Superpixels: An evaluation of the state-of-the-art
•An extensive evaluation of 28 superpixel algorithms on 5 datasets.•Explicit discussion of parameter optimization, including superpixel connectivity.•Presentation of visual quality, algorithm runtime, and a performance-based ranking.•The evaluated implementations as well as the benchmark are publicl...
Uložené v:
| Vydané v: | Computer vision and image understanding Ročník 166; s. 1 - 27 |
|---|---|
| Hlavní autori: | , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier Inc
01.01.2018
|
| Predmet: | |
| ISSN: | 1077-3142, 1090-235X |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | •An extensive evaluation of 28 superpixel algorithms on 5 datasets.•Explicit discussion of parameter optimization, including superpixel connectivity.•Presentation of visual quality, algorithm runtime, and a performance-based ranking.•The evaluated implementations as well as the benchmark are publicly available.
Superpixels group perceptually similar pixels to create visually meaningful entities while heavily reducing the number of primitives for subsequent processing steps. As of these properties, superpixel algorithms have received much attention since their naming in 2003 (Ren and Malik, 2003). By today, publicly available superpixel algorithms have turned into standard tools in low-level vision. As such, and due to their quick adoption in a wide range of applications, appropriate benchmarks are crucial for algorithm selection and comparison. Until now, the rapidly growing number of algorithms as well as varying experimental setups hindered the development of a unifying benchmark. We present a comprehensive evaluation of 28 state-of-the-art superpixel algorithms utilizing a benchmark focussing on fair comparison and designed to provide new insights relevant for applications. To this end, we explicitly discuss parameter optimization and the importance of strictly enforcing connectivity. Furthermore, by extending well-known metrics, we are able to summarize algorithm performance independent of the number of generated superpixels, thereby overcoming a major limitation of available benchmarks. Furthermore, we discuss runtime, robustness against noise, blur and affine transformations, implementation details as well as aspects of visual quality. Finally, we present an overall ranking of superpixel algorithms which redefines the state-of-the-art and enables researchers to easily select appropriate algorithms and the corresponding implementations which themselves are made publicly available as part of our benchmark at http://www.davidstutz.de/projects/superpixel-benchmark/. |
|---|---|
| AbstractList | •An extensive evaluation of 28 superpixel algorithms on 5 datasets.•Explicit discussion of parameter optimization, including superpixel connectivity.•Presentation of visual quality, algorithm runtime, and a performance-based ranking.•The evaluated implementations as well as the benchmark are publicly available.
Superpixels group perceptually similar pixels to create visually meaningful entities while heavily reducing the number of primitives for subsequent processing steps. As of these properties, superpixel algorithms have received much attention since their naming in 2003 (Ren and Malik, 2003). By today, publicly available superpixel algorithms have turned into standard tools in low-level vision. As such, and due to their quick adoption in a wide range of applications, appropriate benchmarks are crucial for algorithm selection and comparison. Until now, the rapidly growing number of algorithms as well as varying experimental setups hindered the development of a unifying benchmark. We present a comprehensive evaluation of 28 state-of-the-art superpixel algorithms utilizing a benchmark focussing on fair comparison and designed to provide new insights relevant for applications. To this end, we explicitly discuss parameter optimization and the importance of strictly enforcing connectivity. Furthermore, by extending well-known metrics, we are able to summarize algorithm performance independent of the number of generated superpixels, thereby overcoming a major limitation of available benchmarks. Furthermore, we discuss runtime, robustness against noise, blur and affine transformations, implementation details as well as aspects of visual quality. Finally, we present an overall ranking of superpixel algorithms which redefines the state-of-the-art and enables researchers to easily select appropriate algorithms and the corresponding implementations which themselves are made publicly available as part of our benchmark at http://www.davidstutz.de/projects/superpixel-benchmark/. |
| Author | Hermans, Alexander Leibe, Bastian Stutz, David |
| Author_xml | – sequence: 1 givenname: David surname: Stutz fullname: Stutz, David email: david.stutz@rwth-aachen.de – sequence: 2 givenname: Alexander surname: Hermans fullname: Hermans, Alexander – sequence: 3 givenname: Bastian surname: Leibe fullname: Leibe, Bastian |
| BookMark | eNp9kM9OwzAMhyM0JLbBC3DqC6TYydZQxGWa-CdN4gBI3KIscUSm0k5JNsHb0zJOHHayffjs3-cJG7VdS4xdIpQIWF1tSrsPu1IAqhJkCaBO2BihBi7k_H009EpxiTNxxiYpbQAQZzWOmXjZbSluwxc16aZYtAXtTbMzOXRt0fkif1CRssnEO8_7gZuYz9mpN02ii786ZW_3d6_LR756fnhaLlbcSoDM-1zgva-8c7Y_tkYHAmU1q2TlqJKonKpUba1QUtRghCRFci7FmmpCL4ycsuvDXhu7lCJ5bUP-TZajCY1G0IO73ujBXQ_uGqTu3XtU_EO3MXya-H0cuj1A_StoHyjqZAO1llyIZLN2XTiG_wC33nRD |
| CitedBy_id | crossref_primary_10_1080_15481603_2025_2498188 crossref_primary_10_3390_sym10050169 crossref_primary_10_1016_j_engappai_2023_107212 crossref_primary_10_1002_rse2_260 crossref_primary_10_3390_rs11090998 crossref_primary_10_1109_ACCESS_2020_2984720 crossref_primary_10_1007_s00371_020_01852_2 crossref_primary_10_1109_TGRS_2023_3294227 crossref_primary_10_1049_el_2019_1092 crossref_primary_10_1145_3286977 crossref_primary_10_1007_s11042_024_19799_0 crossref_primary_10_1117_1_JRS_18_014530 crossref_primary_10_1109_TGRS_2020_3047126 crossref_primary_10_1109_TGRS_2021_3108585 crossref_primary_10_1109_TMM_2019_2907047 crossref_primary_10_1109_LSP_2021_3106586 crossref_primary_10_1109_ACCESS_2019_2939025 crossref_primary_10_1080_02286203_2023_2274258 crossref_primary_10_1109_ACCESS_2023_3293538 crossref_primary_10_3390_rs11050512 crossref_primary_10_3390_rs10081289 crossref_primary_10_3390_rs12111868 crossref_primary_10_1111_jmi_13072 crossref_primary_10_3390_s20092557 crossref_primary_10_1016_j_bspc_2021_103207 crossref_primary_10_1145_3652509 crossref_primary_10_1109_TCSVT_2023_3347402 crossref_primary_10_3390_rs15030715 crossref_primary_10_1007_s11227_021_03666_y crossref_primary_10_1111_cgf_14156 crossref_primary_10_1016_j_bspc_2022_104059 crossref_primary_10_1007_s11517_024_03093_0 crossref_primary_10_1016_j_asoc_2024_111467 crossref_primary_10_3390_s22166043 crossref_primary_10_3390_f16050827 crossref_primary_10_1016_j_optlastec_2020_106703 crossref_primary_10_1109_JSTARS_2023_3324770 crossref_primary_10_1080_02726351_2023_2214095 crossref_primary_10_1109_ACCESS_2020_2981666 crossref_primary_10_1186_s13640_018_0378_3 crossref_primary_10_1109_ACCESS_2020_2985106 crossref_primary_10_3390_jimaging9030059 crossref_primary_10_1016_j_asoc_2025_113389 crossref_primary_10_1109_JSTARS_2023_3265365 crossref_primary_10_1007_s11554_020_01021_7 crossref_primary_10_3390_s19081795 crossref_primary_10_1016_j_neucom_2024_129028 crossref_primary_10_1007_s11229_020_02629_9 crossref_primary_10_1016_j_jag_2022_102935 crossref_primary_10_1016_j_cageo_2019_104395 crossref_primary_10_1007_s10044_020_00925_1 crossref_primary_10_3390_s22030906 crossref_primary_10_1364_AO_58_0000B9 crossref_primary_10_1063_5_0247978 crossref_primary_10_5753_jbcs_2025_4278 crossref_primary_10_1109_JSTARS_2021_3076005 crossref_primary_10_1016_j_neucom_2022_12_028 crossref_primary_10_1109_JSTARS_2023_3281892 crossref_primary_10_1109_LGRS_2022_3201753 crossref_primary_10_1016_j_cageo_2021_105017 crossref_primary_10_3390_rs13152903 crossref_primary_10_1080_07038992_2020_1791693 crossref_primary_10_1109_TIP_2020_3002078 crossref_primary_10_1007_s12145_023_01040_5 crossref_primary_10_1016_j_jag_2018_04_011 crossref_primary_10_1016_j_rse_2020_111803 crossref_primary_10_1109_ACCESS_2023_3312181 crossref_primary_10_1109_TIP_2019_2957937 