{"id":"https://openalex.org/W3197533038","doi":"https://doi.org/10.1109/tmm.2021.3109430","title":"Attention Guided Relation Detection Approach for Video Visual Relation Detection","display_name":"Attention Guided Relation Detection Approach for Video Visual Relation Detection","publication_year":2021,"publication_date":"2021-09-03","ids":{"openalex":"https://openalex.org/W3197533038","doi":"https://doi.org/10.1109/tmm.2021.3109430","mag":"3197533038"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3109430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3109430","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","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/A5022081570","display_name":"Qianwen Cao","orcid":"https://orcid.org/0000-0001-7491-5201"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianwen Cao","raw_affiliation_strings":["Computer Science, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7491-5201","affiliations":[{"raw_affiliation_string":"Computer Science, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087631670","display_name":"Heyan Huang","orcid":"https://orcid.org/0000-0002-0320-7520"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heyan Huang","raw_affiliation_strings":["Computer Science, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0320-7520","affiliations":[{"raw_affiliation_string":"Computer Science, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.545,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.63554171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"24","issue":null,"first_page":"3896","last_page":"3907"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"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":0.9980999827384949,"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/relation","display_name":"Relation (database)","score":0.7086429595947266},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6403385400772095},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5657439827919006},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5076569318771362},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49562132358551025},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.47541099786758423},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4444847106933594},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.41432714462280273},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4120733141899109},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2897680401802063},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22203752398490906},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17597216367721558},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15881720185279846},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.08027946949005127}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.7086429595947266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6403385400772095},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5657439827919006},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5076569318771362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49562132358551025},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.47541099786758423},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4444847106933594},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.41432714462280273},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4120733141899109},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2897680401802063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22203752398490906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17597216367721558},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15881720185279846},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.08027946949005127},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3109430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3109430","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1250004542","display_name":null,"funder_award_id":"61602197","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7118507406","display_name":"\u878d\u5165\u6982\u5ff5\u7684\u9ad8\u6548\u4e3b\u9898\u5206\u6790\u6846\u67b6\u4e0e\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61772076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7920740482","display_name":null,"funder_award_id":"U19B2020","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1589504938","https://openalex.org/W1861492603","https://openalex.org/W1997121481","https://openalex.org/W2016133308","https://openalex.org/W2105101328","https://openalex.org/W2117539524","https://openalex.org/W2154889144","https://openalex.org/W2250384498","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2749203358","https://openalex.org/W2754191212","https