{"id":"https://openalex.org/W2981895973","doi":"https://doi.org/10.1145/3343031.3356076","title":"Video Visual Relation Detection via Multi-modal Feature Fusion","display_name":"Video Visual Relation Detection via Multi-modal Feature Fusion","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981895973","doi":"https://doi.org/10.1145/3343031.3356076","mag":"2981895973"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3356076","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3356076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-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/A5101441137","display_name":"Xu Sun","orcid":"https://orcid.org/0000-0001-8241-9320"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Sun","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084591510","display_name":"Tongwei Ren","orcid":"https://orcid.org/0000-0003-3092-424X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongwei Ren","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070294325","display_name":"Yuan Zi","orcid":"https://orcid.org/0000-0002-4723-538X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zi","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101546753","display_name":"Gangshan Wu","orcid":"https://orcid.org/0000-0003-1391-1762"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangshan Wu","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101441137"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":3.2391,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.93893361,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2657","last_page":"2661"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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":0.9995999932289124,"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":0.8351082801818848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8092923164367676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6971882581710815},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6797670722007751},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6424661874771118},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6084375381469727},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5484564304351807},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5043927431106567},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.49805355072021484},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4922141134738922},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.474911093711853},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43582531809806824},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4249812364578247},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.4132750332355499},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40491917729377747},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18877598643302917},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1838463544845581},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.136358380317688}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.8351082801818848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8092923164367676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6971882581710815},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6797670722007751},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6424661874771118},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6084375381469727},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5484564304351807},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5043927431106567},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49805355072021484},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4922141134738922},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.474911093711853},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43582531809806824},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4249812364578247},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.4132750332355499},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40491917729377747},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18877598643302917},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1838463544845581},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.136358380317688},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3356076","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3356076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1986482242","https://openalex.org/W2108598243","https://openalex.org/W2113221323","https://openalex.org/W2154889144","https://openalex.org/W2194775991","https://openalex.org/W2407521645","https://openalex.org/W2479423890","https://openalex.org/W2591644541","https://openalex.org/W2751514133","https://openalex.org/W2765137706","https://openalex.org/W2777602943","https://openalex.org/W2808609003","https://openalex.org/W2950577311","https://openalex.org/W2951323451","https://openalex.org/W2963576560","https://openalex.org/W2963919999","https://openalex.org/W2964286567","https://openalex.org/W2982515679","https://openalex.org/W4246999471"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2952760143","https://openalex.org/W2017776670","https://openalex.org/W2347897961","https://openalex.org/W4323768008","https://openalex.org/W1941703695","https://openalex.org/W2340870721","https://openalex.org/W2358318464"],"abstract_inverted_index":{"Video":[0,134],"visual":[1,28,129],"relation":[2,29,74,100,104,130],"detection":[3,30,49,131],"is":[4],"a":[5,13,25,118],"meaningful":[6],"research":[7],"problem,":[8],"which":[9,121],"aims":[10],"to":[11],"build":[12],"bridge":[14],"between":[15],"dynamic":[16],"vision":[17],"and":[18,55,67,84,90],"language.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,37,71,95],"propose":[24],"novel":[26],"video":[27,47],"method":[31,113],"with":[32,44,65,87],"multi-model":[33],"feature":[34,52,89],"fusion.":[35],"First,":[36],"detect":[38],"objects":[39,64],"on":[40],"each":[41],"frame":[42],"densely":[43],"the":[45,61,73,98,125],"state-of-the-art":[46],"object":[48,57,78],"model,":[50],"flow-guided":[51],"aggregation":[53],"(FGFA),":[54],"generate":[56],"trajectories":[58],"by":[59,117],"linking":[60],"temporally":[62],"independent":[63],"Seq-NMS":[66],"KCF":[68],"tracker.":[69],"Next,":[70],"break":[72],"candidates,":[75],"i.e.,":[76],"co-occurrent":[77],"trajectory":[79],"pairs,":[80],"into":[81,102],"short-term":[82,99],"segments":[83,101],"predict":[85],"relations":[86],"spatial-temporal":[88],"language":[91],"context":[92],"feature.":[93],"Finally,":[94],"greedily":[96],"associate":[97],"complete":[103],"instances.":[105],"The":[106],"experiment":[107],"results":[108],"show":[109],"that":[110],"our":[111],"proposed":[112],"outperforms":[114],"other":[115],"methods":[116],"large":[119],"margin,":[120],"also":[122],"earned":[123],"us":[124],"first":[126],"place":[127],"in":[128],"task":[132],"of":[133],"Relation":[135],"Understanding":[136],"Challenge":[137],"(VRU),":[138],"ACMMM":[139],"2019.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}