crossref_primary_10_3390_rs15041123 crossref_primary_10_1109_JBHI_2019_2910883 crossref_primary_10_1007_s00371_023_03218_w crossref_primary_10_1007_s11042_019_08438_8 crossref_primary_10_1016_j_patrec_2020_02_018 crossref_primary_10_1016_j_dsp_2025_105068 crossref_primary_10_1016_j_sigpro_2021_108277 crossref_primary_10_2478_ijssis_2023_0008 crossref_primary_10_1109_JSTARS_2025_3600810 crossref_primary_10_1002_rob_21915 crossref_primary_10_1088_1742_6596_1237_3_032027 crossref_primary_10_3390_rs11050556 crossref_primary_10_1038_s41598_024_74179_w crossref_primary_10_3390_jimaging7060093 crossref_primary_10_1016_j_imavis_2019_06_011 crossref_primary_10_1109_TIP_2020_2995056 crossref_primary_10_1080_01431161_2024_2384098 crossref_primary_10_1109_JBHI_2023_3240297 crossref_primary_10_1016_j_ecolind_2024_112108 crossref_primary_10_1093_jcde_qwac141 crossref_primary_10_3390_rs13142687 crossref_primary_10_1016_j_procs_2020_04_045 crossref_primary_10_1016_j_compind_2018_03_010 crossref_primary_10_1016_j_imavis_2021_104315 crossref_primary_10_3390_app112210876 crossref_primary_10_1016_j_eswa_2020_113349 crossref_primary_10_1007_s11263_020_01352_9 crossref_primary_10_1109_JSTARS_2022_3181720 crossref_primary_10_3390_rs16234344 crossref_primary_10_3390_rs11222627 crossref_primary_10_1007_s11548_021_02497_9 crossref_primary_10_1016_j_patcog_2022_108838 crossref_primary_10_1016_j_cag_2024_104014 crossref_primary_10_1016_j_neucom_2020_02_127 crossref_primary_10_1080_10106049_2018_1497093 crossref_primary_10_1016_j_patcog_2020_107705 crossref_primary_10_1109_TBDATA_2024_3423719 crossref_primary_10_3390_rs14071568 crossref_primary_10_1007_s11760_019_01517_1 crossref_primary_10_3390_s19081766 crossref_primary_10_1016_j_cviu_2018_01_006 crossref_primary_10_3390_app13085039 crossref_primary_10_1016_j_patcog_2023_109673 crossref_primary_10_3390_rs10101519 crossref_primary_10_3390_s23146648 crossref_primary_10_1016_j_agsy_2025_104360 crossref_primary_10_1016_j_cag_2020_12_002 crossref_primary_10_1007_s10489_019_01595_1 crossref_primary_10_1109_TIP_2021_3108403 crossref_primary_10_1117_1_JEI_34_2_023020 crossref_primary_10_1186_s12864_020_06832_3 crossref_primary_10_1109_TIP_2023_3290523 crossref_primary_10_1080_10589759_2024_2400588 crossref_primary_10_3390_rs13214315 crossref_primary_10_3390_e20110827 crossref_primary_10_1007_s11760_021_02066_2 crossref_primary_10_3390_jimaging8090244 crossref_primary_10_3390_e23121599 crossref_primary_10_1080_01431161_2022_2111532 crossref_primary_10_1109_JSTARS_2022_3168691 crossref_primary_10_1109_TIP_2022_3187563 crossref_primary_10_1038_s41598_025_08711_x crossref_primary_10_1109_JBHI_2021_3136568 crossref_primary_10_3390_app8122356 crossref_primary_10_3390_s23021002 crossref_primary_10_1109_TIP_2018_2848548 crossref_primary_10_1016_j_sigpro_2019_02_015 crossref_primary_10_1007_s00521_023_08452_w crossref_primary_10_1109_TGRS_2020_3000672 crossref_primary_10_1016_j_rse_2024_114274 crossref_primary_10_1111_mice_12903 crossref_primary_10_1109_TFUZZ_2020_3029939 crossref_primary_10_1007_s12665_023_10840_3 crossref_primary_10_1016_j_ecoinf_2021_101551 crossref_primary_10_1007_s11042_023_14861_9 crossref_primary_10_3390_rs11243026 crossref_primary_10_1038_s41598_023_35518_5 crossref_primary_10_1109_TIP_2023_3234700 crossref_primary_10_1016_j_ins_2022_10_039 crossref_primary_10_1109_TGRS_2022_3177935 crossref_primary_10_1007_s10851_023_01156_9 crossref_primary_10_1007_s11554_021_01128_5 crossref_primary_10_1016_j_compeleceng_2025_110358 crossref_primary_10_1016_j_cemconres_2019_105824 crossref_primary_10_3390_s20154173 crossref_primary_10_1109_TGRS_2020_3040452 crossref_primary_10_1088_1742_6596_2078_1_012040 crossref_primary_10_1109_TIP_2019_2959233 crossref_primary_10_1109_JSTARS_2023_3264452 crossref_primary_10_1109_TGRS_2021_3075956 crossref_primary_10_1016_j_cels_2021_04_008 crossref_primary_10_1109_TIM_2025_3544360 crossref_primary_10_1016_j_patcog_2020_107532 crossref_primary_10_1016_j_sigpro_2019_02_021 crossref_primary_10_3390_s20102969 crossref_primary_10_1016_j_jag_2022_103068 crossref_primary_10_3390_jimaging5060057 crossref_primary_10_1002_ima_22591 crossref_primary_10_1016_j_patrec_2023_01_003 crossref_primary_10_1051_itmconf_20246701048 crossref_primary_10_1016_j_cageo_2022_105232 crossref_primary_10_3390_s23041876 crossref_primary_10_1016_j_patcog_2022_109045 crossref_primary_10_1007_s11045_022_00854_8 crossref_primary_10_1016_j_compind_2023_103885 crossref_primary_10_1109_JSTARS_2024_3394771 crossref_primary_10_1016_j_cageo_2022_105109 crossref_primary_10_3390_rs12213603 crossref_primary_10_1007_s12524_020_01240_2 crossref_primary_10_3390_info12050196 crossref_primary_10_1109_TIP_2022_3176537 crossref_primary_10_1016_j_cma_2024_117677 crossref_primary_10_1109_TMM_2020_3009502 crossref_primary_10_1016_j_compag_2023_107629 crossref_primary_10_1109_TCI_2021_3139328 crossref_primary_10_1016_j_biosystemseng_2022_02_011 crossref_primary_10_1109_ACCESS_2019_2963055 crossref_primary_10_3390_sym13030518 crossref_primary_10_1109_TMM_2022_3163459 crossref_primary_10_15302_J_QB_021_0275 crossref_primary_10_1016_j_isprsjprs_2019_11_006 crossref_primary_10_1016_j_patcog_2019_03_012 crossref_primary_10_1109_JSTARS_2020_3011221 crossref_primary_10_1007_s00371_017_1422_5 crossref_primary_10_1016_j_compeleceng_2023_108610 crossref_primary_10_1007_s10489_023_04512_9 crossref_primary_10_1016_j_heliyon_2024_e34711 crossref_primary_10_3390_sym10100467 crossref_primary_10_1016_j_media_2022_102385 crossref_primary_10_3390_a13100257 crossref_primary_10_1049_iet_ipr_2019_0949 crossref_primary_10_1109_ACCESS_2025_3566506 crossref_primary_10_1109_LGRS_2020_3022478 crossref_primary_10_1186_s12880_022_00801_w crossref_primary_10_1109_TIP_2021_3070732 crossref_primary_10_1016_j_neucom_2024_127927 crossref_primary_10_1007_s00521_022_07315_0 crossref_primary_10_1109_TCSVT_2022_3221925 crossref_primary_10_3390_sym16081011 crossref_primary_10_1007_s10278_020_00401_6 crossref_primary_10_1007_s41095_020_0177_5 crossref_primary_10_3390_app12115370 crossref_primary_10_1016_j_compag_2024_109051 crossref_primary_10_1016_j_media_2024_103141 crossref_primary_10_3390_rs15051441 crossref_primary_10_1177_1094342020945026 crossref_primary_10_1007_s11042_023_16569_2 crossref_primary_10_1016_j_engappai_2022_104709 crossref_primary_10_3390_rs13234899 crossref_primary_10_1016_j_patcog_2021_107964 crossref_primary_10_3390_info12020094 crossref_primary_10_1109_TCSVT_2020_3019109 crossref_primary_10_1016_j_neucom_2025_131502 crossref_primary_10_3390_rs15112889 crossref_primary_10_1016_j_imavis_2021_104263 crossref_primary_10_1155_2020_8886178 crossref_primary_10_3390_rs11111340 crossref_primary_10_3390_rs13061061 crossref_primary_10_1111_2041_210X_14295 crossref_primary_10_3390_rs11060634 crossref_primary_10_1016_j_jag_2023_103556 crossref_primary_10_3390_rs14236017 crossref_primary_10_1016_j_optlaseng_2025_109281 crossref_primary_10_1109_ACCESS_2021_3114324 crossref_primary_10_1016_j_biosystemseng_2019_06_016 crossref_primary_10_1016_j_bspc_2024_106304 crossref_primary_10_1007_s41064_020_00116_x crossref_primary_10_3390_sym16081000 crossref_primary_10_1145_3386090 crossref_primary_10_3390_rs12030473 crossref_primary_10_3390_rs14122914 crossref_primary_10_1109_ACCESS_2020_2975896 crossref_primary_10_1016_j_tust_2024_106072 crossref_primary_10_3390_sym12091417 crossref_primary_10_1016_j_engappai_2021_104281 crossref_primary_10_1080_2573234X_2021_1908861 crossref_primary_10_1109_TGRS_2019_2961599 crossref_primary_10_1016_j_patcog_2022_109082 crossref_primary_10_3390_info11040223 crossref_primary_10_3390_rs11030231 crossref_primary_10_1109_TIP_2022_3188155 crossref_primary_10_1186_s13634_023_00999_z crossref_primary_10_1080_01431161_2018_1465614 crossref_primary_10_1109_JSTARS_2025_3542255 crossref_primary_10_1016_j_patcog_2020_107667 crossref_primary_10_1109_LSP_2020_3015433 crossref_primary_10_3390_s20061682 crossref_primary_10_1002_nbm_70141 crossref_primary_10_1007_s00521_024_10184_4 crossref_primary_10_3390_app8060969 crossref_primary_10_1109_JSTARS_2021_3067349 crossref_primary_10_1109_TGRS_2019_2922672 crossref_primary_10_1109_LSP_2024_3393349 crossref_primary_10_3390_rs12244115 crossref_primary_10_3390_sym16121622 crossref_primary_10_3390_rs12010066 crossref_primary_10_1007_s11042_021_10900_5 crossref_primary_10_3390_s20226429 crossref_primary_10_3390_rs11030227 crossref_primary_10_3390_s18092808 crossref_primary_10_3389_fmars_2024_1411717 crossref_primary_10_3390_diagnostics13243611 crossref_primary_10_1007_s13347_023_00635_6 crossref_primary_10_4049_jimmunol_2100811 crossref_primary_10_3390_app10124415 crossref_primary_10_1109_THMS_2022_3222021 crossref_primary_10_1111_grs_12288 crossref_primary_10_3390_rs11192308 crossref_primary_10_1016_j_imavis_2022_104596 crossref_primary_10_1109_ACCESS_2020_2999942 |