://openalex.org/W2765137706","https://openalex.org/W2801086478","https://openalex.org/W2895845501","https://openalex.org/W2913618459","https://openalex.org/W2951323451","https://openalex.org/W2953461088","https://openalex.org/W2954199749","https://openalex.org/W2962811161","https://openalex.org/W2962949233","https://openalex.org/W2962964995","https://openalex.org/W2963524571","https://openalex.org/W2963536419","https://openalex.org/W2963653352","https://openalex.org/W2964015378","https://openalex.org/W2964015640","https://openalex.org/W2964286567","https://openalex.org/W2968104955","https://openalex.org/W2969897437","https://openalex.org/W2981385984","https://openalex.org/W2981665364","https://openalex.org/W2981820283","https://openalex.org/W2981895973","https://openalex.org/W2982277552","https://openalex.org/W2982277980","https://openalex.org/W2982515679","https://openalex.org/W2999794487","https://openalex.org/W3005881764","https://openalex.org/W3008653537","https://openalex.org/W3009294634","https://openalex.org/W3035503132","https://openalex.org/W3093028502","https://openalex.org/W3093272873","https://openalex.org/W3104374384","https://openalex.org/W3118212025","https://openalex.org/W3118923280","https://openalex.org/W3130464934","https://openalex.org/W3214910576","https://openalex.org/W4240191182","https://openalex.org/W4293437100","https://openalex.org/W4303633609","https://openalex.org/W6639102338","https://openalex.org/W6684821475","https://openalex.org/W6695799263","https://openalex.org/W6697005757","https://openalex.org/W6726873649"],"related_works":["https://openalex.org/W2504004674","https://openalex.org/W2963177394","https://openalex.org/W4313359513","https://openalex.org/W2498744856","https://openalex.org/W4390482104","https://openalex.org/W322408318","https://openalex.org/W149041114","https://openalex.org/W1965815883","https://openalex.org/W763418848","https://openalex.org/W1583261078"],"abstract_inverted_index":{"Video":[0],"Visual":[1],"Relation":[2],"Detection":[3],"(VidVRD)":[4],"aims":[5],"at":[6],"detecting":[7],"the":[8,16,27,30,33,46,70,77,92,105,114,121,135,155,162,169,185,213,224,228],"relation":[9,23,78,146],"instances":[10,79],"between":[11],"two":[12,60],"observed":[13],"objects":[14],"in":[15,59,65,83,111,123,137,227],"form":[17],"of$<":[18],"$subject-predicate-object$>$.":[19],"Unlike":[20],"image":[21],"visual":[22,196],"detection,":[24],"due":[25,103],"to":[26,42,68,104,119,130,153,180,193],"introduction":[28],"of":[29,215],"time":[31],"dimensions,":[32],"various":[34],"predicates":[35],"and":[36,72,108,160,175,198,209],"spatial-temporal":[37],"locations":[38,82],"are":[39],"both":[40,195],"required":[41],"be":[43],"tackled,":[44],"making":[45],"task":[47,58],"challenging.":[48],"To":[49,133],"balance":[50],"these":[51,167],"challenges,":[52],"most":[53],"existing":[54],"works":[55,86,125],"perform":[56],"this":[57,138],"phases:":[61],"first":[62],"predicting":[63],"relationships":[64,89],"segmented":[66],"clips":[67],"capture":[69],"motions,":[71],"then":[73],"associating":[74],"them":[75,98],"into":[76,201],"with":[80],"proper":[81],"videos.":[84],"These":[85],"detect":[87],"different":[88,158],"by":[90],"collecting":[91],"cues":[93,159,168],"from":[94],"multi-aspects,":[95],"but":[96],"treat":[97],"equally":[99],"without":[100],"distinction.":[101],"Furthermore,":[102],"dynamic":[106],"scenes":[107],"drifting":[109],"problem":[110],"object":[112],"tracking,":[113],"rigid":[115],"spatial":[116],"overlap":[117],"used":[118],"determine":[120],"association":[122,176],"previous":[124],"is":[126,230],"insufficient,":[127],"which":[128],"leads":[129],"missing":[131],"associations.":[132],"address":[134],"problems,":[136],"paper,":[139],"we":[140,165,187],"propose":[141],"a":[142,190],"novel":[143],"attention":[144,170],"guided":[145],"detection":[147],"approach":[148,229],"for":[149,172],"VidVRD.":[150],"In":[151,178],"order":[152],"model":[154],"distinction":[156],"among":[157],"strengthen":[161],"salient":[163],"characteristics,":[164],"assign":[166],"weights":[171],"relationship":[173],"prediction":[174],"decision-making.":[177],"addition,":[179],"comprehensively":[181],"measure":[182],"whether":[183],"merging":[184],"relationships,":[186],"put":[188],"forward":[189],"customized":[191],"network":[192],"take":[194],"appearance":[197],"geometric":[199],"location":[200],"account.":[202],"Extensive":[203],"experiment":[204],"results":[205],"on":[206],"ImageNet-VidVRD":[207],"dataset":[208,211],"VidOR":[210],"demonstrate":[212],"effectiveness":[214],"our":[216],"proposed":[217],"approach.":[218],"And":[219],"abundant":[220],"ablation":[221],"studies":[222],"verify":[223],"component":[225],"designed":[226],"essential.":[231]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}