{"id":"https://openalex.org/W3206633059","doi":"https://doi.org/10.1145/3474085.3475263","title":"Video Visual Relation Detection via Iterative Inference","display_name":"Video Visual Relation Detection via Iterative Inference","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206633059","doi":"https://doi.org/10.1145/3474085.3475263","mag":"3206633059"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475263","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475263","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475263","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017342089","display_name":"Xindi Shang","orcid":"https://orcid.org/0000-0002-9308-2927"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Xindi Shang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101762861","display_name":"Yicong Li","orcid":"https://orcid.org/0000-0002-5659-793X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yicong Li","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024669782","display_name":"Junbin Xiao","orcid":"https://orcid.org/0000-0001-5573-6195"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junbin Xiao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101397422","display_name":"Wei Ji","orcid":"https://orcid.org/0000-0002-8106-9768"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Ji","raw_affiliation_strings":["National University of Singapore & Sea-NExT Joint Lab, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore & Sea-NExT Joint Lab, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore & Sea-NExT Joint Lab, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore & Sea-NExT Joint Lab, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017342089"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":2.7196,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.91992304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3654","last_page":"3663"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9983000159263611,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980999827384949,"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/inference","display_name":"Inference","score":0.8051806688308716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.770328164100647},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.659760594367981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6425792574882507},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5834149718284607},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5212079286575317},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4540404677391052},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4535773694515228},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33462148904800415}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8051806688308716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770328164100647},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.659760594367981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6425792574882507},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5834149718284607},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5212079286575317},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4540404677391052},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4535773694515228},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33462148904800415},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475263","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475263","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3474085.3475263","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475263","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475263","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3206633059.pdf","grobid_xml":"https://content.openalex.org/works/W3206633059.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2117539524","https://openalex.org/W2250384498","https://openalex.org/W2274287116","https://openalex.org/W2470139095","https://openalex.org/W2479423890","https://openalex.org/W2579549467","https://openalex.org/W2590174509","https://openalex.org/W2591644541","https://openalex.org/W2607855566","https://openalex.org/W2618799552","https://openalex.org/W2751514133","https://openalex.org/W2765137706","https://openalex.org/W2810482788","https://openalex.org/W2883275382","https://openalex.org/W2886970679","https://openalex.org/W2950096400","https://openalex.org/W2951323451","https://openalex.org/W2962785943","https://openalex.org/W2963351448","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2963650529","https://openalex.org/W2964286567","https://openalex.org/W2981385984","https://openalex.org/W2981665364","https://openalex.org/W2981895973","https://openalex.org/W2982147439","https://openalex.org/W2982272924","https://openalex.org/W2982277552","https://openalex.org/W2982515679","https://openalex.org/W2985775525","https://openalex.org/W2987123286","https://openalex.org/W2991971130","https://openalex.org/W3034467781","https://openalex.org/W3035017890","https://openalex.org/W3035309251","https://openalex.org/W3035503132","https://openalex.org/W3092803144","https://openalex.org/W3093028502","https://openalex.org/W3093195700","https://openalex.org/W3100591638","https://openalex.org/W3109142545","https://openalex.org/W3109173645","https://openalex.org/W3118923280","https://openalex.org/W3121480429","https://openalex.org/W3122622502","https://openalex.org/W3152619510","https://openalex.org/W3160698766","https://openalex.org/W3175961224","https://openalex.org/W3206723373","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W4230315250","https://openalex.org/W2086519370","https://openalex.org/W2087343574"],"abstract_inverted_index":{"The":[0],"core":[1],"problem":[2],"of":[3,18,21,30,68,91,193],"video":[4],"visual":[5,69],"relation":[6,14,41,70,79,93,147],"detection":[7],"(VidVRD)":[8],"lies":[9],"in":[10,43,64,72,152],"accurately":[11],"classifying":[12],"the":[13,19,27,54,66,89,108,112,119,136,159,188],"triplets,":[15],"which":[16,95,177],"comprise":[17],"classes":[20,29],"subject":[22],"and":[23,26,100,135,156,195],"object":[24],"entities,":[25],"predicate":[28],"various":[31],"relationships":[32],"between":[33],"them.":[34,57],"Existing":[35],"VidVRD":[36,171],"approaches":[37],"classify":[38],"these":[39],"three":[40],"components":[42],"either":[44],"independent":[45],"or":[46],"cascaded":[47],"manner,":[48],"thus":[49],"fail":[50],"to":[51,60,105,125],"fully":[52],"exploit":[53],"inter-dependency":[55,63],"among":[56],"In":[58],"order":[59],"utilize":[61],"this":[62,145],"tackling":[65],"challenges":[67],"recognition":[71],"videos,":[73],"we":[74,164],"propose":[75,101],"a":[76,102,153,168],"novel":[77],"iterative":[78,146],"inference":[80,121,148],"approach":[81,104,122],"for":[82],"VidVRD.":[83],"We":[84],"derive":[85],"our":[86],"model":[87],"from":[88,111],"viewpoint":[90],"joint":[92],"classification":[94],"is":[96,123],"light-weight":[97],"yet":[98],"effective,":[99],"training":[103],"better":[106],"learn":[107],"dependency":[109,134],"knowledge":[110],"likely":[113],"correct":[114],"triplet":[115],"combinations.":[116],"As":[117],"such,":[118],"proposed":[120],"able":[124],"gradually":[126],"refine":[127],"each":[128],"component":[129],"based":[130],"on":[131,191],"its":[132],"learnt":[133],"other":[137],"two's":[138],"predictions.":[139],"Our":[140],"ablation":[141],"studies":[142],"show":[143,184],"that":[144,185],"can":[149],"empirically":[150],"converge":[151],"few":[154],"steps":[155],"consistently":[157],"boost":[158],"performance":[160,190],"over":[161],"baselines.":[162],"Further,":[163],"incorporate":[165],"it":[166],"into":[167],"newly":[169],"designed":[170],"architecture,":[172],"named":[173],"VidVRD-II":[174,186],"(Iterative":[175],"Inference),":[176],"generalizes":[178],"well":[179],"across":[180],"different":[181],"datasets.":[182,198],"Experiments":[183],"achieves":[187],"start-of-the-art":[189],"both":[192],"ImageNet-VidVRD":[194],"VidOR":[196],"benchmark":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}