{"id":"https://openalex.org/W4408353195","doi":"https://doi.org/10.1109/icassp49660.2025.10890443","title":"Improving Open-vocabulary Video Visual Relation Detection with Decomposed Prompt Learning and Relation Adjustment","display_name":"Improving Open-vocabulary Video Visual Relation Detection with Decomposed Prompt Learning and Relation Adjustment","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353195","doi":"https://doi.org/10.1109/icassp49660.2025.10890443"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5062679781","display_name":"Ming Pei","orcid":"https://orcid.org/0000-0001-5710-3578"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Pei","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040998859","display_name":"Yi Tan","orcid":"https://orcid.org/0000-0002-8670-1312"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Tan","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043525989","display_name":"Yanbin Hao","orcid":"https://orcid.org/0000-0002-0695-1566"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbin Hao","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100746702","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-1664-8739"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Technology and Research(A*STAR),Centre for Frontier AI Research, Agency for Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology and Research(A*STAR),Centre for Frontier AI Research, Agency for Science,Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053355549","display_name":"Jinmeng Wu","orcid":"https://orcid.org/0000-0002-0264-8025"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinmeng Wu","raw_affiliation_strings":["Wuhan Institute of Technology,Hubei Key Laboratory of Intelligent Robot,Wuhan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan Institute of Technology,Hubei Key Laboratory of Intelligent Robot,Wuhan,China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090467618","display_name":"Basura Fernando","orcid":"https://orcid.org/0000-0002-6920-9916"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Basura Fernando","raw_affiliation_strings":["Technology and Research(A*STAR),Centre for Frontier AI Research, Agency for Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technology and Research(A*STAR),Centre for Frontier AI Research, Agency for Science,Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034737032","display_name":"Xun Yang","orcid":"https://orcid.org/0000-0003-0201-1638"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Yang","raw_affiliation_strings":["University of Science and Technology of China,School of Information Science and Technology,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,School of Information Science and Technology,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03822559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"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":0.9983999729156494,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9915000200271606,"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":0.9587000012397766,"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/relation","display_name":"Relation (database)","score":0.8772359490394592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7682032585144043},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5670483112335205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5021235942840576},{"id":"https://openalex.org/keywords/vocabulary-learning","display_name":"Vocabulary learning","score":0.42695847153663635},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.386574387550354},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.13199007511138916},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06298664212226868}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.8772359490394592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682032585144043},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5670483112335205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5021235942840576},{"id":"https://openalex.org/C2984601542","wikidata":"https://www.wikidata.org/wiki/Q48842322","display_name":"Vocabulary learning","level":3,"score":0.42695847153663635},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.386574387550354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13199007511138916},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06298664212226868},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2765137706","https://openalex.org/W2951323451","https://openalex.org/W2963890755","https://openalex.org/W2981385984","https://openalex.org/W3035309251","https://openalex.org/W3035503132","https://openalex.org/W3134134173","https://openalex.org/W3152619510","https://openalex.org/W3186621246","https://openalex.org/W3205497712","https://openalex.org/W3206633059","https://openalex.org/W4200630194","https://openalex.org/W4205817612","https://openalex.org/W4296262844","https://openalex.org/W4313118515","https://openalex.org/W4313186260","https://openalex.org/W4385681696","https://openalex.org/W4389888036","https://openalex.org/W4391216149","https://openalex.org/W4393159487","https://openalex.org/W4400096419","https://openalex.org/W4402874874","https://openalex.org/W4403791443","https://openalex.org/W6775993988","https://openalex.org/W6791353385","https://openalex.org/W6849600822","https://openalex.org/W6861153079"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","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":{"Open-vocabulary":[0],"video":[1,40],"visual":[2,83],"relation":[3,186,194],"detection":[4],"(VidVRD)":[5],"expands":[6],"the":[7,36,43,73,80,103,132,140,174,198,218],"scope":[8],"of":[9,38,45,114,200],"detecting":[10],"object":[11],"relations":[12,26,158,201],"in":[13,23,99,202,209],"videos":[14],"to":[15,54,63,102,136,139,196],"include":[16],"unseen":[17],"categories.":[18,58],"It":[19],"marks":[20],"considerable":[21],"advancement":[22],"recognizing":[24],"novel":[25,49,104,125,141,157,180,203],"solely":[27],"by":[28,205],"training":[29],"on":[30,48,56,131,217],"a":[31,119,185],"base":[32,57,123,133,155,178,193],"set,":[33],"thus":[34],"extending":[35],"frontiers":[37],"automated":[39],"understanding.":[41],"However,":[42],"performance":[44,223],"current":[46],"methods":[47],"predicates":[50],"remains":[51],"significantly":[52],"inferior":[53],"that":[55,172,190],"We":[59,153,183],"attribute":[60],"this":[61],"discrepancy":[62],"two":[64,149],"primary":[65],"factors:":[66],"(1)":[67,152],"A":[68],"significant":[69,222],"task":[70,78],"misalignment":[71],"between":[72,122,177],"Visual":[74],"Relation":[75],"Detection":[76],"(VRD)":[77],"and":[79,95,111,124,156,161,164,179],"pre-trained":[81],"models\u2019":[82],"feature":[84],"extractors,":[85],"which":[86,117],"are":[87],"often":[88],"designed":[89],"for":[90],"tasks":[91],"like":[92],"video-text":[93],"retrieval":[94],"image-text":[96],"retrieval,":[97],"resulting":[98],"poor":[100],"generalization":[101],"set.":[105,142],"(2)":[106,182],"The":[107],"relatively":[108],"small":[109],"size":[110],"limited":[112],"vocabulary":[113],"open-vocabulary":[115],"datasets,":[116],"create":[118],"substantial":[120],"gap":[121],"predicates.":[126],"Consequently,":[127],"text":[128,168],"prompts":[129],"trained":[130],"set":[134],"fail":[135],"generalize":[137],"effectively":[138],"To":[143],"address":[144],"these":[145],"issues,":[146],"we":[147],"propose":[148],"improvement":[150],"measures:":[151],"decompose":[154],"into":[159],"actional":[160,211],"spatial":[162,213],"patterns":[163,176],"introduce":[165],"an":[166],"innovative":[167],"prompt":[169],"learning":[170],"method":[171],"leverages":[173],"shared":[175],"relations.":[181],"develop":[184],"probability":[187],"adjustment":[188],"mechanism":[189],"utilizes":[191],"reliable":[192],"predictions":[195],"adjust":[197],"probabilities":[199],"classes":[204],"considering":[206],"their":[207],"overlaps":[208],"either":[210],"or":[212],"contents.":[214],"Experimental":[215],"results":[216],"benchmark":[219],"dataset":[220],"demonstrate":[221],"improvements.":[224]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}