{"id":"https://openalex.org/W4415709466","doi":"https://doi.org/10.1109/icme59968.2025.11209176","title":"An End-To-End Class-Aware Transformer Framework For Weakly-Supervised Semantic Segmentation","display_name":"An End-To-End Class-Aware Transformer Framework For Weakly-Supervised Semantic Segmentation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709466","doi":"https://doi.org/10.1109/icme59968.2025.11209176"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5038012360","display_name":"Wenzhe Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhe Gu","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100711421","display_name":"Kaiwen Li","orcid":"https://orcid.org/0000-0003-1550-5987"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiwen Li","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392796","display_name":"Bin Zhang","orcid":"https://orcid.org/0000-0001-9545-2760"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhang","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038749014","display_name":"Baosheng Liu","orcid":"https://orcid.org/0000-0002-3670-3467"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baosheng Liu","raw_affiliation_strings":["Xi’an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8866000175476074,"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":0.8866000175476074,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.019200000911951065,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.015699999406933784,"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/segmentation","display_name":"Segmentation","score":0.7257000207901001},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6780999898910522},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6280999779701233},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.5024999976158142},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4032000005245209},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3702999949455261}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7257000207901001},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6780999898910522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6416000127792358},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6280999779701233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5817999839782715},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4032000005245209},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3361000120639801},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.3043999969959259},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2768000066280365}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2144794286","https://openalex.org/W2306289963","https://openalex.org/W2996952120","https://openalex.org/W3035703639","https://openalex.org/W3142837074","https://openalex.org/W3166286626","https://openalex.org/W3175456851","https://openalex.org/W3207676276","https://openalex.org/W4221115899","https://openalex.org/W4312509967","https://openalex.org/W4312566218","https://openalex.org/W4312836939","https://openalex.org/W4313153210","https://openalex.org/W4386066092","https://openalex.org/W4386071966","https://openalex.org/W4386598348","https://openalex.org/W4408352348"],"related_works":[],"abstract_inverted_index":{"Weakly-Supervised":[0],"Semantic":[1],"Segmentation":[2],"(WSSS)":[3],"is":[4],"a":[5],"challenging":[6],"task":[7],"that":[8,45,120],"utilizes":[9],"image-level":[10],"labels":[11],"to":[12,26,49,75,85,102],"generate":[13],"pixel-level":[14],"pseudo":[15],"labels.":[16],"Current":[17],"approaches":[18],"predominantly":[19],"rely":[20],"on":[21,109],"CNNs,":[22],"which":[23],"often":[24],"fail":[25],"extract":[27],"integral":[28],"object":[29],"regions.":[30],"To":[31],"remedy":[32],"this":[33,90],"limitation,":[34],"several":[35],"recent":[36],"methods":[37,47],"have":[38],"adopted":[39],"transformer":[40,97],"architectures.":[41],"However,":[42],"we":[43,92],"note":[44],"transformer-based":[46],"continue":[48],"grapple":[50],"with":[51],"two":[52,105],"critical":[53],"issues:":[54],"over-activation,":[55],"where":[56,66],"background":[57],"pixels":[58,67],"are":[59,72],"erroneously":[60],"classified":[61],"as":[62,100],"foreground,":[63],"and":[64,114,131],"mistake-activation,":[65],"from":[68,80],"one":[69],"foreground":[70],"class":[71],"incorrectly":[73],"attributed":[74],"another.":[76],"Both":[77],"problems":[78],"stem":[79],"the":[81,86,104,110,121,127],"long-range":[82],"dependencies":[83],"intrinsic":[84],"attention":[87],"mechanism.":[88],"In":[89],"paper,":[91],"propose":[93],"an":[94],"end-to-end":[95],"class-aware":[96],"framework,":[98],"denoted":[99],"CAT,":[101],"address":[103,126],"issues":[106,130],"above.":[107],"Experiments":[108],"PASCAL":[111],"VOC":[112],"2012":[113],"MS":[115],"COCO":[116],"2014":[117],"datasets":[118],"show":[119],"proposed":[122],"CAT":[123],"can":[124],"significantly":[125],"above":[128],"mentioned":[129],"achieve":[132],"impressive":[133],"results.":[134]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}