{"id":"https://openalex.org/W3205903209","doi":"https://doi.org/10.1145/3474085.3479214","title":"Joint Learning for Relationship and Interaction Analysis in Video with Multimodal Feature Fusion","display_name":"Joint Learning for Relationship and Interaction Analysis in Video with Multimodal Feature Fusion","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205903209","doi":"https://doi.org/10.1145/3474085.3479214","mag":"3205903209"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3479214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3479214","pdf_url":null,"source":null,"license":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100441018","display_name":"Beibei Zhang","orcid":"https://orcid.org/0009-0005-2301-8160"},"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":"Beibei Zhang","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/A5100616402","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-4978-0023"},"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":"Fan Yu","raw_affiliation_strings":["Nanjing University & Shenzhen Research Institute of Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University & Shenzhen Research Institute of Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060152249","display_name":"Yanxin Gao","orcid":"https://orcid.org/0000-0002-4350-428X"},"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":"Yanxin Gao","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 & Shenzhen Research Institute of Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University & Shenzhen Research Institute of 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":5,"corresponding_author_ids":["https://openalex.org/A5100441018"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.5764,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.68810458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4848","last_page":"4852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.798425555229187},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7432706356048584},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6692413091659546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6108119487762451},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6033013463020325},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.5074507594108582},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.4776659905910492},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42774543166160583},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3648790121078491},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3471550941467285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.322797954082489}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.798425555229187},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7432706356048584},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6692413091659546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6108119487762451},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6033013463020325},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.5074507594108582},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.4776659905910492},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42774543166160583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3648790121078491},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3471550941467285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.322797954082489},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3479214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3479214","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5028012422","display_name":null,"funder_award_id":"BK20191248","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G5780412165","display_name":null,"funder_award_id":"JCYJ20180307151516166","funder_id":"https://openalex.org/F4320326705","funder_display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality"}],"funders":[{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326705","display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1677409904","https://openalex.org/W2048017049","https://openalex.org/W2067766814","https://openalex.org/W2169393274","https://openalex.org/W2214946242","https://openalex.org/W2341528187","https://openalex.org/W2609468337","https://openalex.org/W2613779721","https://openalex.org/W2765137706","https://openalex.org/W2896457183","https://openalex.org/W2920942303","https://openalex.org/W2951728675","https://openalex.org/W2981393651","https://openalex.org/W2982672255","https://openalex.org/W3014391540","https://openalex.org/W3021553284","https://openalex.org/W3034364644","https://openalex.org/W3034552680","https://openalex.org/W3035124602","https://openalex.org/W3093087807","https://openalex.org/W3095753995","https://openalex.org/W3096861448","https://openalex.org/W3101998545","https://openalex.org/W3105473141","https://openalex.org/W3158783196"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2888483922","https://openalex.org/W4396737233","https://openalex.org/W2367747139","https://openalex.org/W4391102217","https://openalex.org/W2566187525","https://openalex.org/W2566334511","https://openalex.org/W3147584709","https://openalex.org/W4224286930"],"abstract_inverted_index":{"To":[0],"comprehend":[1],"long":[2],"duration":[3],"videos,":[4],"the":[5,39,58,123,126,133,138],"deep":[6],"video":[7,74,117],"understanding":[8],"(DVU)":[9],"task":[10,41,60],"is":[11],"proposed":[12],"to":[13,38,101,122,136],"recognize":[14],"interactions":[15],"on":[16,21,27,132],"scene":[17,66,69],"level":[18,23],"and":[19,24,48,51,72,85,88,97],"relationships":[20],"movie":[22],"answer":[25,114],"questions":[26,115],"these":[28],"two":[29],"levels.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,104,113],"propose":[35],"a":[36,106],"solution":[37,56],"DVU":[40,59,120],"which":[42,79],"applies":[43],"joint":[44,63,110],"learning":[45,64],"of":[46,78,125,140],"interaction":[47,70,96],"relationship":[49,75,98],"prediction":[50],"multimodal":[52],"feature":[53],"fusion.":[54],"Our":[55],"handles":[57],"with":[61,109],"three":[62,127],"sub-tasks:":[65],"sentiment":[67],"classification,":[68],"recognition":[71],"super-scene":[73],"recognition,":[76],"all":[77],"utilize":[80],"text":[81],"features,":[82,87],"visual":[83],"features":[84],"audio":[86],"predict":[89],"representations":[90],"in":[91,119],"semantic":[92],"space.":[93],"Since":[94],"sentiment,":[95],"are":[99],"related":[100],"each":[102],"other,":[103],"train":[105],"unified":[107],"framework":[108],"learning.":[111],"Then,":[112],"for":[116],"analysis":[118],"according":[121],"results":[124],"sub-tasks.":[128],"We":[129],"conduct":[130],"experiments":[131],"HLVU":[134],"dataset":[135],"evaluate":[137],"effectiveness":[139],"our":[141],"method.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}