| Cites_doi | 10.1109/34.868688 10.1109/TPAMI.2010.161 10.1007/s11263-007-0090-8 10.1109/TMI.2011.2171705 10.1007/s11263-006-0031-y 10.1007/978-1-4471-6515-6 10.1007/BF02998459 10.1023/B:VISI.0000022288.19776.77 10.1007/s11263-014-0777-6 10.1109/TPAMI.2004.1273918 10.1145/1073204.1073232 10.1109/TIP.2014.2300823 10.1109/TPAMI.2009.96 10.1109/TMM.2013.2285526 10.1109/TIP.2014.2302892 10.1007/s11263-015-0822-0 10.1109/TPAMI.2012.120 10.1007/s11263-008-0140-x |
| ContentType | Journal Article |
| Copyright | 2017 Elsevier Inc. |
| Copyright_xml | – notice: 2017 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.cviu.2017.03.007 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Engineering Computer Science |
| EISSN | 1090-235X |
| EndPage | 27 |
| ExternalDocumentID | 10_1016_j_cviu_2017_03_007 S1077314217300589 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 6TJ 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKC AAIKJ AAKOC AALRI AAMNW AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADFGL ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CAG COF CS3 DM4 DU5 EBS EFBJH EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HF~ HVGLF HZ~ IHE J1W JJJVA KOM LG5 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SSV SSZ T5K TN5 XPP ZMT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS SST ~HD |
| ID | FETCH-LOGICAL-c300t-1010fff6fddc114b1d021364636de6317d7679cc273290a23e7e3532be9e1f2a3 |
| ISICitedReferencesCount | 382 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000419933000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1077-3142 |
| IngestDate | Sat Nov 29 06:43:52 EST 2025 Tue Nov 18 20:51:21 EST 2025 Fri Feb 23 02:26:56 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Benchmark Image segmentation Evaluation Superpixels Superpixel segmentation Perceptual grouping |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c300t-1010fff6fddc114b1d021364636de6317d7679cc273290a23e7e3532be9e1f2a3 |
| PageCount | 27 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_cviu_2017_03_007 crossref_primary_10_1016_j_cviu_2017_03_007 elsevier_sciencedirect_doi_10_1016_j_cviu_2017_03_007 |
| PublicationCentury | 2000 |
| PublicationDate | January 2018 2018-01-00 |
| PublicationDateYYYYMMDD | 2018-01-01 |
| PublicationDate_xml | – month: 01 year: 2018 text: January 2018 |
| PublicationDecade | 2010 |
| PublicationTitle | Computer vision and image understanding |
| PublicationYear | 2018 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Song, Lichtenberg, Xiao (bib0082) 2015 He, Lau, Liu, Huang, Yang (bib0036) 2015; 115 Koniusz, Mikolajczyk (bib0042) 2009 Xiao, Owens, Torralba (bib0089) 2013 Perazzi, Krähenbühl, Pritch, Hornung (bib0068) 2012 Neubert, Protzel (bib0066) 2013 Levinshtein, Stere, Kutulakos, Fleet, Dickinson, Siddiqi (bib0044) 2009; 31 Rohkohl, Engel (bib0074) 2007 Hoiem, Stein, Efros, Hebert (bib0039) 2007 Lu, Yang, Min, Do (bib0050) 2013 Mester, Franke (bib0061) 1988 Vedaldi, A., Fulkerson, B., 2008. VLFeat: An Open and Portable Library of Computer Vision Algorithms. Gupta, Arbeláez, Girshick, Malik (bib0034) 2015; 112 Dong, Chen, Xia, Huang, Yan (bib0022) 2013 Kim, Zhang, Kang, Ko (bib0041) 2013 Andres, Köthe, Helmstaedter, Denk, Hamprecht (bib0003) 2008 Gould, Fulton, Koller (bib0031) 2009 van den Bergh, Boix, Roig, de Capitani, van Gool (bib0008) 2013; abs/1309.3848 Achanta, Shaji, Smith, Lucchi, Fua, Süsstrunk (bib0002) 2012; 34 Liu, Salzmann, He (bib0048) 2014 Lui, Tuzel, Ramalingam, Chellappa (bib0053) 2011 Shu, Dehghan, Shah (bib0079) 2013 . Dollár, Wojek, Schiele, Perona (bib0020) 2009 Shi, Malik (bib0078) 2000; 22 Weikersdorfer, Gossow, Beetz (bib0088) 2012 Silberman, Hoiem, Kohli, Fergus (bib0080) 2012 Deng, Dong, Socher, Li, Li, Fei-Fei (bib0019) 2009 Felzenswalb, Huttenlocher (bib0026) 2004; 59 Yao, Boben, Fidler, Urtasun (bib0096) 2015 Ren, Shakhnarovich (bib0073) 2013 Veksler, Boykov, Mehrani (bib0086) 2010; 6315 Lin, Fidler, Urtasun (bib0045) 2013 Dollár, Zitnick (bib0021) 2013 Malladi, Ram, Rodriguez (bib0056) 2014 Hoiem, Efros, Hebert (bib0038) 2007; 75 Yamaguchi, M. H, Ortiz, Berg (bib0091) 2012 Conrad, Mertz, Mester (bib0016) 2013 Du, Shen, Yu, Wang (bib0023) 2012 Schick, Fischer, Stiefelhagen (bib0076) 2012 Janoch, Karayev, Jia, Barron, Fritz, Saenko, Darrell (bib0040) 2011 Rantalankila, Kannala, Rahtu (bib0070) 2014 Ren, Bo (bib0071) 2012 Ren, Malik (bib0072) 2003 Zhang, Hartley, Mashford, Burn (bib0099) 2011 Arbeláez, Pont-Tuset, Barron, Marqués, Malik (bib0005) 2014 Benesova, Kottman (bib0006) 2014 Haas, Donner, Burner, Holzer, Langs (bib0035) 2011 Achanta, Shaji, Smith, Lucchi, Fua, Süsstrunk (bib0001) 2010 Strassburg, Grzeszick, Rothacker, Fink (bib0083) 2015 van den Bergh, Boix, Roig, de Capitani, van Gool (bib0007) 2012; vol. 7578 Yan, Yu, Zhu, Lei, Li (bib0093) 2015 Bradski (bib0012) 2000 Criminisi, A., 2004. Microsoft research cambridge object recognition image database. Everingham, L.M., van Gool, L., Williams, C. K. I., Winn, J., Zisserman, A., 2007. The PASCAL Visual Object Classes Challenge (VOC2007) Results. Neubert, Protzel (bib0067) 2014 Yang, Gan, Gui, Li, Hou (bib0095) 2013 Meyer (bib0062) 1992 Tighe, Lazebnik (bib0084) 2010 den Bergh, Carton, van Gool (bib0010) 2013 Siva, Wong (bib0081) 2014 Hoiem, Efros, Hebert (bib0037) 2005; 24 Arbeláez, Maire, Fowlkes, Malik (bib0004) 2011; 33 Menze, Geiger (bib0059) 2015 Mester, Conrad, Guevara (bib0060) 2011 Lucchi, Smith, Achanta, Knott, Fua (bib0051) 2012; 31 Butler, Wulff, Stanley, Black (bib0013) 2012 Gadde, Jampani, Kiefel, Gehler (bib0028) 2015; abs/1511.06739 Xu, Corso (bib0090) 2012 van den Bergh, Roig, Boix, Manen, van Gool (bib0009) 2013 Gonfaus, Bosch, van de Weijer, Bagdanov, Serrat, Gonzàlez (bib0030) 2010 Neubert, Protzel (bib0065) 2012 Bódis-Szomorú, Riemenschneider, van Gool (bib0011) 2015 Lucchi, Smith, Achanta, Lepetit, Fua (bib0052) 2010 Lerma, Kosecka (bib0043) 2014 Freifeld, Li, Fisher (bib0027) 2015 Shen, Du, Wang, Li (bib0077) 2014; 23 Demsar (bib0018) 2006; 7 Wang, Lu, Yang, Yang (bib0087) 2011 Liu, Feng, Domokos, Xu, Huang, Hu, Yan (bib0049) 2014; 16 Lin, Maire, Belongie, Bourdev, Girshick, Hays, Perona, Ramanan, Dollár, Zitnick (bib0046) 2014; abs/1405.0312 Yamaguchi, McAllester, Urtasun (bib0092) 2014 Lv (bib0054) 2015; 8 Marcotegui, Meyer (bib0057) 1997; 52 Grundmann, Kwatra, Han, Essa (bib0033) 2010 Moore, Prince, Warrell, Mohammed, Jones (bib0063) 2008 Russell, Torralba, Murphy, Freeman (bib0075) 2008; 77 Zeng, Wang, Wang, Gan, Zha (bib0097) 2011 Engel, Spinello, Triebel, Siegwart, Bülthoff, Curio (bib0025) 2009 Morerio, Marcenaro, Regazzoni (bib0064) 2014 Gould, Rodgers, Cohen, Elidan, Koller (bib0032) 2008; 80 Liu, Shen, Lin (bib0047) 2014; abs/1411.6387 Ducournau, Rital, Bretto, Laget (bib0024) 2010 Geiger, Wang (bib0029) 2015 Zhang, Kan, Schwing, Urtasun (bib0098) 2013 Martin, Fowlkes, Malik (bib0058) 2004; 26 Yang, Lu, Yang (bib0094) 2014; 23 Carr, Hartley (bib0015) 2009 Perbet, Maki (bib0069) 2011 Buyssens, Gardin, Ruan (bib0014) 2014; 35 Koniusz (10.1016/j.cviu.2017.03.007_bib0042) 2009 Neubert (10.1016/j.cviu.2017.03.007_bib0066) 2013 Russell (10.1016/j.cviu.2017.03.007_bib0075) 2008; 77 Yao (10.1016/j.cviu.2017.03.007_bib0096) 2015 Benesova (10.1016/j.cviu.2017.03.007_bib0006) 2014 Liu (10.1016/j.cviu.2017.03.007_bib0049) 2014; 16 den Bergh (10.1016/j.cviu.2017.03.007_bib0010) 2013 Gould (10.1016/j.cviu.2017.03.007_bib0032) 2008; 80 Carr (10.1016/j.cviu.2017.03.007_bib0015) 2009 Achanta (10.1016/j.cviu.2017.03.007_bib0002) 2012; 34 Felzenswalb (10.1016/j.cviu.2017.03.007_bib0026) 2004; 59 Arbeláez (10.1016/j.cviu.2017.03.007_bib0005) 2014 Lv (10.1016/j.cviu.2017.03.007_bib0054) 2015; 8 Ren (10.1016/j.cviu.2017.03.007_bib0073) 2013 Du (10.1016/j.cviu.2017.03.007_bib0023) 2012 Shu (10.1016/j.cviu.2017.03.007_bib0079) 2013 10.1016/j.cviu.2017.03.007_bib0017 Levinshtein (10.1016/j.cviu.2017.03.007_bib0044) 2009; 31 Arbeláez (10.1016/j.cviu.2017.03.007_bib0004) 2011; 33 Achanta (10.1016/j.cviu.2017.03.007_bib0001) 2010 Strassburg (10.1016/j.cviu.2017.03.007_bib0083) 2015 Mester (10.1016/j.cviu.2017.03.007_bib0060) 2011 Butler (10.1016/j.cviu.2017.03.007_bib0013) 2012 Xu (10.1016/j.cviu.2017.03.007_bib0090) 2012 van den Bergh (10.1016/j.cviu.2017.03.007_bib0009) 2013 Liu (10.1016/j.cviu.2017.03.007_bib0048) 2014 Bódis-Szomorú (10.1016/j.cviu.2017.03.007_bib0011) 2015 Zhang (10.1016/j.cviu.2017.03.007_bib0099) 2011 Menze (10.1016/j.cviu.2017.03.007_bib0059) 2015 Buyssens (10.1016/j.cviu.2017.03.007_bib0014) 2014; 35 Gupta (10.1016/j.cviu.2017.03.007_bib0034) 2015; 112 He (10.1016/j.cviu.2017.03.007_bib0036) 2015; 115 Deng (10.1016/j.cviu.2017.03.007_bib0019) 2009 Rantalankila (10.1016/j.cviu.2017.03.007_bib0070) 2014 Janoch (10.1016/j.cviu.2017.03.007_bib0040) 2011 Gadde (10.1016/j.cviu.2017.03.007_bib0028) 2015; abs/1511.06739 Hoiem (10.1016/j.cviu.2017.03.007_bib0037) 2005; 24 Hoiem (10.1016/j.cviu.2017.03.007_bib0039) 2007 Marcotegui (10.1016/j.cviu.2017.03.007_bib0057) 1997; 52 Lucchi (10.1016/j.cviu.2017.03.007_bib0052) 2010 Grundmann (10.1016/j.cviu.2017.03.007_bib0033) 2010 Neubert (10.1016/j.cviu.2017.03.007_bib0065) 2012 Liu (10.1016/j.cviu.2017.03.007_bib0047) 2014; abs/1411.6387 Andres (10.1016/j.cviu.2017.03.007_bib0003) 2008 Perbet (10.1016/j.cviu.2017.03.007_bib0069) 2011 Yang (10.1016/j.cviu.2017.03.007_bib0094) 2014; 23 Yang (10.1016/j.cviu.2017.03.007_bib0095) 2013 Geiger (10.1016/j.cviu.2017.03.007_bib0029) 2015 Zeng (10.1016/j.cviu.2017.03.007_bib0097) 2011 Tighe (10.1016/j.cviu.2017.03.007_bib0084) 2010 Shen (10.1016/j.cviu.2017.03.007_bib0077) 2014; 23 Rohkohl (10.1016/j.cviu.2017.03.007_bib0074) 2007 Shi (10.1016/j.cviu.2017.03.007_bib0078) 2000; 22 Conrad (10.1016/j.cviu.2017.03.007_bib0016) 2013 Lu (10.1016/j.cviu.2017.03.007_bib0050) 2013 Lui (10.1016/j.cviu.2017.03.007_bib0053) 2011 Dollár (10.1016/j.cviu.2017.03.007_bib0020) 2009 Song (10.1016/j.cviu.2017.03.007_bib0082) 2015 10.1016/j.cviu.2017.03.007_bib0055 Zhang (10.1016/j.cviu.2017.03.007_bib0098) 2013 van den Bergh (10.1016/j.cviu.2017.03.007_bib0008) 2013; abs/1309.3848 Malladi (10.1016/j.cviu.2017.03.007_bib0056) 2014 Yan (10.1016/j.cviu.2017.03.007_bib0093) 2015 Gould (10.1016/j.cviu.2017.03.007_bib0031) 2009 Moore (10.1016/j.cviu.2017.03.007_bib0063) 2008 Xiao (10.1016/j.cviu.2017.03.007_bib0089) 2013 Martin (10.1016/j.cviu.2017.03.007_bib0058) 2004; 26 Morerio (10.1016/j.cviu.2017.03.007_bib0064) 2014 Meyer (10.1016/j.cviu.2017.03.007_bib0062) 1992 Silberman (10.1016/j.cviu.2017.03.007_bib0080) 2012 Weikersdorfer (10.1016/j.cviu.2017.03.007_bib0088) 2012 Lin (10.1016/j.cviu.2017.03.007_bib0045) 2013 Schick (10.1016/j.cviu.2017.03.007_bib0076) 2012 Engel (10.1016/j.cviu.2017.03.007_bib0025) 2009 van den Bergh (10.1016/j.cviu.2017.03.007_bib0007) 2012; vol. 7578 Haas (10.1016/j.cviu.2017.03.007_bib0035) 2011 Yamaguchi (10.1016/j.cviu.2017.03.007_bib0092) 2014 Mester (10.1016/j.cviu.2017.03.007_bib0061) 1988 Veksler (10.1016/j.cviu.2017.03.007_bib0086) 2010; 6315 Dong (10.1016/j.cviu.2017.03.007_bib0022) 2013 Ren (10.1016/j.cviu.2017.03.007_bib0071) 2012 Lucchi (10.1016/j.cviu.2017.03.007_bib0051) 2012; 31 Yamaguchi (10.1016/j.cviu.2017.03.007_bib0091) 2012 Ren (10.1016/j.cviu.2017.03.007_bib0072) 2003 Perazzi (10.1016/j.cviu.2017.03.007_bib0068) 2012 Lin (10.1016/j.cviu.2017.03.007_bib0046) 2014; abs/1405.0312 Neubert (10.1016/j.cviu.2017.03.007_bib0067) 2014 Wang (10.1016/j.cviu.2017.03.007_bib0087) 2011 Kim (10.1016/j.cviu.2017.03.007_bib0041) 2013 Siva (10.1016/j.cviu.2017.03.007_bib0081) 2014 Gonfaus (10.1016/j.cviu.2017.03.007_bib0030) 2010 Demsar (10.1016/j.cviu.2017.03.007_bib0018) 2006; 7 Freifeld (10.1016/j.cviu.2017.03.007_bib0027) 2015 Hoiem (10.1016/j.cviu.2017.03.007_bib0038) 2007; 75 Bradski (10.1016/j.cviu.2017.03.007_sbref0012) 2000 10.1016/j.cviu.2017.03.007_bib0085 Ducournau (10.1016/j.cviu.2017.03.007_bib0024) 2010 Lerma (10.1016/j.cviu.2017.03.007_bib0043) 2014 Dollár (10.1016/j.cviu.2017.03.007_bib0021) 2013 |
| References_xml | – start-page: 62 year: 2012 end-page: 63 ident: bib0023 article-title: Superpixels using random walker publication-title: IEEE Global High Tech Congress on Electronics – volume: 31 start-page: 2290 year: 2009 end-page: 2297 ident: bib0044 article-title: TurboPixels: fast superpixels using geometric flows publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 930 year: 2012 end-page: 934 ident: bib0076 article-title: Measuring and evaluating the compactness of superpixels publication-title: International Conference on Pattern Recognition – year: 2013 ident: bib0066 article-title: Evaluating superpixels in video: Metrics beyond figure-ground segmentation publication-title: British Machine Vision Conference – start-page: 10 year: 2003 end-page: 17 ident: bib0072 article-title: Learning a classification model for segmentation publication-title: International Conference on Computer Vision – volume: 80 start-page: 300 year: 2008 end-page: 316 ident: bib0032 article-title: Multi-class segmentation with relative location prior publication-title: Int. J. Comput. Vis. – start-page: 733 year: 2012 end-page: 740 ident: bib0068 article-title: Saliency filters: contrast based filtering for salient region detection publication-title: IEEE Conference on Computer Vision and Pattern Recognition – reference: Everingham, L.M., van Gool, L., Williams, C. K. I., Winn, J., Zisserman, A., 2007. The PASCAL Visual Object Classes Challenge (VOC2007) Results. – volume: 112 start-page: 133 year: 2015 end-page: 149 ident: bib0034 article-title: Indoor scene understanding with RGB-D images: bottom-up segmentation, object detection and semantic segmentation publication-title: Int. J. Comput. Vis. – start-page: 616 year: 1988 end-page: 624 ident: bib0061 article-title: Statistical model based image segmentation using region growing, contour relaxation and classification publication-title: SPIE Symposium on Visual Communications and Image Processing – volume: 7 start-page: 1 year: 2006 end-page: 30 ident: bib0018 article-title: Statistical comparisons of classifiers over multiple data sets publication-title: J. Mach. Learn. Res. – volume: 6315 start-page: 211 year: 2010 end-page: 224 ident: bib0086 article-title: Superpixels and supervoxels in an energy optimization framework publication-title: European Conference on Computer Vision – start-page: 518 year: 2015 end-page: 527 ident: bib0083 article-title: On the influence of superpixel methods for image parsing publication-title: International Conference on Computer Vision Theory and Application – year: 2012 ident: bib0065 article-title: Superpixel benchmark and comparison publication-title: Forum Bildverarbeitung – volume: 77 start-page: 157 year: 2008 end-page: 173 ident: bib0075 article-title: Labelme: a database and web-based tool for image annotation publication-title: Int. J. Comput. Vis. – start-page: 463 year: 2010 end-page: 471 ident: bib0052 article-title: A fully automated approach to segmentation of irregularly shaped cellular structures in EM images publication-title: International Conference on Medical Image Computing and Computer Assisted Interventions – start-page: 250 year: 2011 end-page: 261 ident: bib0060 article-title: Multichannel Segmentation Using Contour Relaxation: Fast Super-pixels and Temporal Propagation publication-title: Scandinavian Conference Image Analysis – start-page: 1 year: 2009 end-page: 8 ident: bib0031 article-title: Decomposing a scene into geometric and semantically consistent regions publication-title: International Conference on Computer Vision – start-page: 1 year: 2014 end-page: 7 ident: bib0064 article-title: A generative superpixel method publication-title: International Conference on Information Fusion – volume: 22 start-page: 888 year: 2000 end-page: 905 ident: bib0078 article-title: Normalized cuts and image segmentation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 