{"id":"https://openalex.org/W4387968037","doi":"https://doi.org/10.1145/3581783.3612148","title":"QA-CLIMS: Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation","display_name":"QA-CLIMS: Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968037","doi":"https://doi.org/10.1145/3581783.3612148"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612148","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-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/A5076939216","display_name":"Songhe Deng","orcid":"https://orcid.org/0009-0005-9843-2083"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Songhe Deng","raw_affiliation_strings":["Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101504155","display_name":"Wei Zhuo","orcid":"https://orcid.org/0009-0004-5780-0364"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhuo","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044361651","display_name":"Jinheng Xie","orcid":"https://orcid.org/0000-0001-5678-4500"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinheng Xie","raw_affiliation_strings":["Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019313200","display_name":"Linlin Shen","orcid":"https://orcid.org/0000-0003-1420-0815"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linlin Shen","raw_affiliation_strings":["Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076939216"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":1.1919,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81515314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5572","last_page":"5583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"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":0.8264022469520569},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.7555785179138184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7174884080886841},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5597981810569763},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5374562740325928},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5090963244438171},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4901669919490814},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4875006377696991},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48407307267189026},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43916967511177063},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4295046329498291},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42838144302368164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8264022469520569},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.7555785179138184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7174884080886841},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5597981810569763},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5374562740325928},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5090963244438171},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4901669919490814},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4875006377696991},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48407307267189026},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43916967511177063},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4295046329498291},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42838144302368164},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612148","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1141204904","display_name":null,"funder_award_id":"2023A1515010688","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1477544716","display_name":null,"funder_award_id":"Guangdong","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2981938667","display_name":null,"funder_award_id":"Shenzhen","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3111586145","display_name":null,"funder_award_id":"31101412","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3398858419","display_name":null,"funder_award_id":"51501068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3472539505","display_name":null,"funder_award_id":"202205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3577061224","display_name":null,"funder_award_id":"JCYJ20220531101412030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3757194791","display_name":null,"funder_award_id":"JCYJ20","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7041006821","display_name":null,"funder_award_id":"82261138629","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8322697783","display_name":null,"funder_award_id":"82261138","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8442882701","display_name":null,"funder_award_id":"JCYJ20220531101412030","funder_id":"https://openalex.org/F4320329174","funder_display_name":"Shenzhen Municipal Science and Technology Innovation Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329174","display_name":"Shenzhen Municipal Science and Technology Innovation Council","ror":"https://ror.org/017n8df75"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2337429362","https://openalex.org/W2412782625","https://openalex.org/W2552414813","https://openalex.org/W2558580397","https://openalex.org/W2755136704","https://openalex.org/W2896435145","https://openalex.org/W2962758679","https://openalex.org/W2962867364","https://openalex.org/W3034373787","https://openalex.org/W3034930876","https://openalex.org/W3035524453","https://openalex.org/W3088940539","https://openalex.org/W3100040694","https://openalex.org/W3102714038","https://openalex.org/W3166286626","https://openalex.org/W3177958285","https://openalex.org/W3205377930","https://openalex.org/W3207676276","https://openalex.org/W4200634368","https://openalex.org/W4226158211","https://openalex.org/W4286904314","https://openalex.org/W4304014881","https://openalex.org/W4304091443","https://openalex.org/W4312509967","https://openalex.org/W4312566218","https://openalex.org/W4312680544","https://openalex.org/W4312709262","https://openalex.org/W4312954872","https://openalex.org/W4313052647","https://openalex.org/W4313139852","https://openalex.org/W4386065526","https://openalex.org/W4386113282","https://openalex.org/W6600018615"],"related_works":["https://openalex.org/W3177249605","https://openalex.org/W4376620596","https://openalex.org/W2534152068","https://openalex.org/W4299545679","https://openalex.org/W1972515067","https://openalex.org/W1689909837","https://openalex.org/W4293054914","https://openalex.org/W2549121492","https://openalex.org/W3138508047","https://openalex.org/W2953362004"],"abstract_inverted_index":{"Class":[0],"Activation":[1],"Map":[2],"(CAM)":[3],"has":[4],"emerged":[5],"as":[6,64,174],"a":[7,50,65,72,101,123,144,185],"popular":[8],"tool":[9],"for":[10,78],"weakly":[11],"supervised":[12],"semantic":[13],"segmentation":[14],"(WSSS),":[15],"allowing":[16],"the":[17,47,57,62,82,88,95,110,153,160,166,171,178,202],"localization":[18],"of":[19,36,42,52,91,97,103,125,193],"object":[20,38,188],"regions":[21,39,44,158],"in":[22,143],"an":[23],"image":[24,63],"using":[25],"only":[26],"image-level":[27],"labels.":[28],"However,":[29],"existing":[30],"CAM":[31],"methods":[32],"suffer":[33],"from":[34,170],"under-activation":[35],"target":[37,128],"and":[40,93,130,156,190,205,217],"false-activation":[41,192],"background":[43,157,194],"due":[45],"to":[46,60,86,109,121,135,151,180,200],"fact":[48],"that":[49,132,207],"lack":[51],"detailed":[53],"supervision":[54],"can":[55],"hinder":[56],"model's":[58],"ability":[59],"understand":[61],"whole.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"propose":[71],"novel":[73],"Question-Answer":[74,117],"Cross-Language-Image":[75],"Matching":[76],"framework":[77],"WSSS":[79],"(QA-CLIMS),":[80],"leveraging":[81],"vision-language":[83],"foundation":[84],"model":[85,115,179],"maximize":[87],"text-based":[89],"understanding":[90],"images":[92],"guide":[94],"generation":[96],"activation":[98],"maps.":[99],"First,":[100],"series":[102],"carefully":[104],"designed":[105],"questions":[106],"are":[107,133],"posed":[108],"VQA":[111],"(Visual":[112],"Question":[113],"Answering)":[114],"with":[116,159,184],"Prompt":[118],"Engineering":[119],"(QAPE)":[120],"generate":[122,181],"corpus":[124],"both":[126,213],"foreground":[127,155],"objects":[129],"backgrounds":[131],"adaptive":[134],"query":[136],"images.":[137],"We":[138,196],"then":[139],"employ":[140],"contrastive":[141],"learning":[142],"Region":[145],"Image":[146],"Text":[147],"Contrastive":[148],"(RITC)":[149],"network":[150],"compare":[152],"obtained":[154],"generated":[161],"corpus.":[162],"Our":[163],"approach":[164,209],"exploits":[165],"rich":[167],"textual":[168],"information":[169],"open":[172],"vocabulary":[173],"additional":[175],"supervision,":[176],"enabling":[177],"high-quality":[182],"CAMs":[183],"more":[186],"complete":[187],"region":[189],"reduce":[191],"regions.":[195],"conduct":[197],"extensive":[198],"analysis":[199],"validate":[201],"proposed":[203],"method":[204],"show":[206],"our":[208],"performs":[210],"state-of-the-art":[211],"on":[212],"PASCAL":[214],"VOC":[215],"2012":[216],"MS":[218],"COCO":[219],"datasets.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}