{"id":"https://openalex.org/W4402981238","doi":"https://doi.org/10.1109/icme57554.2024.10688344","title":"Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model","display_name":"Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981238","doi":"https://doi.org/10.1109/icme57554.2024.10688344"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5102652601","display_name":"Jihao Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jihao Dong","raw_affiliation_strings":["Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Institute of Image Communication and Network Engineering,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850450","display_name":"Hua Yang","orcid":"https://orcid.org/0009-0000-1050-6177"},"institutions":[{"id":"https://openalex.org/I4210134018","display_name":"Western Digital (China)","ror":"https://ror.org/035vbre72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210121352","https://openalex.org/I4210134018"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Yang","raw_affiliation_strings":["Shanghai Key Lab of Digital Media Processing and Transmission,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Digital Media Processing and Transmission,China","institution_ids":["https://openalex.org/I4210134018"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038073714","display_name":"Renjie Pan","orcid":"https://orcid.org/0000-0001-6811-8572"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renjie Pan","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,China MoE Key Lab of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,China MoE Key Lab of Artificial Intelligence,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102652601"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.1458,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8772858,"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.707099974155426,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.707099974155426,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8184630870819092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5661611557006836},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5335223078727722},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.344421923160553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184630870819092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5661611557006836},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5335223078727722},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.344421923160553}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.44999998807907104}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2964225075","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3151099711","https://openalex.org/W3174164794","https://openalex.org/W3197395033","https://openalex.org/W4226451294","https://openalex.org/W4312241193","https://openalex.org/W4312446811","https://openalex.org/W4312770707","https://openalex.org/W4312960102","https://openalex.org/W4382240040","https://openalex.org/W4385245566","https://openalex.org/W4386065740","https://openalex.org/W4386071869","https://openalex.org/W4386075882","https://openalex.org/W4390872886","https://openalex.org/W4390874582","https://openalex.org/W6632922691","https://openalex.org/W6780226713","https://openalex.org/W6791353385","https://openalex.org/W6799822930","https://openalex.org/W6843484045"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Human-Object":[0],"Interaction":[1],"(HOI)":[2],"detection":[3],"aims":[4],"to":[5,93,112],"localize":[6],"human-object":[7],"pairs":[8],"and":[9,30,43,78,88,131,139],"comprehend":[10],"their":[11],"interactions.":[12],"Recently,":[13],"two-stage":[14],"transformer-based":[15],"methods":[16,23],"have":[17],"demonstrated":[18],"competitive":[19,126],"performance.":[20],"However,":[21],"these":[22],"frequently":[24],"focus":[25],"on":[26,55,128],"object":[27,92],"appearance":[28],"features":[29,90,115],"ignore":[31],"global":[32,84],"contextual":[33],"information.":[34],"Besides,":[35],"vision-language":[36],"model":[37],"CLIP":[38],"which":[39,67],"effectively":[40],"aligns":[41],"visual":[42,77],"text":[44],"embeddings":[45],"has":[46],"shown":[47],"great":[48],"potential":[49],"in":[50,97],"zero-shot":[51,144],"HOI":[52,63],"detection.":[53],"Based":[54],"the":[56,101,129,141],"former":[57],"facts,":[58],"We":[59,81],"introduce":[60],"a":[61,106],"novel":[62],"detector":[64],"named":[65],"ISA-HOI,":[66],"extensively":[68],"leverages":[69],"knowledge":[70],"from":[71],"CLIP,":[72],"aligning":[73],"interactive":[74],"semantics":[75],"between":[76],"textual":[79,114],"features.":[80],"first":[82],"extract":[83],"context":[85],"of":[86,91,116],"image":[87],"local":[89],"Improve":[94],"interaction":[95],"Features":[96],"images":[98],"(IF).":[99],"On":[100],"other":[102],"hand,":[103],"we":[104],"propose":[105],"Verb":[107],"Semantic":[108],"Improvement":[109],"(VSI)":[110],"module":[111],"enhance":[113],"verb":[117],"labels":[118],"via":[119],"cross-modal":[120],"fusion.":[121],"Ultimately,":[122],"our":[123],"method":[124],"achieves":[125],"results":[127],"HICO-DET":[130],"V-COCO":[132],"benchmarks":[133],"with":[134],"much":[135],"fewer":[136],"training":[137],"epochs,":[138],"outperforms":[140],"state-of-the-art":[142],"under":[143],"settings.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}