{"id":"https://openalex.org/W4205645931","doi":"https://doi.org/10.1145/3469877.3493599","title":"Hybrid Improvements in Multimodal Analysis for Deep Video Understanding","display_name":"Hybrid Improvements in Multimodal Analysis for Deep Video Understanding","publication_year":2021,"publication_date":"2021-12-01","ids":{"openalex":"https://openalex.org/W4205645931","doi":"https://doi.org/10.1145/3469877.3493599"},"language":"en","primary_location":{"id":"doi:10.1145/3469877.3493599","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3493599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","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/A5047310500","display_name":"Beibei Zhang","orcid":"https://orcid.org/0000-0002-6597-0046"},"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":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, 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":["State Key Laboratory for Novel Software Technology, Nanjing University, China and Shenzhen Research Institute of Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China and Shenzhen Research Institute of Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109589641","display_name":"Yaqun Fang","orcid":null},"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":"Yaqun Fang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, 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":["State Key Laboratory for Novel Software Technology, Nanjing University, China and Shenzhen Research Institute of Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China and Shenzhen Research Institute of Nanjing University, 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":["State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047310500"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.1921,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5146732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.833537757396698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.579245388507843},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5658135414123535},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5481904745101929},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.504654049873352},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49877357482910156},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49155697226524353},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4664819836616516},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4642207622528076},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4604443311691284},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4329715967178345},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3762989938259125},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34124070405960083},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12112551927566528},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.0779312252998352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833537757396698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579245388507843},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5658135414123535},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5481904745101929},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.504654049873352},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49877357482910156},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49155697226524353},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4664819836616516},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4642207622528076},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4604443311691284},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4329715967178345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3762989938259125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34124070405960083},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12112551927566528},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0779312252998352},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3469877.3493599","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469877.3493599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2194775991","https://openalex.org/W2963524571","https://openalex.org/W3021553284","https://openalex.org/W3095753995","https://openalex.org/W3105473141","https://openalex.org/W3167949052","https://openalex.org/W3173209770"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W4386083130","https://openalex.org/W2611989081","https://openalex.org/W3111737715","https://openalex.org/W2117442182","https://openalex.org/W2069571255","https://openalex.org/W3125517176","https://openalex.org/W4230611425","https://openalex.org/W2023355163","https://openalex.org/W2731899572"],"abstract_inverted_index":{"The":[0],"Deep":[1],"Video":[2],"Understanding":[3],"Challenge":[4],"(DVU)":[5],"is":[6,23],"a":[7],"task":[8],"that":[9],"focuses":[10],"on":[11],"comprehending":[12],"long":[13],"duration":[14],"videos":[15],"which":[16,46],"involve":[17],"many":[18,51],"entities.":[19],"Its":[20],"main":[21],"goal":[22],"to":[24,33],"build":[25],"relationship":[26],"and":[27,62],"interaction":[28],"knowledge":[29],"graph":[30],"between":[31],"entities":[32],"answer":[34],"relevant":[35],"questions.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,47],"improved":[41],"the":[42,68],"joint":[43],"learning":[44],"method":[45],"previously":[48],"proposed":[49],"in":[50],"aspects,":[52],"including":[53],"few":[54],"shot":[55],"learning,":[56],"optical":[57],"flow":[58],"feature,":[59],"entity":[60],"recognition,":[61],"video":[63],"description":[64],"matching.":[65],"We":[66],"verified":[67],"effectiveness":[69],"of":[70],"these":[71],"measures":[72],"through":[73],"experiments.":[74]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}