{"id":"https://openalex.org/W4413155536","doi":"https://doi.org/10.1109/cvpr52734.2025.00921","title":"Beyond Image Classification: A Video Benchmark and Dual-Branch Hybrid Discrimination Framework for Compositional Zero-Shot Learning","display_name":"Beyond Image Classification: A Video Benchmark and Dual-Branch Hybrid Discrimination Framework for Compositional Zero-Shot Learning","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413155536","doi":"https://doi.org/10.1109/cvpr52734.2025.00921"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5101319756","display_name":"Dongyao Jiang","orcid":"https://orcid.org/0009-0009-7035-9266"},"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":"Dongyao Jiang","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Shanxi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Shanxi,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058752981","display_name":"Haodong Jing","orcid":"https://orcid.org/0000-0001-6643-7588"},"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":"Haodong Jing","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Shanxi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Shanxi,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101200166","display_name":"Yongqiang Ma","orcid":"https://orcid.org/0000-0002-6063-5601"},"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":"Yongqiang Ma","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Shanxi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Shanxi,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047405956","display_name":"Nanning Zheng","orcid":"https://orcid.org/0000-0003-1608-8257"},"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":"Nanning Zheng","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Shanxi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Shanxi,China","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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9860","last_page":"9869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9703999757766724,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9703999757766724,"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/T11293","display_name":"Orthopedic Infections and Treatments","score":0.9266999959945679,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11381","display_name":"Infectious Diseases and Tuberculosis","score":0.9106000065803528,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.791361927986145},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7186599373817444},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7121244668960571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.684229850769043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6116927862167358},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6049066185951233},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5117638111114502},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4983682632446289},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43993860483169556},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4146595001220703}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.791361927986145},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7186599373817444},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7121244668960571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.684229850769043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116927862167358},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6049066185951233},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5117638111114502},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4983682632446289},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43993860483169556},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4146595001220703},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1948251820","https://openalex.org/W1969946615","https://openalex.org/W1983439863","https://openalex.org/W2093848332","https://openalex.org/W2156406284","https://openalex.org/W2400717490","https://openalex.org/W2736809457","https://openalex.org/W2889167066","https://openalex.org/W2986385672","https://openalex.org/W2990152177","https://openalex.org/W2990650678","https://openalex.org/W3035084814","https://openalex.org/W3158711590","https://openalex.org/W3162332195","https://openalex.org/W3164354101","https://openalex.org/W3198377975","https://openalex.org/W4229453513","https://openalex.org/W4312400874","https://openalex.org/W4312539810","https://openalex.org/W4312578829","https://openalex.org/W4375929081","https://openalex.org/W4386065859","https://openalex.org/W4386075982","https://openalex.org/W4386076688","https://openalex.org/W4394597571","https://openalex.org/W4402716195","https://openalex.org/W4402727748","https://openalex.org/W4402997051","https://openalex.org/W4404563275"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2378211422","https://openalex.org/W4411535265","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W4321353415","https://openalex.org/W2958550830"],"abstract_inverted_index":{"Human":[0],"reasoning":[1,66],"naturally":[2],"combines":[3],"concepts":[4],"to":[5,17,58,112],"identify":[6],"unseen":[7],"compositions,":[8,140],"a":[9,48,53,70,88,92,107,142],"capability":[10],"that":[11,26,79],"Compositional":[12],"Zero-Shot":[13],"Learning":[14],"(CZSL)":[15],"aims":[16],"replicate":[18],"in":[19,34,83,116,129,136],"machine":[20],"learning":[21],"models.":[22],"However,":[23],"we":[24,45,68],"observe":[25],"focusing":[27],"solely":[28],"on":[29],"typical":[30],"image":[31],"classification":[32],"tasks":[33],"CZSL":[35,126,146],"may":[36],"limit":[37],"models\u2019":[38],"compositional":[39,54],"generalization":[40],"potential.":[41],"To":[42],"address":[43],"this,":[44],"introduce":[46],"C-EgoExo,":[47],"video-based":[49,133],"benchmark,":[50],"along":[51],"with":[52],"action":[55],"recognition":[56],"task":[57],"enable":[59],"more":[60],"comprehensive":[61],"evaluations.":[62],"Inspired":[63],"by":[64,101],"human":[65],"processes,":[67],"propose":[69],"Dual-branch":[71],"Hybrid":[72],"Discrimination":[73],"(DHD)":[74],"framework,":[75],"featuring":[76],"two":[77],"branches":[78],"decode":[80],"visual":[81],"inputs":[82],"distinct":[84],"observation":[85],"sequences.":[86],"Through":[87],"cross-attention":[89],"mechanism":[90],"and":[91,132,135,138],"contextual":[93,114],"dependency":[94],"encoder,":[95],"DHD":[96],"effectively":[97],"mitigates":[98],"challenges":[99],"posed":[100],"conditional":[102],"variance.":[103],"We":[104],"further":[105],"design":[106],"Copula-based":[108],"orthogonal":[109],"decoding":[110],"loss":[111],"counteract":[113],"interference":[115],"primitive":[117],"decoding.":[118],"Our":[119],"approach":[120],"demonstrates":[121],"outstanding":[122],"performance":[123],"across":[124],"diverse":[125],"tasks,":[127],"excelling":[128],"both":[130],"image-based":[131],"modalities":[134],"attribute-object":[137],"action-object":[139],"setting":[141],"new":[143],"benchmark":[144],"for":[145],"evaluation.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}