{"id":"https://openalex.org/W4386598266","doi":"https://doi.org/10.1109/icip49359.2023.10222927","title":"Zero-Shot Human-Object Interaction (HOI) Classification by Bridging Generative and Contrastive Image-Language Models","display_name":"Zero-Shot Human-Object Interaction (HOI) Classification by Bridging Generative and Contrastive Image-Language Models","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386598266","doi":"https://doi.org/10.1109/icip49359.2023.10222927"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222927","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5100776910","display_name":"Ying Jin","orcid":"https://orcid.org/0000-0003-0347-495X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Ying Jin","raw_affiliation_strings":["Microsoft","University of Washington"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007557621","display_name":"Yinpeng Chen","orcid":"https://orcid.org/0000-0003-1411-225X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yinpeng Chen","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358523","display_name":"Jianfeng Wang","orcid":"https://orcid.org/0000-0003-0932-3060"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianfeng Wang","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436501","display_name":"Lijuan Wang","orcid":"https://orcid.org/0000-0002-2517-2728"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lijuan Wang","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101702810","display_name":"Jenq\u2013Neng Hwang","orcid":"https://orcid.org/0000-0002-8877-2421"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jenq-Neng Hwang","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101728117","display_name":"Zicheng Liu","orcid":"https://orcid.org/0000-0001-5894-7828"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zicheng Liu","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100776910"],"corresponding_institution_ids":["https://openalex.org/I201448701","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10812136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1970","last_page":"1974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9972000122070312,"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":0.9846000075340271,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7801509499549866},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.7014966011047363},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6895947456359863},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6821727156639099},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6696135997772217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6053728461265564},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.532704770565033},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4860694706439972},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.47602537274360657},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4601481556892395},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4368404746055603},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4228416085243225},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41880160570144653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3686436414718628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7801509499549866},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7014966011047363},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6895947456359863},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6821727156639099},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6696135997772217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6053728461265564},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.532704770565033},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4860694706439972},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.47602537274360657},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4601481556892395},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4368404746055603},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4228416085243225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41880160570144653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3686436414718628},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222927","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10222927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W874179280","https://openalex.org/W2080873731","https://openalex.org/W2081580037","https://openalex.org/W2214124602","https://openalex.org/W2339712187","https://openalex.org/W2801004733","https://openalex.org/W2883697687","https://openalex.org/W2912083425","https://openalex.org/W2938667732","https://openalex.org/W2952122856","https://openalex.org/W3035047011","https://openalex.org/W3095753865","https://openalex.org/W3109754877","https://openalex.org/W3156636935","https://openalex.org/W3166396011","https://openalex.org/W3168279596","https://openalex.org/W3175466730","https://openalex.org/W4224947536","https://openalex.org/W4281633937","https://openalex.org/W4312261477","https://openalex.org/W4312343844","https://openalex.org/W4312574495","https://openalex.org/W4312960102","https://openalex.org/W4313169234","https://openalex.org/W4320458302","https://openalex.org/W4385445765","https://openalex.org/W6743837088","https://openalex.org/W6761634466","https://openalex.org/W6791353385","https://openalex.org/W6797371478","https://openalex.org/W6810367305","https://openalex.org/W6850204008"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4288282832","https://openalex.org/W2956331735","https://openalex.org/W4380551139","https://openalex.org/W2963244934","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531"],"abstract_inverted_index":{"Existing":[0],"studies":[1],"in":[2,79],"Human-Object":[3],"Interaction":[4],"(HOI)":[5],"classification":[6],"rely":[7],"on":[8,28,106,127],"costly":[9],"human-annotated":[10],"labels.":[11,30],"The":[12],"goal":[13],"of":[14,77,103],"this":[15,80],"paper":[16],"is":[17,145],"to":[18,24,94],"study":[19],"a":[20,33,40,46,55,116,136],"new":[21,41,137],"zero-shot":[22],"setup":[23],"remove":[25],"the":[26,52,60,64,96,100,104,122,128],"dependency":[27],"ground-truth":[29],"We":[31],"propose":[32],"novel":[34],"Heterogenous":[35],"Teacher-Student":[36],"(HTS)":[37],"framework":[38],"and":[39,54,69],"loss":[42,113],"function.":[43],"HTS":[44,62],"employs":[45],"generative":[47,67],"pretrained":[48],"image":[49],"captioner":[50],"as":[51,59],"teacher":[53],"contrastive":[56,72],"pre-trained":[57],"classifier":[58],"student.":[61,97],"combines":[63],"discriminability":[65],"from":[66,71,90],"pre-training":[68],"efficiency":[70],"pre-training.":[73],"To":[74,98],"facilitate":[75],"learning":[76,102],"HOI":[78,88],"setup,":[81],"we":[82,109],"introduce":[83],"pseudo-label":[84],"filtering":[85],"which":[86,114],"aggregates":[87],"probabilities":[89],"multiple":[91],"regional":[92],"captions":[93],"supervise":[95],"enhance":[99],"multi-label":[101],"student":[105,123],"few-shot":[107],"classes,":[108],"design":[110],"LogSumExp":[111],"(LSE)-Sign":[112],"features":[115],"dynamic":[117],"gradient":[118],"re-weighting":[119],"mechanism.":[120],"Eventually,":[121],"achieves":[124],"49.6":[125],"mAP":[126],"HICO":[129],"dataset":[130],"without":[131],"using":[132],"ground":[133],"truth,":[134],"becoming":[135],"state-of-the-art":[138],"method":[139],"that":[140],"outperforms":[141],"supervised":[142],"approaches.":[143],"Code":[144],"available.":[146]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}