{"id":"https://openalex.org/W4304087177","doi":"https://doi.org/10.1145/3503161.3551575","title":"Two stage Multi-Modal Modeling for Video Interaction Analysis in Deep Video Understanding Challenge","display_name":"Two stage Multi-Modal Modeling for Video Interaction Analysis in Deep Video Understanding Challenge","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304087177","doi":"https://doi.org/10.1145/3503161.3551575"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3551575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551575","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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/A5101751688","display_name":"Siyang Sun","orcid":"https://orcid.org/0000-0003-0579-2732"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Siyang Sun","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752678","display_name":"Xiong Xiong","orcid":"https://orcid.org/0000-0002-5992-9733"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiong Xiong","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058744406","display_name":"Yun Zheng","orcid":"https://orcid.org/0000-0002-1612-7191"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Zheng","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101751688"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.3596,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67324968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7040","last_page":"7044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.8564995527267456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6900926232337952},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6547617316246033},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5880861282348633},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5792953372001648},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5222405195236206},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5067391991615295},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5016582012176514},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.495461106300354},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.465236097574234},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4131196439266205},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3803684711456299}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8564995527267456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6900926232337952},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6547617316246033},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5880861282348633},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5792953372001648},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5222405195236206},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5067391991615295},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5016582012176514},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.495461106300354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.465236097574234},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4131196439266205},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3803684711456299},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3551575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551575","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":23,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1927052826","https://openalex.org/W2194775991","https://openalex.org/W2765137706","https://openalex.org/W2963076818","https://openalex.org/W2963524571","https://openalex.org/W2963976704","https://openalex.org/W2994972433","https://openalex.org/W3014641072","https://openalex.org/W3021553284","https://openalex.org/W3034364644","https://openalex.org/W3105473141","https://openalex.org/W3135367836","https://openalex.org/W3145166545","https://openalex.org/W3173795112","https://openalex.org/W3184549588","https://openalex.org/W3205021045","https://openalex.org/W3205621936","https://openalex.org/W3205903209","https://openalex.org/W3207650505","https://openalex.org/W4247717022","https://openalex.org/W4312245820","https://openalex.org/W4312864639"],"related_works":["https://openalex.org/W2888673113","https://openalex.org/W2056065966","https://openalex.org/W2062641654","https://openalex.org/W2352602608","https://openalex.org/W4323768008","https://openalex.org/W2212288070","https://openalex.org/W3023262859","https://openalex.org/W4360995134","https://openalex.org/W1941703695","https://openalex.org/W2387529410"],"abstract_inverted_index":{"Interaction":[0],"understanding":[1,19],"between":[2,27,63],"different":[3,28],"entities":[4,30],"in":[5,98],"human-centered":[6],"movie":[7],"video":[8,18],"is":[9,22,68],"receiving":[10],"more":[11,13],"and":[12,41,78,86,93,114,121],"attention.":[14],"Recently,":[15],"a":[16,54],"deep":[17],"(DVU)":[20],"task":[21],"proposed":[23,126],"to":[24,59,127],"identify":[25],"interactions":[26,44,129],"person":[29,79,88,107],"on":[31,141],"scene":[32,66],"level":[33],"task.":[34],"However,":[35],"limited":[36],"samples":[37],"of":[38],"DVU":[39,143],"dataset":[40],"multiple":[42,122],"complex":[43],"make":[45],"it":[46],"difficult.":[47],"To":[48],"tackle":[49],"these":[50],"problems,":[51],"we":[52,91],"propose":[53],"two":[55],"stage":[56],"multi-modal":[57,96],"method":[58,137],"predict":[60,128],"the":[61,99,142],"interaction":[62],"entities.":[64],"Specifically,":[65],"segment":[67],"first":[69],"divided":[70],"into":[71],"several":[72],"sub-scene":[73],"clips,":[74],"meanwhile":[75],"face":[76,84,104],"trajectory":[77,80],"are":[81,125],"obtained":[82],"through":[83],"tracking/recognition":[85],"skeleton-based":[87],"tracing.":[89],"Then,":[90],"extract":[92],"jointly":[94],"train":[95],"features":[97,113],"same":[100],"semantic":[101],"space":[102],"including":[103],"emotion":[105],"feature,":[106,109],"entity":[108],"visual":[110],"features,":[111],"text":[112],"audio":[115],"features.":[116],"Finally,":[117],"zero-shot":[118],"transfer":[119],"model":[120,124],"classification":[123],"together.":[130],"The":[131],"experimental":[132],"results":[133],"show":[134],"that":[135],"our":[136],"performs":[138],"new":[139],"state-of-the-art":[140],"dataset.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
