{"id":"https://openalex.org/W4392781880","doi":"https://doi.org/10.48550/arxiv.2403.07246","title":"Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration","display_name":"Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration","publication_year":2024,"publication_date":"2024-03-12","ids":{"openalex":"https://openalex.org/W4392781880","doi":"https://doi.org/10.48550/arxiv.2403.07246"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.07246","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.07246","pdf_url":"https://arxiv.org/pdf/2403.07246","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.07246","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100312434","display_name":"Weiying Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xue, Weiying","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453144","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0001-5378-6404"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102629584","display_name":"Qiwei Xiong","orcid":"https://orcid.org/0009-0008-5569-3437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Qiwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104608196","display_name":"Yuxiao Wang","orcid":"https://orcid.org/0009-0006-5943-9757"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuxiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054252180","display_name":"Zhenao Wei","orcid":"https://orcid.org/0000-0002-6541-1287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Zhenao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036301580","display_name":"Xiaofen Xing","orcid":"https://orcid.org/0000-0002-0016-9055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing, Xiaofen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033271721","display_name":"Xiangmin Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Xiangmin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100312434"],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9921000003814697,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9842000007629395,"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/zero","display_name":"Zero (linguistics)","score":0.7226250767707825},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6232971549034119},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5802240371704102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5240744948387146},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4958816468715668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4820424020290375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32749858498573303},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2652907967567444},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.10558369755744934}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7226250767707825},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6232971549034119},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5802240371704102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5240744948387146},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4958816468715668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4820424020290375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32749858498573303},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2652907967567444},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.10558369755744934},{"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":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.07246","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.07246","pdf_url":"https://arxiv.org/pdf/2403.07246","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.07246","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.07246","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.07246","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.07246","pdf_url":"https://arxiv.org/pdf/2403.07246","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392781880.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Human-object":[0],"interaction":[1,12,101,143],"(HOI)":[2],"detection":[3],"aims":[4],"to":[5,42,53,76,92,136],"locate":[6],"human-object":[7],"pairs":[8],"and":[9,111,152,166],"identify":[10],"their":[11],"categories":[13],"in":[14,124,163],"images.":[15],"Most":[16],"existing":[17],"methods":[18,162],"primarily":[19],"focus":[20],"on":[21,26,67,148],"supervised":[22],"learning,":[23],"which":[24],"relies":[25],"extensive":[27],"manual":[28],"HOI":[29,43,56],"annotations.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,126],"propose":[35],"a":[36,116,128],"novel":[37],"framework,":[38],"termed":[39],"Knowledge":[40],"Integration":[41],"(KI2HOI),":[44],"that":[45,156],"effectively":[46,104],"integrates":[47],"the":[48,59,72,99,132,138,149,160],"knowledge":[49,130],"of":[50],"visual-language":[51],"model":[52,158],"improve":[54],"zero-shot":[55,122,165],"detection.":[57],"Specifically,":[58],"verb":[60,73,79],"feature":[61,113],"learning":[62,123],"module":[63],"is":[64],"designed":[65],"based":[66],"visual":[68,96,112],"semantics,":[69],"by":[70,108],"employing":[71],"extraction":[74],"decoder":[75,103],"convert":[77],"corresponding":[78],"queries":[80],"into":[81],"interaction-specific":[82],"category":[83],"representations.":[84,97],"We":[85],"develop":[86],"an":[87],"effective":[88],"additive":[89],"self-attention":[90],"mechanism":[91],"generate":[93],"more":[94],"comprehensive":[95],"Moreover,":[98],"innovative":[100],"representation":[102],"extracts":[105],"informative":[106],"regions":[107],"integrating":[109],"spatial":[110],"information":[114],"through":[115],"cross-attention":[117],"mechanism.":[118],"To":[119],"deal":[120],"with":[121],"low-data,":[125],"leverage":[127],"priori":[129],"from":[131],"CLIP":[133],"text":[134],"encoder":[135],"initialize":[137],"linear":[139],"classifier":[140],"for":[141],"enhanced":[142],"understanding.":[144],"Extensive":[145],"experiments":[146],"conducted":[147],"mainstream":[150],"HICO-DET":[151],"V-COCO":[153],"datasets":[154],"demonstrate":[155],"our":[157],"outperforms":[159],"previous":[161],"various":[164],"full-supervised":[167],"settings.":[168]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2024-03-14T00:00:00"}