{"id":"https://openalex.org/W4415708536","doi":"https://doi.org/10.1109/icme59968.2025.11208902","title":"Visual-Textual Feature Learning for Rare Human-Object Interactions Detection","display_name":"Visual-Textual Feature Learning for Rare Human-Object Interactions Detection","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708536","doi":"https://doi.org/10.1109/icme59968.2025.11208902"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5005856571","display_name":"Mingliang Xue","orcid":"https://orcid.org/0009-0006-2985-2786"},"institutions":[{"id":"https://openalex.org/I107982497","display_name":"Dalian Ocean University","ror":"https://ror.org/0523b6g79","country_code":"CN","type":"education","lineage":["https://openalex.org/I107982497"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Xue","raw_affiliation_strings":["Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600","institution_ids":["https://openalex.org/I4210092944","https://openalex.org/I27357992","https://openalex.org/I107982497"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101641562","display_name":"Chong Cao","orcid":"https://orcid.org/0000-0001-5990-8820"},"institutions":[{"id":"https://openalex.org/I107982497","display_name":"Dalian Ocean University","ror":"https://ror.org/0523b6g79","country_code":"CN","type":"education","lineage":["https://openalex.org/I107982497"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Cao","raw_affiliation_strings":["Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600","institution_ids":["https://openalex.org/I4210092944","https://openalex.org/I27357992","https://openalex.org/I107982497"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038246109","display_name":"Zhengyang Zhao","orcid":"https://orcid.org/0000-0003-2667-1358"},"institutions":[{"id":"https://openalex.org/I107982497","display_name":"Dalian Ocean University","ror":"https://ror.org/0523b6g79","country_code":"CN","type":"education","lineage":["https://openalex.org/I107982497"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyang Zhao","raw_affiliation_strings":["Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600","institution_ids":["https://openalex.org/I4210092944","https://openalex.org/I27357992","https://openalex.org/I107982497"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101944883","display_name":"Xiaodong Duan","orcid":"https://orcid.org/0009-0001-1775-6280"},"institutions":[{"id":"https://openalex.org/I107982497","display_name":"Dalian Ocean University","ror":"https://ror.org/0523b6g79","country_code":"CN","type":"education","lineage":["https://openalex.org/I107982497"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Duan","raw_affiliation_strings":["Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600","institution_ids":["https://openalex.org/I4210092944","https://openalex.org/I27357992","https://openalex.org/I107982497"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100684800","display_name":"Shu Cao","orcid":"https://orcid.org/0000-0003-2258-0221"},"institutions":[{"id":"https://openalex.org/I107982497","display_name":"Dalian Ocean University","ror":"https://ror.org/0523b6g79","country_code":"CN","type":"education","lineage":["https://openalex.org/I107982497"]},{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Cao","raw_affiliation_strings":["Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Minzu University,SEAC Key Laboratory of Big Data Applied Technology, College of Computer Science and Engineering,Dalian,China,116600","institution_ids":["https://openalex.org/I4210092944","https://openalex.org/I27357992","https://openalex.org/I107982497"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9728000164031982,"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":0.9728000164031982,"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":0.008700000122189522,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004399999976158142,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/task","display_name":"Task (project management)","score":0.5512999892234802},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5116000175476074},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.501800000667572},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4749000072479248},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4309999942779541},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42719998955726624},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.39820000529289246},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.39640000462532043},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.3939000070095062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6660000085830688},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4309999942779541},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.39820000529289246},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3659000098705292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31380000710487366},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C193581530","wikidata":"https://www.wikidata.org/wiki/Q683778","display_name":"Structured light","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":17,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2964225075","https://openalex.org/W3009811369","https://openalex.org/W3138516171","https://openalex.org/W3151099711","https://openalex.org/W4289752563","https://openalex.org/W4364323060","https://openalex.org/W4386065740","https://openalex.org/W4386071869","https://openalex.org/W4386076501","https://openalex.org/W4388579521","https://openalex.org/W4390874582","https://openalex.org/W4393149532","https://openalex.org/W4402387113","https://openalex.org/W4402968873","https://openalex.org/W4402981238","https://openalex.org/W4409263010"],"related_works":[],"abstract_inverted_index":{"Human-Object":[0],"Interaction":[1],"(HOI)":[2],"detection":[3],"is":[4,68,157],"a":[5,38],"fundamental":[6],"task":[7],"in":[8,28,151],"understanding":[9],"human-object":[10,74],"relationships.":[11],"However,":[12],"existing":[13],"methods":[14,140],"struggle":[15],"with":[16,72],"long-tail":[17],"data":[18],"distributions":[19],"and":[20,47,56,70,118,144],"capturing":[21],"global":[22,54,66,101],"context,":[23],"leading":[24],"to":[25,50,59,79,114,128],"poor":[26],"performance":[27],"detecting":[29],"rare":[30,61,134,152],"classes.":[31,62,135],"To":[32],"address":[33],"these":[34],"challenges,":[35],"we":[36],"propose":[37],"novel":[39],"HOI":[40],"detector":[41],"named":[42],"VTHOI,":[43],"which":[44],"integrates":[45,92],"visual":[46],"textual":[48,116],"embeddings":[49],"improve":[51],"the":[52,64,85,93,98,105,109,126,131,142],"model\u2019s":[53],"perception":[55],"its":[57],"ability":[58],"detect":[60],"First,":[63],"image\u2019s":[65],"context":[67],"extracted":[69],"fused":[71],"local":[73],"pair":[75],"features":[76,132],"during":[77],"decoding":[78],"generate":[80],"vision":[81,94],"logits":[82,95],"prompts.":[83],"Subsequently,":[84],"proposed":[86],"Adaptive":[87],"Logits":[88],"Fusion":[89],"Module":[90],"(ALFM)":[91],"prompts":[96],"into":[97],"backbone,":[99],"enhancing":[100],"contextual":[102],"understanding.":[103],"Additionally,":[104],"consistency":[106],"constraints":[107],"of":[108,121,133],"language":[110],"model":[111,127],"are":[112],"employed":[113],"learn":[115],"descriptions":[117],"semantic":[119],"relationships":[120],"non-rare":[122],"classes,":[123],"thereby":[124],"enabling":[125],"better":[129],"capture":[130],"Our":[136,155],"approach":[137],"outperforms":[138],"state-of-the-art":[139],"on":[141],"HICO-DET":[143],"V-COCO":[145],"datasets,":[146],"achieving":[147],"significant":[148],"improvements,":[149],"particularly":[150],"class":[153],"detection.":[154],"code":[156],"available":[158],"at:":[159],"https://github.com/CrystalCao9/VTHOI.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}