{"id":"https://openalex.org/W4392902868","doi":"https://doi.org/10.1109/icassp48485.2024.10445910","title":"Boosting Zero-Shot Human-Object Interaction Detection with Vision-Language Transfer","display_name":"Boosting Zero-Shot Human-Object Interaction Detection with Vision-Language Transfer","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902868","doi":"https://doi.org/10.1109/icassp48485.2024.10445910"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445910","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5017150634","display_name":"Sandipan Sarma","orcid":"https://orcid.org/0000-0003-4619-3058"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandipan Sarma","raw_affiliation_strings":["Indian Institute of Technology,Department of Computer Science and Engineering,Guwahati,India","Department of Computer Science and Engineering, Indian Institute of Technology, Guwahati, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Department of Computer Science and Engineering,Guwahati,India","institution_ids":["https://openalex.org/I1317621060"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094178894","display_name":"Pradnesh Kalkar","orcid":null},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pradnesh Kalkar","raw_affiliation_strings":["Indian Institute of Technology,Department of Computer Science and Engineering,Guwahati,India","Department of Computer Science and Engineering, Indian Institute of Technology, Guwahati, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Department of Computer Science and Engineering,Guwahati,India","institution_ids":["https://openalex.org/I1317621060"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090992514","display_name":"Arijit Sur","orcid":"https://orcid.org/0000-0002-9038-8138"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arijit Sur","raw_affiliation_strings":["Indian Institute of Technology,Department of Computer Science and Engineering,Guwahati,India","Department of Computer Science and Engineering, Indian Institute of Technology, Guwahati, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Department of Computer Science and Engineering,Guwahati,India","institution_ids":["https://openalex.org/I1317621060"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46261172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"34","issue":null,"first_page":"6355","last_page":"6359"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9984999895095825,"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":0.7848016619682312},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7518925070762634},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7499254941940308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7003052830696106},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6739247441291809},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6094365119934082},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5248344540596008},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5196458101272583},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4392321705818176},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35112613439559937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7848016619682312},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7518925070762634},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7499254941940308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7003052830696106},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6739247441291809},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6094365119934082},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5248344540596008},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5196458101272583},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4392321705818176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35112613439559937},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445910","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10445910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2801004733","https://openalex.org/W2964225075","https://openalex.org/W2997150218","https://openalex.org/W3034934229","https://openalex.org/W3035598501","https://openalex.org/W3049440217","https://openalex.org/W3096609285","https://openalex.org/W3101631402","https://openalex.org/W3106121867","https://openalex.org/W3109754877","https://openalex.org/W3168279596","https://openalex.org/W3197395033","https://openalex.org/W4212774754","https://openalex.org/W4231449374","https://openalex.org/W4312574495","https://openalex.org/W6757817989","https://openalex.org/W6791353385","https://openalex.org/W6799822930"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2571255492","https://openalex.org/W2963610131"],"abstract_inverted_index":{"Human-Object":[0],"Interaction":[1],"(HOI)":[2],"detection":[3,70],"is":[4,67,150],"a":[5,103,110,126],"crucial":[6],"task":[7],"that":[8],"involves":[9],"localizing":[10],"interactive":[11],"human-object":[12,86],"pairs":[13,87],"and":[14,28,88,94,121,130],"identifying":[15],"the":[16,30,43,55,99,135],"actions":[17,93,120],"being":[18],"performed.":[19],"Most":[20],"existing":[21],"HOI":[22,69],"detectors":[23,46],"are":[24],"supervised":[25],"in":[26,59,71,74],"nature":[27],"lack":[29],"ability":[31],"of":[32,35,92],"zero-shot":[33,75,141],"discovery":[34],"unseen":[36,119],"interactions.":[37],"Recently,":[38],"transformer-based":[39,81],"methods":[40],"have":[41],"superseded":[42],"traditional":[44],"CNN":[45],"by":[47],"aggregating":[48],"image-wide":[49],"context":[50],"but":[51],"still":[52],"suffer":[53],"from":[54,102],"long-tail":[56],"distribution":[57],"problem":[58],"HOI.":[60],"In":[61],"this":[62],"work,":[63],"our":[64],"primary":[65],"focus":[66],"improving":[68],"images,":[72],"particularly":[73],"scenarios.":[76],"We":[77],"use":[78],"an":[79],"end-to-end":[80],"object":[82],"detector":[83],"to":[84,114,145],"localize":[85],"yield":[89],"visual":[90],"features":[91],"objects.":[95,122],"Moreover,":[96],"we":[97,124],"adopt":[98],"text":[100],"encoder":[101],"popular":[104],"visual-language":[105],"model":[106],"called":[107],"CLIP":[108],"with":[109,143],"novel":[111],"prompting":[112],"mechanism":[113],"extract":[115],"semantic":[116],"information":[117],"for":[118],"Finally,":[123],"learn":[125],"strong":[127],"visual-semantic":[128],"alignment":[129],"achieve":[131],"state-of-the-art":[132],"performance":[133],"on":[134],"challenging":[136],"HICO-DET":[137],"dataset":[138],"across":[139],"five":[140],"settings,":[142],"up":[144],"70.88%":[146],"relative":[147],"gains.":[148],"Code":[149],"available":[151],"at":[152],"https://github.com/sandipan211/ZSHOI-VLT.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
