{"id":"https://openalex.org/W4323338514","doi":"https://doi.org/10.1109/tcsvt.2023.3252807","title":"StructToken: Rethinking Semantic Segmentation With Structural Prior","display_name":"StructToken: Rethinking Semantic Segmentation With Structural Prior","publication_year":2023,"publication_date":"2023-03-06","ids":{"openalex":"https://openalex.org/W4323338514","doi":"https://doi.org/10.1109/tcsvt.2023.3252807"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3252807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3252807","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088346438","display_name":"Fangjian Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fangjian Lin","raw_affiliation_strings":["School of Software, Xinjiang University, Urumqi, China","Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101560457","display_name":"Zhanhao Liang","orcid":"https://orcid.org/0009-0003-0087-5034"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanhao Liang","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China","School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064754605","display_name":"Sitong Wu","orcid":"https://orcid.org/0000-0002-2830-2831"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sitong Wu","raw_affiliation_strings":["Baidu Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Research, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056327997","display_name":"Junjun He","orcid":"https://orcid.org/0000-0002-1813-1784"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjun He","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038149192","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0003-4160-1024"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China","SenseTime Research, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"SenseTime Research, Shanghai, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075221279","display_name":"Shengwei Tian","orcid":"https://orcid.org/0000-0003-3525-5102"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwei Tian","raw_affiliation_strings":["School of Software, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5088346438"],"corresponding_institution_ids":["https://openalex.org/I4391012619","https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":5.8546,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.97310242,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"33","issue":"10","first_page":"5655","last_page":"5663"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7971541881561279},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.764296293258667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7509555220603943},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5606080889701843},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5353881120681763},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5352094769477844},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5342831611633301},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5309540629386902},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5217015147209167},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.51237952709198},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.46221867203712463},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4386936128139496},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4205547571182251},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3636016845703125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3369237780570984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971541881561279},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.764296293258667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7509555220603943},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5606080889701843},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5353881120681763},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5352094769477844},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5342831611633301},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5309540629386902},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5217015147209167},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.51237952709198},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.46221867203712463},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4386936128139496},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4205547571182251},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3636016845703125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3369237780570984},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3252807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3252807","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2594744562","display_name":null,"funder_award_id":"U2003208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7981239406","display_name":null,"funder_award_id":"2021B01002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2158967129","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2507296351","https://openalex.org/W2560023338","https://openalex.org/W2561196672","https://openalex.org/W2630837129","https://openalex.org/W2884822772","https://openalex.org/W2910628332","https://openalex.org/W2948080074","https://openalex.org/W2955058313","https://openalex.org/W2962919941","https://openalex.org/W2963136578","https://openalex.org/W2963727650","https://openalex.org/W2964309882","https://openalex.org/W2981609437","https://openalex.org/W2981689412","https://openalex.org/W2981899103","https://openalex.org/W2982220924","https://openalex.org/W2985459778","https://openalex.org/W2988226917","https://openalex.org/W2993235622","https://openalex.org/W2997563949","https://openalex.org/W3008115128","https://openalex.org/W3035071066","https://openalex.org/W3035526186","https://openalex.org/W3048402753","https://openalex.org/W3106728613","https://openalex.org/W3107634219","https://openalex.org/W3108139472","https://openalex.org/W3109301572","https://openalex.org/W3109772732","https://openalex.org/W3138516171","https://openalex.org/W3156772576","https://openalex.org/W3169770376","https://openalex.org/W3170841864","https://openalex.org/W3172661913","https://openalex.org/W3177248696","https://openalex.org/W3195135988","https://openalex.org/W3198020043","https://openalex.org/W3209412357","https://openalex.org/W3211490618","https://openalex.org/W3213165621","https://openalex.org/W4214520160","https://openalex.org/W4214893857","https://openalex.org/W4221148862","https://openalex.org/W4226442776","https://openalex.org/W4287116734","https://openalex.org/W4312815172","https://openalex.org/W4385245566","https://openalex.org/W6684191040","https://openalex.org/W6739696289","https://openalex.org/W6739901393","https://openalex.org/W6748481559","https://openalex.org/W6797175998","https://openalex.org/W6797399245","https://openalex.org/W6797784111","https://openalex.org/W6798160016","https://openalex.org/W6798837711","https://openalex.org/W6804552856","https://openalex.org/W6810214861","https://openalex.org/W7036195979"],"related_works":["https://openalex.org/W4285411112","https://openalex.org/W2085033728","https://openalex.org/W2171299904","https://openalex.org/W2922442631","https://openalex.org/W2053596378","https://openalex.org/W2168523118","https://openalex.org/W2106540031","https://openalex.org/W1982025852","https://openalex.org/W1522196789","https://openalex.org/W4309346246"],"abstract_inverted_index":{"In":[0,53],"previous":[1],"deep-learning-based":[2],"methods,":[3],"semantic":[4,62],"segmentation":[5,71],"has":[6],"been":[7],"regarded":[8],"as":[9],"a":[10,23,58,77],"static":[11],"or":[12,36],"dynamic":[13],"per-pixel":[14],"classification":[15,37],"task,":[16],"i.e.,":[17],"classify":[18],"each":[19,96],"pixel":[20,34],"representation":[21],"to":[22,49,89],"specific":[24],"category.":[25],"However,":[26],"these":[27],"methods":[28],"only":[29],"focus":[30],"on":[31,110],"learning":[32],"better":[33],"representations":[35],"kernels":[38],"while":[39],"ignoring":[40],"the":[41,70,74,84,92,99,108],"structural":[42,93],"information":[43,94],"of":[44,79,95],"objects,":[45],"which":[46,87],"is":[47],"critical":[48],"human":[50],"decision-making":[51],"mechanism.":[52],"this":[54],"paper,":[55],"we":[56],"present":[57],"new":[59],"paradigm":[60],"for":[61],"segmentation,":[63],"named":[64],"structure-aware":[65],"extraction.":[66],"Specifically,":[67],"it":[68],"generates":[69],"results":[72],"via":[73],"interactions":[75],"between":[76],"set":[78],"learned":[80],"structure":[81],"tokens":[82],"and":[83,117],"image":[85],"feature,":[86],"aims":[88],"progressively":[90],"extract":[91],"category":[97],"from":[98],"feature.":[100],"Extensive":[101],"experiments":[102],"show":[103],"that":[104],"our":[105],"StructToken":[106],"outperforms":[107],"state-of-the-art":[109],"three":[111],"widely-used":[112],"benchmarks,":[113],"including":[114],"ADE20K,":[115],"Cityscapes,":[116],"COCO-Stuff-10K.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":9}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}