{"id":"https://openalex.org/W4387968023","doi":"https://doi.org/10.1145/3581783.3611735","title":"Improving Human-Object Interaction Detection via Virtual Image Learning","display_name":"Improving Human-Object Interaction Detection via Virtual Image Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968023","doi":"https://doi.org/10.1145/3581783.3611735"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611735","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5075034166","display_name":"Shuman Fang","orcid":"https://orcid.org/0000-0003-4414-7744"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuman Fang","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101847034","display_name":"Shuai Liu","orcid":"https://orcid.org/0009-0005-3998-7556"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Liu","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102011570","display_name":"Jie Li","orcid":"https://orcid.org/0000-0003-3102-6425"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020568230","display_name":"Guannan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guannan Jiang","raw_affiliation_strings":["Contemporary Amperex Technology Co. Limited (CATL), Ningde, China"],"affiliations":[{"raw_affiliation_string":"Contemporary Amperex Technology Co. Limited (CATL), Ningde, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101445574","display_name":"Xianming Lin","orcid":"https://orcid.org/0000-0003-4739-8936"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianming Lin","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075034166"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.7369,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.733389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5455","last_page":"5463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9990000128746033,"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":0.8484105467796326},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6379233598709106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5958887338638306},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5922597050666809},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5769614577293396},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5556685924530029},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5344139337539673},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.49727728962898254},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3127351701259613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8484105467796326},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6379233598709106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5958887338638306},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5922597050666809},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5769614577293396},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5556685924530029},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5344139337539673},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.49727728962898254},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3127351701259613},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611735","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1570557094","https://openalex.org/W1861492603","https://openalex.org/W2012210378","https://openalex.org/W2525770387","https://openalex.org/W2732026016","https://openalex.org/W2742737904","https://openalex.org/W2888814092","https://openalex.org/W2962766617","https://openalex.org/W2964225075","https://openalex.org/W2983943451","https://openalex.org/W2984933298","https://openalex.org/W2998124504","https://openalex.org/W3087975588","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3109754877","https://openalex.org/W3151099711","https://openalex.org/W3168279596","https://openalex.org/W3181762391","https://openalex.org/W3197395033","https://openalex.org/W4226451294","https://openalex.org/W4241307704","https://openalex.org/W4284681282","https://openalex.org/W4304092632","https://openalex.org/W4312241193","https://openalex.org/W4312343844","https://openalex.org/W4312446811","https://openalex.org/W4312538795","https://openalex.org/W4312933868","https://openalex.org/W4313057876","https://openalex.org/W4313141979","https://openalex.org/W4362641980","https://openalex.org/W4386075633"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Human-Object":[0],"Interaction":[1],"(HOI)":[2],"detection":[3],"aims":[4],"to":[5,30,50,76,115,142],"understand":[6],"the":[7,38,52,117,120,124,150,171],"interactions":[8],"between":[9],"humans":[10],"and":[11,102,112,133,181],"objects,":[12],"which":[13],"plays":[14],"a":[15,65,78,83],"curtail":[16],"role":[17],"in":[18],"high-level":[19],"semantic":[20],"understanding":[21],"tasks.":[22],"However,":[23],"most":[24],"works":[25],"pursue":[26],"designing":[27],"better":[28],"architectures":[29],"learn":[31],"overall":[32],"features":[33],"more":[34],"efficiently,":[35],"while":[36],"ignoring":[37],"long-tail":[39],"nature":[40],"of":[41,54,127,149,153,173],"interaction-object":[42],"pair":[43],"categories.":[44],"In":[45,89],"this":[46,90],"paper,":[47],"we":[48,108,135],"propose":[49],"alleviate":[51],"impact":[53],"such":[55],"an":[56,137],"unbalanced":[57],"distribution":[58,85],"via":[59],"Virtual":[60],"Image":[61,71],"Leaning":[62],"(VIL).":[63],"Firstly,":[64],"novel":[66],"label-to-image":[67],"approach,":[68],"Multiple":[69],"Steps":[70],"Creation":[72],"(MUSIC),":[73],"is":[74,147],"proposed":[75],"create":[77],"high-quality":[79],"dataset":[80],"that":[81],"has":[82],"consistent":[84],"with":[86,99,119,161],"real":[87,113],"images.":[88],"stage,":[91],"virtual":[92,111,129],"images":[93,114,130],"are":[94,131,185],"generated":[95],"based":[96],"on":[97,187],"prompts":[98],"specific":[100],"characterizations":[101],"selected":[103],"by":[104,164],"multi-filtering":[105],"processes.":[106],"Secondly,":[107],"use":[109],"both":[110],"train":[116],"model":[118],"teacher-student":[121],"framework.":[122],"Considering":[123],"initial":[125],"labels":[126],"some":[128],"inaccurate":[132],"inadequate,":[134],"devise":[136],"Adaptive":[138],"Matching-and-Filtering":[139],"(AMF)":[140],"module":[141],"construct":[143],"pseudo-labels.":[144],"Our":[145],"method":[146],"independent":[148],"internal":[151],"structure":[152],"HOI":[154],"detectors,":[155],"so":[156],"it":[157],"can":[158],"be":[159],"combined":[160],"off-the-shelf":[162],"methods":[163,177],"training":[165],"merely":[166],"10":[167],"additional":[168],"epochs.":[169],"With":[170],"assistance":[172],"our":[174],"method,":[175],"multiple":[176],"obtain":[178],"significant":[179],"improvements,":[180],"new":[182],"state-of-the-art":[183],"results":[184],"achieved":[186],"two":[188],"benchmarks.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}