23 start-page: 1639 year: 2014 end-page: 1651 ident: bib0094 article-title: Robust superpixel tracking publication-title: Trans. Image Process. – start-page: 377 year: 2013 end-page: 384 ident: bib0009 article-title: Online video seeds for temporal window objectness publication-title: International Conference on Computer Vision – start-page: 996 year: 2014 end-page: 1001 ident: bib0067 article-title: Compact watershed and preemptive SLIC: on improving trade-offs of superpixel segmentation algorithms publication-title: International Conference on Pattern Recognition – start-page: 1 year: 2010 end-page: 4 ident: bib0024 article-title: Hypergraph coarsening for image superpixelization publication-title: International Symposium on I/V Communications and Mobile Network – start-page: 3280 year: 2010 end-page: 3287 ident: bib0030 article-title: Harmony potentials for joint classification and segmentation publication-title: IEEE Conference on Computer Vision and Pattern Recognition – year: 2010 ident: bib0001 article-title: SLIC Superpixels publication-title: Technical Report – start-page: 1323 year: 2011 end-page: 1330 ident: bib0087 article-title: Superpixel tracking publication-title: International Conference on Computer Vision – volume: 24 start-page: 577 year: 2005 end-page: 584 ident: bib0037 article-title: Automatic photo pop-up publication-title: ACM Trans. Graph. – start-page: 84 year: 2011 end-page: 91 ident: bib0099 article-title: Superpixels, occlusion and stereo publication-title: International Conference on Digital Image Computing Techniques and Applications – volume: 75 start-page: 151 year: 2007 end-page: 172 ident: bib0038 article-title: Recovering surface layout from an image publication-title: Int. J. Comput. Vis. – start-page: 363 year: 2013 end-page: 368 ident: bib0010 article-title: Depth SEEDS: recovering incomplete depth data using superpixels publication-title: Winter Conference on Applications of Computer Vision – volume: 52 start-page: 397 year: 1997 end-page: 407 ident: bib0057 article-title: Bottom-up segmentation of image sequences for coding publication-title: Ann. Télécommun. – start-page: 1202 year: 2012 end-page: 1209 ident: bib0090 article-title: Evaluation of super-voxel methods for early video processing publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 1273 year: 2013 end-page: 1280 ident: bib0098 article-title: Estimating the 3d layout of indoor scenes and its clutter from depth sensors publication-title: International Conference on Computer Vision – start-page: 183 year: 2015 end-page: 195 ident: bib0029 article-title: Joint 3d object and layout inference from a single RGB-D image publication-title: German Conference on Pattern Recognition – start-page: 1168 year: 2011 end-page: 1174 ident: bib0040 article-title: A category-level 3-d object dataset: putting the kinect to work publication-title: International Conference on Computer Vision Workshops – start-page: 2947 year: 2015 end-page: 2955 ident: bib0096 article-title: Real-time coarse-to-fine topologically preserving segmentation publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 1 year: 2009 end-page: 11 ident: bib0042 article-title: Segmentation based interest points and evaluation of unsupervised image segmentation methods publication-title: British Machine Vision Conference – start-page: 716 year: 2014 end-page: 723 ident: bib0048 article-title: Discrete-continuous depth estimation from a single image publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 2042 year: 2009 end-page: 2049 ident: bib0015 article-title: Minimizing energy functions on 4-connected lattices using elimination publication-title: International Conference on Computer Vision – start-page: 3408 year: 2013 end-page: 3415 ident: bib0022 article-title: A deformable mixture parsing model with parselets publication-title: International Conference on Computer Vision – volume: 16 start-page: 253 year: 2014 end-page: 265 ident: bib0049 article-title: Fashion parsing with weak color-category labels publication-title: IEEE Trans. Multimedia – year: 2009 ident: bib0019 article-title: ImageNet: a large-scale hierarchical image database publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 593 year: 2012 end-page: 601 ident: bib0071 article-title: Discriminatively trained sparse code gradients for contour detection publication-title: Neural Information Processing Systems – start-page: 611 year: 2012 end-page: 625 ident: bib0013 article-title: A naturalistic open source movie for optical flow evaluation publication-title: European Conference on Computer Vision – start-page: 746 year: 2012 end-page: 760 ident: bib0080 article-title: Indoor segmentation and support inference from RGBD images publication-title: European Conference on Computer Vision – start-page: 1841 year: 2013 end-page: 1848 ident: bib0021 article-title: Structured forests for fast edge detection publication-title: International Conference on Computer Vision – start-page: 1854 year: 2013 end-page: 1861 ident: bib0050 article-title: Patch match filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 1417 year: 2013 end-page: 1424 ident: bib0045 article-title: Holistic scene understanding for 3d object detection with RGBD cameras publication-title: International Conference on Computer Vision – volume: 8 start-page: 239 year: 2015 end-page: 248 ident: bib0054 article-title: An improved slic superpixels using reciprocal nearest neighbor clustering publication-title: Int. J. Signal Process. Image Process. Pattern Recognit. – volume: abs/1511.06739 year: 2015 ident: bib0028 article-title: Superpixel convolutional networks using bilateral inceptions publication-title: Comput. Res. Reposit. – start-page: 2011 year: 2013 end-page: 2018 ident: bib0073 article-title: Image segmentation by cascaded region agglomeration publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 35 year: 2013 end-page: 46 ident: bib0095 article-title: 3-d geometry enhanced superpixels for RGB-D data publication-title: Pacific-Rim Conference on Multimedia – volume: 33 start-page: 898 year: 2011 end-page: 916 ident: bib0004 article-title: Contour detection and hierarchical image segmentation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 304 year: 2009 end-page: 311 ident: bib0020 article-title: Pedestrian detection: a benchmark publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 145 year: 2014 end-page: 148 ident: bib0056 article-title: Superpixels using morphology for rock image segmentation publication-title: IEEE Southwest Symposium on Image Analysis and Interpretation – volume: 23 start-page: 1451 year: 2014 end-page: 1462 ident: bib0077 article-title: Lazy random walks for superpixel segmentation publication-title: Trans. Image Process. – start-page: 5107 year: 2015 end-page: 5116 ident: bib0093 article-title: Object detection by labeling superpixels publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 2141 year: 2010 end-page: 2148 ident: bib0033 article-title: Efficient hierarchical graph-based video segmentation publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 756 year: 2014 end-page: 771 ident: bib0092 article-title: Efficient joint segmentation, occlusion labeling, stereo and flow estimation publication-title: European Conference on Computer Vision – volume: abs/1405.0312 year: 2014 ident: bib0046 article-title: Microsoft COCO: common objects in context publication-title: Comput. Res. Reposit. – start-page: 280 year: 2013 end-page: 293 ident: bib0016 article-title: Contour-relaxed superpixels publication-title: Energy Minimization Methods in Computer Vision and Pattern Recognition – reference: Vedaldi, A., Fulkerson, B., 2008. VLFeat: An Open and Portable Library of Computer Vision Algorithms. – volume: abs/1309.3848 year: 2013 ident: bib0008 article-title: SEEDS: superpixels extracted via energy-driven sampling publication-title: Comput. Res. Reposit. – start-page: 303 year: 1992 end-page: 306 ident: bib0062 article-title: Color image segmentation publication-title: International Conference on Image Processing and its Applications – year: 2000 ident: bib0012 article-title: The opencv library publication-title: Dr. Dobb’s Journal of Software Tools – start-page: 447 year: 2011 end-page: 454 ident: bib0097 article-title: Structure-sensitive superpixels via geodesic distance publication-title: International Conference on Computer Vision – start-page: 259 year: 2013 end-page: 260 ident: bib0041 article-title: Improved simple linear iterative clustering superpixels publication-title: International Symposium on Consumer Electronics – start-page: 1 year: 2007 end-page: 8 ident: bib0039 article-title: Recovering occlusion boundaries from a single image publication-title: International Conference on Computer Vision – start-page: 328 year: 2014 end-page: 335 ident: bib0005 article-title: Multiscale combinatorial grouping publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 3570 year: 2012 end-page: 3577 ident: bib0091 article-title: Parsing clothing in fashion photographs publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 26 year: 2011 end-page: 30 ident: bib0069 article-title: Homogeneous superpixels from random walks publication-title: Machine Vision and Applications, Conference on – volume: 31 start-page: 474 year: 2012 end-page: 486 ident: bib0051 article-title: Supervoxel-based segmentation of mitochondria in EM image stacks with learned shape features publication-title: IEEE Trans. Med. Imaging – volume: 35 start-page: 20 year: 2014 end-page: 26 ident: bib0014 article-title: Eikonal based region growing for superpixels generation: application to semi-supervised real time organ segmentation in CT images publication-title: Innovat. Res. BioMed. Eng. – volume: vol. 7578 start-page: 13 year: 2012 end-page: 26 ident: bib0007 article-title: SEEDS: superpixels extracted via energy-driven sampling publication-title: European Conference on Computer Vision – start-page: 2639 year: 2014 end-page: 2645 ident: bib0043 article-title: Semantic segmentation with heterogeneous sensor coverages publication-title: IEEE International Conference on Robotics and Automation – start-page: 352 year: 2010 end-page: 365 ident: bib0084 article-title: SuperParsing: scalable nonparametric image parsing with superpixels publication-title: European Conference on Computer Vision – volume: 26 start-page: 530 year: 2004 end-page: 549 ident: bib0058 article-title: Learning to detect natural image boundaries using local brightness, color, and texture cues publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 2011 year: 2015 end-page: 2020 ident: bib0011 article-title: Superpixel meshes for fast edge-preserving surface reconstruction publication-title: IEEE Conference on Computer Vision and Pattern Recognition – volume: 34 start-page: 2274 year: 2012 end-page: 2281 ident: bib0002 article-title: SLIC superpixels compared to state-of-the-art superpixel methods publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: Criminisi, A., 2004. Microsoft research cambridge object recognition image database. – start-page: 3061 year: 2015 end-page: 3070 ident: bib0059 article-title: Object scene flow for autonomous vehicles publication-title: IEEE Conference on Computer Vision and Pattern Recognition, Boston, Massachusetts – start-page: 2417 year: 2014 end-page: 2424 ident: bib0070 article-title: Generating object segmentation proposals using global and local search publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 58 year: 2011 end-page: 68 ident: bib0035 article-title: Superpixel-based interest points for effective bags of visual words medical image retrieval publication-title: International Conference onMedical Image Computing and Computer Assisted Interventions – start-page: 127 year: 2014 end-page: 134 ident: bib0081 article-title: Grid seams: A fast superpixel algorithm for real-time applications publication-title: Computer and Robot Vision, Conference on – start-page: 1625 year: 2013 end-page: 1632 ident: bib0089 article-title: SUN3D: a database of big spaces reconstructed using sfm and object labels publication-title: International Conference on Computer Vision – start-page: 2087 year: 2012 end-page: 2090 ident: bib0088 article-title: Depth-adaptive superpixels publication-title: International Conference on Pattern Recognition – year: 2014 ident: bib0006 article-title: Fast superpixel segmentation using morphological processing publication-title: Conference on Machine Vision and Machine Learning – start-page: 2184 year: 2015 end-page: 2188 ident: bib0027 article-title: A fast method for inferring high-quality simply-connected superpixels publication-title: International Conference on Image Processing – start-page: 142 year: 2008 end-page: 152 ident: bib0003 article-title: Segmentation of SBFSEM volume data of neural tissue by hierarchical classification publication-title: DAGM Annual Pattern Recognition Symposium – start-page: 248 year: 2009 end-page: 252 ident: bib0025 article-title: Medial features for superpixel segmentation publication-title: IAPR International Conference on Machine Vision Applications – start-page: 3721 year: 2013 end-page: 3727 ident: bib0079 article-title: Improving an object detector and extracting regions using superpixels publication-title: IEEE Conference on Computer Vision and Pattern Recognition – volume: 59 start-page: 167 year: 2004 end-page: 181 ident: bib0026 article-title: Efficient graph-based image segmentation publication-title: Int. J. Comput. Vis. – volume: abs/1411.6387 year: 2014 ident: bib0047 article-title: Deep convolutional neural fields for depth estimation from a single image publication-title: Comput. Res. Reposit. – reference: . – start-page: 1 year: 2008 end-page: 8 ident: bib0063 article-title: Superpixel lattices publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 254 year: 2007 end-page: 263 ident: bib0074 article-title: Efficient image segmentation using pairwise pixel similarities publication-title: DAGM Annual Pattern Recognition Symposium – volume: 115 start-page: 330 year: 2015 end-page: 344 ident: bib0036 article-title: Supercnn: a superpixelwise convolutional neural network for salient object detection publication-title: Int. J. Comput. Vis. – start-page: 567 year: 2015 end-page: 576 ident: bib0082 article-title: SUN RGB-D: a RGB-D scene understanding benchmark suite publication-title: IEEE Conference on Computer Vision and Pattern Recognition – start-page: 2097 year: 2011 end-page: 2104 ident: bib0053 article-title: Entropy rate superpixel segmentation publication-title: IEEE Conference on Computer Vision and Pattern Recognition – volume: 7 start-page: 1 year: 2006 ident: 10.1016/j.cviu.2017.03.007_bib0018 article-title: Statistical comparisons of classifiers over multiple data sets publication-title: J. Mach. Learn. Res. – volume: 22 start-page: 888 issue: 8 year: 2000 ident: 10.1016/j.cviu.2017.03.007_bib0078 article-title: Normalized cuts and image segmentation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/34.868688 – start-page: 611 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0013 article-title: A naturalistic open source movie for optical flow evaluation – start-page: 756 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0092 article-title: Efficient joint segmentation, occlusion labeling, stereo and flow estimation – start-page: 142 year: 2008 ident: 10.1016/j.cviu.2017.03.007_bib0003 article-title: Segmentation of SBFSEM volume data of neural tissue by hierarchical classification – volume: 33 start-page: 898 issue: 5 year: 2011 ident: 10.1016/j.cviu.2017.03.007_bib0004 article-title: Contour detection and hierarchical image segmentation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2010.161 – start-page: 518 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0083 article-title: On the influence of superpixel methods for image parsing – volume: vol. 7578 start-page: 13 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0007 article-title: SEEDS: superpixels extracted via energy-driven sampling – start-page: 303 year: 1992 ident: 10.1016/j.cviu.2017.03.007_bib0062 article-title: Color image segmentation – start-page: 10 year: 2003 ident: 10.1016/j.cviu.2017.03.007_bib0072 article-title: Learning a classification model for segmentation – start-page: 2087 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0088 article-title: Depth-adaptive superpixels – start-page: 1854 