{"id":"https://openalex.org/W4385681038","doi":"https://doi.org/10.48550/arxiv.2308.02606","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":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385681038","doi":"https://doi.org/10.48550/arxiv.2308.02606"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2308.02606","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.02606","pdf_url":"https://arxiv.org/pdf/2308.02606","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":null,"license_id":null,"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/2308.02606","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075034166","display_name":"Shuman Fang","orcid":"https://orcid.org/0000-0003-4414-7744"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fang, Shuman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103034233","display_name":"Shuai Liu","orcid":"https://orcid.org/0009-0001-9733-1441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shuai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428256","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-5311-3012"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020568230","display_name":"Guannan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Guannan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101445574","display_name":"Xianming Lin","orcid":"https://orcid.org/0000-0003-4739-8936"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xianming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Rongrong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075034166"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9962999820709229,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9860000014305115,"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":0.8251238465309143},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6552494168281555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5979504585266113},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5968317985534668},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5949684381484985},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5248798727989197},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5016915798187256},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4818509817123413},{"id":"https://openalex.org/keywords/virtual-image","display_name":"Virtual image","score":0.41161566972732544},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.320284366607666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06681749224662781}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251238465309143},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6552494168281555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5979504585266113},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5968317985534668},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5949684381484985},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5248798727989197},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5016915798187256},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4818509817123413},{"id":"https://openalex.org/C51970089","wikidata":"https://www.wikidata.org/wiki/Q44415","display_name":"Virtual image","level":2,"score":0.41161566972732544},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.320284366607666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06681749224662781},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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":2,"locations":[{"id":"pmh:oai:arXiv.org:2308.02606","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.02606","pdf_url":"https://arxiv.org/pdf/2308.02606","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2308.02606","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2308.02606","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.02606","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.02606","pdf_url":"https://arxiv.org/pdf/2308.02606","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G1271955826","display_name":null,"funder_award_id":"62072387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1300220747","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1627692989","display_name":null,"funder_award_id":"2021J01002","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G1787173488","display_name":null,"funder_award_id":"62072389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G187639494","display_name":null,"funder_award_id":"No. 62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G2564228358","display_name":null,"funder_award_id":"No. 62025603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2785666877","display_name":null,"funder_award_id":"62002305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3181244293","display_name":null,"funder_award_id":"2022J06001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3568142893","display_name":null,"funder_award_id":"62272401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G390962370","display_name":null,"funder_award_id":"2021J01002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5284885812","display_name":null,"funder_award_id":"62176222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6058138561","display_name":null,"funder_award_id":", No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G6688104968","display_name":null,"funder_award_id":"620023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6727647225","display_name":null,"funder_award_id":"62176226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G717600273","display_name":null,"funder_award_id":"U22B2051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7220565969","display_name":null,"funder_award_id":"2022J06001","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G7272499820","display_name":null,"funder_award_id":"U21B2037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7779606772","display_name":null,"funder_award_id":"62176223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8406165135","display_name":null,"funder_award_id":"62072386","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8863666567","display_name":null,"funder_award_id":"and No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385681038.pdf","grobid_xml":"https://content.openalex.org/works/W4385681038.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4309505463","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W2465398362","https://openalex.org/W2296174333","https://openalex.org/W2558391692","https://openalex.org/W2253875927","https://openalex.org/W2009559671","https://openalex.org/W2294448994","https://openalex.org/W2012474401"],"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":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}