{"id":"https://openalex.org/W3093195700","doi":"https://doi.org/10.1145/3394171.3416284","title":"Video Relation Detection with Trajectory-aware Multi-modal Features","display_name":"Video Relation Detection with Trajectory-aware Multi-modal Features","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093195700","doi":"https://doi.org/10.1145/3394171.3416284","mag":"3093195700"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3416284","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3416284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.08165","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101087678","display_name":"Wentao Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wentao Xie","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004911199","display_name":"Guanghui Ren","orcid":"https://orcid.org/0000-0002-2743-8278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanghui Ren","raw_affiliation_strings":["YITU Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"YITU Technology, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100330138","display_name":"Si Liu","orcid":"https://orcid.org/0000-0002-9180-2935"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Si Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101087678"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.472,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.84920055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4590","last_page":"4594"},"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":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","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"}}],"keywords":[{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.8633116483688354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.801881730556488},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.765863835811615},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7030457258224487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6851826310157776},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6244568228721619},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6174344420433044},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.555436372756958},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5546923875808716},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5444740653038025},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5074095129966736},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4474496841430664},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4271141290664673},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.346401572227478},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2555558681488037},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2523798942565918}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.8633116483688354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.801881730556488},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.765863835811615},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7030457258224487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6851826310157776},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6244568228721619},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6174344420433044},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.555436372756958},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5546923875808716},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5444740653038025},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5074095129966736},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4474496841430664},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4271141290664673},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.346401572227478},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2555558681488037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2523798942565918},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394171.3416284","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3416284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.08165","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.08165","pdf_url":"https://arxiv.org/pdf/2101.08165","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.08165","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.08165","pdf_url":"https://arxiv.org/pdf/2101.08165","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W2282391807","https://openalex.org/W2765137706","https://openalex.org/W2884561390","https://openalex.org/W2924996095","https://openalex.org/W2951323451","https://openalex.org/W2963351448","https://openalex.org/W2963524571","https://openalex.org/W2963536419","https://openalex.org/W2964241181","https://openalex.org/W2981385984","https://openalex.org/W2981665364","https://openalex.org/W2981895973","https://openalex.org/W2982272924","https://openalex.org/W2982515679","https://openalex.org/W3016719260","https://openalex.org/W3021735172","https://openalex.org/W3035017890","https://openalex.org/W3035503132","https://openalex.org/W3035598501","https://openalex.org/W4293437100","https://openalex.org/W4297665946","https://openalex.org/W4302602837"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2017776670","https://openalex.org/W2952760143","https://openalex.org/W2347897961","https://openalex.org/W2979236518","https://openalex.org/W1941703695","https://openalex.org/W2358318464","https://openalex.org/W2340870721"],"abstract_inverted_index":{"Video":[0,103],"relation":[1,29,45,61,87,99],"detection":[2,7,30,46,68,77,100],"problem":[3],"refers":[4],"to":[5,35,70,82],"the":[6,9,40,65,72,84,93,97],"of":[8,42,74,86,102],"relationship":[10,19],"between":[11,88],"different":[12],"objects":[13],"in":[14,47,108],"videos,":[15,48],"such":[16],"as":[17],"spatial":[18],"and":[20,60,78],"action":[21],"relationship.":[22],"In":[23],"this":[24,37,51],"paper,":[25],"we":[26,49],"present":[27],"video":[28,98],"with":[31,112],"trajectory-aware":[32],"multi-modal":[33,79],"features":[34],"solve":[36],"task.":[38],"Considering":[39],"complexity":[41],"doing":[43],"visual":[44],"decompose":[50],"task":[52,101],"into":[53],"three":[54],"sub-tasks:":[55],"object":[56,67,75],"detection,":[57],"trajectory":[58,76],"proposal":[59],"prediction.":[62],"We":[63],"use":[64],"state-of-the-art":[66],"method":[69,91],"ensure":[71],"accuracy":[73],"feature":[80],"representation":[81],"help":[83],"prediction":[85],"objects.":[89],"Our":[90],"won":[92],"first":[94],"place":[95],"on":[96],"Relation":[104],"Understanding":[105],"Grand":[106],"Challenge":[107],"ACM":[109],"Multimedia":[110],"2020":[111],"11.74%":[113],"mAP,":[114],"which":[115],"surpasses":[116],"other":[117],"methods":[118],"by":[119],"a":[120],"large":[121],"margin.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}