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0050 article-title: Patch match filter: efficient edge-aware filtering meets randomized search for fast correspondence field estimation – start-page: 2011 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0073 article-title: Image segmentation by cascaded region agglomeration – start-page: 1323 year: 2011 ident: 10.1016/j.cviu.2017.03.007_bib0087 article-title: Superpixel tracking – start-page: 1168 year: 2011 ident: 10.1016/j.cviu.2017.03.007_bib0040 article-title: A category-level 3-d object dataset: putting the kinect to work – start-page: 62 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0023 article-title: Superpixels using random walker – start-page: 2097 year: 2011 ident: 10.1016/j.cviu.2017.03.007_bib0053 article-title: Entropy rate superpixel segmentation – volume: 77 start-page: 157 issue: 1–3 year: 2008 ident: 10.1016/j.cviu.2017.03.007_bib0075 article-title: Labelme: a database and web-based tool for image annotation publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-007-0090-8 – start-page: 463 year: 2010 ident: 10.1016/j.cviu.2017.03.007_bib0052 article-title: A fully automated approach to segmentation of irregularly shaped cellular structures in EM images – ident: 10.1016/j.cviu.2017.03.007_bib0055 – start-page: 1202 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0090 article-title: Evaluation of super-voxel methods for early video processing – ident: 10.1016/j.cviu.2017.03.007_bib0017 – volume: 35 start-page: 20 issue: 1 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0014 article-title: Eikonal based region growing for superpixels generation: application to semi-supervised real time organ segmentation in CT images publication-title: Innovat. Res. BioMed. Eng. – year: 2010 ident: 10.1016/j.cviu.2017.03.007_bib0001 article-title: SLIC Superpixels – start-page: 1 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0064 article-title: A generative superpixel method – volume: 31 start-page: 474 issue: 2 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0051 article-title: Supervoxel-based segmentation of mitochondria in EM image stacks with learned shape features publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2011.2171705 – start-page: 2417 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0070 article-title: Generating object segmentation proposals using global and local search – volume: abs/1511.06739 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0028 article-title: Superpixel convolutional networks using bilateral inceptions publication-title: Comput. Res. Reposit. – start-page: 259 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0041 article-title: Improved simple linear iterative clustering superpixels – start-page: 3280 year: 2010 ident: 10.1016/j.cviu.2017.03.007_bib0030 article-title: Harmony potentials for joint classification and segmentation – year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0065 article-title: Superpixel benchmark and comparison – volume: 75 start-page: 151 issue: 1 year: 2007 ident: 10.1016/j.cviu.2017.03.007_bib0038 article-title: Recovering surface layout from an image publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-006-0031-y – start-page: 716 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0048 article-title: Discrete-continuous depth estimation from a single image doi: 10.1007/978-1-4471-6515-6 – start-page: 1 year: 2009 ident: 10.1016/j.cviu.2017.03.007_bib0042 article-title: Segmentation based interest points and evaluation of unsupervised image segmentation methods – volume: 52 start-page: 397 issue: 7 year: 1997 ident: 10.1016/j.cviu.2017.03.007_bib0057 article-title: Bottom-up segmentation of image sequences for coding publication-title: Ann. Télécommun. doi: 10.1007/BF02998459 – start-page: 593 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0071 article-title: Discriminatively trained sparse code gradients for contour detection – start-page: 254 year: 2007 ident: 10.1016/j.cviu.2017.03.007_bib0074 article-title: Efficient image segmentation using pairwise pixel similarities – start-page: 377 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0009 article-title: Online video seeds for temporal window objectness – start-page: 58 year: 2011 ident: 10.1016/j.cviu.2017.03.007_bib0035 article-title: Superpixel-based interest points for effective bags of visual words medical image retrieval – volume: 8 start-page: 239 issue: 5 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0054 article-title: An improved slic superpixels using reciprocal nearest neighbor clustering publication-title: Int. J. Signal Process. Image Process. Pattern Recognit. – start-page: 3570 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0091 article-title: Parsing clothing in fashion photographs – start-page: 1417 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0045 article-title: Holistic scene understanding for 3d object detection with RGBD cameras – volume: 59 start-page: 167 issue: 2 year: 2004 ident: 10.1016/j.cviu.2017.03.007_bib0026 article-title: Efficient graph-based image segmentation publication-title: Int. J. Comput. Vis. doi: 10.1023/B:VISI.0000022288.19776.77 – ident: 10.1016/j.cviu.2017.03.007_bib0085 – start-page: 1841 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0021 article-title: Structured forests for fast edge detection – start-page: 304 year: 2009 ident: 10.1016/j.cviu.2017.03.007_bib0020 article-title: Pedestrian detection: a benchmark – start-page: 250 year: 2011 ident: 10.1016/j.cviu.2017.03.007_bib0060 article-title: Multichannel Segmentation Using Contour Relaxation: Fast Super-pixels and Temporal Propagation – start-page: 567 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0082 article-title: SUN RGB-D: a RGB-D scene understanding benchmark suite – volume: 112 start-page: 133 issue: 2 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0034 article-title: Indoor scene understanding with RGB-D images: bottom-up segmentation, object detection and semantic segmentation publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-014-0777-6 – start-page: 1 year: 2008 ident: 10.1016/j.cviu.2017.03.007_bib0063 article-title: Superpixel lattices – start-page: 2011 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0011 article-title: Superpixel meshes for fast edge-preserving surface reconstruction – start-page: 1625 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0089 article-title: SUN3D: a database of big spaces reconstructed using sfm and object labels – start-page: 5107 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0093 article-title: Object detection by labeling superpixels – year: 2000 ident: 10.1016/j.cviu.2017.03.007_sbref0012 article-title: The opencv library publication-title: Dr. Dobb’s Journal of Software Tools – volume: 26 start-page: 530 issue: 5 year: 2004 ident: 10.1016/j.cviu.2017.03.007_bib0058 article-title: Learning to detect natural image boundaries using local brightness, color, and texture cues publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2004.1273918 – start-page: 2042 year: 2009 ident: 10.1016/j.cviu.2017.03.007_bib0015 article-title: Minimizing energy functions on 4-connected lattices using elimination – start-page: 352 year: 2010 ident: 10.1016/j.cviu.2017.03.007_bib0084 article-title: SuperParsing: scalable nonparametric image parsing with superpixels – year: 2009 ident: 10.1016/j.cviu.2017.03.007_bib0019 article-title: ImageNet: a large-scale hierarchical image database – start-page: 26 year: 2011 ident: 10.1016/j.cviu.2017.03.007_bib0069 article-title: Homogeneous superpixels from random walks – start-page: 3721 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0079 article-title: Improving an object detector and extracting regions using superpixels – start-page: 328 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0005 article-title: Multiscale combinatorial grouping – volume: 6315 start-page: 211 year: 2010 ident: 10.1016/j.cviu.2017.03.007_bib0086 article-title: Superpixels and supervoxels in an energy optimization framework – start-page: 1 year: 2010 ident: 10.1016/j.cviu.2017.03.007_bib0024 article-title: Hypergraph coarsening for