{"id":"https://openalex.org/W4414360026","doi":"https://doi.org/10.24963/ijcai.2025/223","title":"METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection","display_name":"METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360026","doi":"https://doi.org/10.24963/ijcai.2025/223"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/223","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5101867694","display_name":"Yongqi Wang","orcid":"https://orcid.org/0000-0001-7889-2262"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqi Wang","raw_affiliation_strings":["Beijing Institute of Technology","Shenzhen MSU-BIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Shenzhen MSU-BIT University","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011070646","display_name":"Xinxiao Wu","orcid":"https://orcid.org/0000-0002-2056-6947"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxiao Wu","raw_affiliation_strings":["Beijing Institute of Technology","Shenzhen MSU-BIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Shenzhen MSU-BIT University","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4388482657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008524479","display_name":"Shuo Yang","orcid":"https://orcid.org/0000-0003-2868-7070"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Yang","raw_affiliation_strings":["Shenzhen MSU-BIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen MSU-BIT University","institution_ids":["https://openalex.org/I4210152380","https://openalex.org/I4388482657"]}]}],"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":"2000","last_page":"2008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9934999942779541,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9811999797821045,"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/leverage","display_name":"Leverage (statistics)","score":0.5953999757766724},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5443000197410583},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5127999782562256},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.491100013256073},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4799000024795532},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.44830000400543213},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.428600013256073},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4147000014781952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490000128746033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.63919997215271},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5953999757766724},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5443000197410583},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4799000024795532},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.32440000772476196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C2986522900","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relationship","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26350000500679016}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/223","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"video":[1],"visual":[2,114],"relationship":[3,21,95],"detection":[4,93],"aims":[5],"to":[6,37,47,63,86,120,136,146,160],"detect":[7,49],"objects":[8,50,117,152],"and":[9,51,66,79,89,94,118,127,153,171],"their":[10,158],"relationships":[11,54,119,154],"in":[12,97],"videos":[13],"without":[14],"being":[15],"restricted":[16],"by":[17,155],"predefined":[18],"object":[19,92,128],"or":[20],"categories.":[22,40,138],"Existing":[23],"methods":[24],"leverage":[25],"the":[26,57,122,132,149],"rich":[27],"semantic":[28],"knowledge":[29],"of":[30,77,116,124,134,151],"pre-trained":[31],"vision-language":[32],"models":[33],"such":[34],"as":[35],"CLIP":[36],"identify":[38],"novel":[39,137],"They":[41],"typically":[42],"adopt":[43],"a":[44,82,106],"cascaded":[45],"pipeline":[46],"first":[48,104],"then":[52],"classify":[53],"based":[55],"on":[56,166],"detected":[58],"objects,":[59],"which":[60],"may":[61],"lead":[62],"error":[64],"propagation":[65],"thus":[67,130],"suboptimal":[68],"performance.":[69,163,179],"In":[70],"this":[71,101],"paper,":[72],"we":[73,103,140],"propose":[74,141],"Mutual":[75],"EnhancemenT":[76],"Objects":[78],"Relationships":[80],"(METOR),":[81],"query-based":[83],"unified":[84],"framework":[85,176],"jointly":[87],"model":[88],"mutually":[90],"enhance":[91,148],"classification":[96],"open-vocabulary":[98],"scenarios.":[99],"Under":[100],"framework,":[102],"design":[105],"CLIP-based":[107],"contextual":[108],"refinement":[109],"encoding":[110,123,135],"module":[111,145],"that":[112,174],"extracts":[113],"contexts":[115],"refine":[121],"text":[125],"features":[126],"queries,":[129],"improving":[131],"generalization":[133],"Then":[139],"an":[142],"iterative":[143],"enhancement":[144],"alternatively":[147],"representations":[150],"fully":[156],"exploiting":[157],"interdependence":[159],"improve":[161],"recognition":[162],"Extensive":[164],"experiments":[165],"two":[167],"public":[168],"datasets,":[169],"VidVRD":[170],"VidOR,":[172],"demonstrate":[173],"our":[175],"achieves":[177],"state-of-the-art":[178],"Codes":[180],"are":[181],"at":[182],"https://github.com/wangyongqi558/METOR.":[183]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}