011 ident: ref37 article-title: Fusing generic objectness and visual saliency for salient object detection publication-title: Proc IEEE Int Conf Comput Vis
SSID	ssj0014847
Score	2.6249535
Snippet	Detection of salient objects from images is gaining increasing research interest in recent years as it can substantially facilitate a wide range of...
SourceID	crossref ieee
SourceType	Enrichment Source Index Database Publisher
StartPage	1309
SubjectTerms	deep reconstruction residual Encoding Feature extraction Image reconstruction Noise reduction Object detection Robustness salient object detection stacked denoising autoencoder Training
Title	Background Prior-Based Salient Object Detection via Deep Reconstruction Residual
URI	https://ieeexplore.ieee.org/document/6987333
Volume	25
WOSCitedRecordID	wos000359213400005&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-2205 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014847 issn: 1051-8215 databaseCode: RIE dateStart: 19910101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG6AeNCDLzTiKz1400K7j3b3KCrxhCSg4bbpaxOiWQggv99pd0FMjIm3bdM2m6-b_WbamW8Quol5miotJQmc_mUkckqkiCQRiYIOyYW0ZbEJ0e8n43E6qKG7TS6MtdYHn9m2e_R3-WaqP91RWYeDgxyGYR3VhRBlrtbmxiBKfDExMBcYSYDH1gkyNO2MHoZvIxfFFbUdQUWC_SChraoqnlR6B_97nUO0XxmP-L7c7SNUs8Ux2tuSFGyiQVfqd5eqURg8mE-mc9IFnjJ4CPY2rIZflDt4wY926WOwCryaSGjZGXaO6LecLDQXPk_rBL32nkYPz6SqmkB0wMWSMCZDaTQ3YPsLKmkeeMUbbWisqAHrRQrONReBiqwGd8wwlmrKdQxutWS5CU9Ro5gW9gzhWOWpihJYTJlIWtg-lcM_wUgV5yrUpoXYGsZMV5LirrLFR-ZdC5pmHvrMQZ9V0LfQ7WbOrBTU-HN00-G-GVlBfv579wXahclxGZ93iRoAmb1CO3q1nCzm1_57-QLtXr5A
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwED_mFNQHv6Y4P_vgm9Y1bZq0jzoVRZ2DTdlbyVdhKJ3Mub_fS1qnggi-JSE9wi-hd5fc_Q7gKGZpKpUQfmj5LynPA19wKnyeSBwQjAtTFpvgnU4yGKTdGpzMcmGMMS74zJzapnvL1yP1bq_KWgwd5CiK5mA-pjQkZbbW7M2AJq6cGBoMxE9Qk32myARpq9_uPfVtHBc9tSqKcvJDDX2rq-LUytXq_xa0BiuV-eidlfu9DjVTbMDyN1LBBnTPhXq2yRqF9rrj4Wjsn6Om0l4PLW6U5j1Ie_XiXZiJi8IqvOlQYM-8etYV_SKUxe6by9TahMery3772q_qJvgqZHziEyIioRXTaP3zQAR56DhvlA5iGWi0XwRnTDEeSmoUOmSakFQFTMXoWAuS62gL6sWoMNvgxTJPJU1QmNRUGNxAmeNfQQsZ5zJSugnkE8ZMVaTitrbFS-aciyDNHPSZhT6roG_C8eyb15JS48_ZDYv7bGYF-c7vw4eweN2_v8vubjq3u7CEguIyWm8P6gif2YcFNZ0M38YH7ux8AP4swYc
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=Background+Prior-Based+Salient+Object+Detection+via+Deep+Reconstruction+Residual&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Junwei+Han&rft.au=Dingwen+Zhang&rft.au=Xintao+Hu&rft.au=Lei+Guo&rft.date=2015-08-01&rft.pub=IEEE&rft.issn=1051-8215&rft.volume=25&rft.issue=8&rft.spage=1309&rft.epage=1321&rft_id=info:doi/10.1109%2FTCSVT.2014.2381471&rft.externalDocID=6987333
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8215&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8215&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8215&client=summon