image superpixelization – start-page: 1 year: 2009 ident: 10.1016/j.cviu.2017.03.007_bib0031 article-title: Decomposing a scene into geometric and semantically consistent regions – year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0066 article-title: Evaluating superpixels in video: Metrics beyond figure-ground segmentation – volume: 24 start-page: 577 issue: 3 year: 2005 ident: 10.1016/j.cviu.2017.03.007_bib0037 article-title: Automatic photo pop-up publication-title: ACM Trans. Graph. doi: 10.1145/1073204.1073232 – start-page: 248 year: 2009 ident: 10.1016/j.cviu.2017.03.007_bib0025 article-title: Medial features for superpixel segmentation – start-page: 616 year: 1988 ident: 10.1016/j.cviu.2017.03.007_bib0061 article-title: Statistical model based image segmentation using region growing, contour relaxation and classification – start-page: 127 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0081 article-title: Grid seams: A fast superpixel algorithm for real-time applications – start-page: 1273 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0098 article-title: Estimating the 3d layout of indoor scenes and its clutter from depth sensors – volume: 23 start-page: 1639 issue: 4 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0094 article-title: Robust superpixel tracking publication-title: Trans. Image Process. doi: 10.1109/TIP.2014.2300823 – start-page: 2947 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0096 article-title: Real-time coarse-to-fine topologically preserving segmentation – start-page: 996 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0067 article-title: Compact watershed and preemptive SLIC: on improving trade-offs of superpixel segmentation algorithms – volume: 31 start-page: 2290 issue: 12 year: 2009 ident: 10.1016/j.cviu.2017.03.007_bib0044 article-title: TurboPixels: fast superpixels using geometric flows publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2009.96 – volume: abs/1411.6387 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0047 article-title: Deep convolutional neural fields for depth estimation from a single image publication-title: Comput. Res. Reposit. – volume: 16 start-page: 253 issue: 1 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0049 article-title: Fashion parsing with weak color-category labels publication-title: IEEE Trans. Multimedia doi: 10.1109/TMM.2013.2285526 – start-page: 2184 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0027 article-title: A fast method for inferring high-quality simply-connected superpixels – volume: abs/1405.0312 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0046 article-title: Microsoft COCO: common objects in context publication-title: Comput. Res. Reposit. – start-page: 1 year: 2007 ident: 10.1016/j.cviu.2017.03.007_bib0039 article-title: Recovering occlusion boundaries from a single image – year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0006 article-title: Fast superpixel segmentation using morphological processing – start-page: 183 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0029 article-title: Joint 3d object and layout inference from a single RGB-D image – start-page: 733 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0068 article-title: Saliency filters: contrast based filtering for salient region detection – volume: 23 start-page: 1451 issue: 4 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0077 article-title: Lazy random walks for superpixel segmentation publication-title: Trans. Image Process. doi: 10.1109/TIP.2014.2302892 – start-page: 746 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0080 article-title: Indoor segmentation and support inference from RGBD images – start-page: 35 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0095 article-title: 3-d geometry enhanced superpixels for RGB-D data – volume: abs/1309.3848 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0008 article-title: SEEDS: superpixels extracted via energy-driven sampling publication-title: Comput. Res. Reposit. – volume: 115 start-page: 330 issue: 3 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0036 article-title: Supercnn: a superpixelwise convolutional neural network for salient object detection publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-015-0822-0 – start-page: 3061 year: 2015 ident: 10.1016/j.cviu.2017.03.007_bib0059 article-title: Object scene flow for autonomous vehicles – start-page: 2639 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0043 article-title: Semantic segmentation with heterogeneous sensor coverages – volume: 34 start-page: 2274 issue: 11 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0002 article-title: SLIC superpixels compared to state-of-the-art superpixel methods publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2012.120 – start-page: 363 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0010 article-title: Depth SEEDS: recovering incomplete depth data using superpixels – start-page: 447 year: 2011 ident: 10.1016/j.cviu.2017.03.007_bib0097 article-title: Structure-sensitive superpixels via geodesic distance – start-page: 84 year: 2011 ident: 10.1016/j.cviu.2017.03.007_bib0099 article-title: Superpixels, occlusion and stereo – start-page: 280 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0016 article-title: Contour-relaxed superpixels – start-page: 145 year: 2014 ident: 10.1016/j.cviu.2017.03.007_bib0056 article-title: Superpixels using morphology for rock image segmentation – start-page: 3408 year: 2013 ident: 10.1016/j.cviu.2017.03.007_bib0022 article-title: A deformable mixture parsing model with parselets – volume: 80 start-page: 300 issue: 3 year: 2008 ident: 10.1016/j.cviu.2017.03.007_bib0032 article-title: Multi-class segmentation with relative location prior publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-008-0140-x – start-page: 930 year: 2012 ident: 10.1016/j.cviu.2017.03.007_bib0076 article-title: Measuring and evaluating the compactness of superpixels – start-page: 2141 year: 2010 ident: 10.1016/j.cviu.2017.03.007_bib0033 article-title: Efficient hierarchical graph-based video segmentation |
| SSID | ssj0011491 |
| Score | 2.660281 |
| Snippet | •An extensive evaluation of 28 superpixel algorithms on 5 datasets.•Explicit discussion of parameter optimization, including superpixel... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 1 |
| SubjectTerms | Benchmark Evaluation Image segmentation Perceptual grouping Superpixel segmentation Superpixels |
| Title | Superpixels: An evaluation of the state-of-the-art |
| URI | https://dx.doi.org/10.1016/j.cviu.2017.03.007 |
| Volume | 166 |
| WOSCitedRecordID | wos000419933000001&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: 1090-235X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0011491 issn: 1077-3142 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3da9swEBdZu4ftYeu6jXUfxQ99Kyr6iC1rb2F0bKOUQruSpxpLliCldUISh_z5O1nyR7JRtkFfjHNEiXx3Pt2d7n5C6Egww0hBFeYxyfGQ2iHOrZGY5cpqJhJFatyC6zNxfp6Ox_JiMLhpemFWd6Is0_Vazh5V1EADYbvW2X8Qd_ujQIB7EDpcQexw_SvBX1YzM59N1rDohaxfh-jdVATUbUR4ajF8wFswR805D8e-7dzvLty70p6q3wjTpmaWVX0kbL863qVWXTPCYqOFpqv9mSjj9zpq-9JPPNB0K_HQdsRsFGxCNOnynh4x68QEmiSY8Xi8YXWTvt2kvQXYYwX8Ztp9luH2RK8mlSvJEx6cVnQLWVteeOlm4SZBazT-VD5Bu0zEEqze7uj76fhHu88E8SH1Val-1qGtylcAbv_Tn12XnjtytYdehDgiGnn5v0IDU-6jlyGmiILFXgCpEWdD20fPexiUrxHr6cvnaFRGnbZEUxuBgkTb2vIG_fx6evXlGw4HaWANz7-EpZYSa21ii0LDIytagGfHE4cVV5gEPMhCJEJqeDc5kyRn3AjDY86UkYZalvO3aKecluYdirgsIOQ2hOg0GRrNlNYuhM0hUFCqIOYA0YZHmQ4o8-6wk7usKSe8zRxfM8fXjPAM-HqAjtsxM4-x8uC344b1WfASvfeXgaY8MO79f477gJ512v8R7SznlfmEnurVcrKYHwaF-gVjZop9 |
| 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=Superpixels%3A+An+evaluation+of+the+state-of-the-art&rft.jtitle=Computer+vision+and+image+understanding&rft.au=Stutz%2C+David&rft.au=Hermans%2C+Alexander&rft.au=Leibe%2C+Bastian&rft.date=2018-01-01&rft.pub=Elsevier+Inc&rft.issn=1077-3142&rft.eissn=1090-235X&rft.volume=166&rft.spage=1&rft.epage=27&rft_id=info:doi/10.1016%2Fj.cviu.2017.03.007&rft.externalDocID=S1077314217300589 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-3142&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-3142&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-3142&client=summon |