{"id":"https://openalex.org/W4304097992","doi":"https://doi.org/10.1145/3503161.3551578","title":"Deep Video Understanding with a Unified Multi-Modal Retrieval Framework","display_name":"Deep Video Understanding with a Unified Multi-Modal Retrieval Framework","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304097992","doi":"https://doi.org/10.1145/3503161.3551578"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3551578","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551578","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/A5040830437","display_name":"Chen-Wei Xie","orcid":null},"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":"Chen-Wei Xie","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","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":false,"raw_author_name":"Siyang Sun","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008764454","display_name":"Liming Zhao","orcid":"https://orcid.org/0009-0007-8872-2110"},"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":"Liming Zhao","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020280128","display_name":"Jianmin Wu","orcid":"https://orcid.org/0000-0002-0999-9194"},"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":"Jianmin Wu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052878078","display_name":"Dangwei Li","orcid":"https://orcid.org/0000-0001-5252-9174"},"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":"Dangwei Li","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, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040830437"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.0602,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.27912448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7055","last_page":"7059"},"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":0.9973999857902527,"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":0.9970999956130981,"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":0.8676700592041016},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.8263353109359741},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6663903594017029},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6086887717247009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.567559540271759},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5274294018745422},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.5085598230361938},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43986648321151733},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35827282071113586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8676700592041016},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.8263353109359741},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6663903594017029},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6086887717247009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.567559540271759},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5274294018745422},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.5085598230361938},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43986648321151733},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35827282071113586},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3551578","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551578","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":14,"referenced_works":["https://openalex.org/W2078238240","https://openalex.org/W2612690371","https://openalex.org/W2914699769","https://openalex.org/W2963890755","https://openalex.org/W3021553284","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3105473141","https://openalex.org/W3135367836","https://openalex.org/W3176641147","https://openalex.org/W3177224328","https://openalex.org/W3207650505","https://openalex.org/W3216765867","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W4301594054","https://openalex.org/W2794488505","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2714992399"],"abstract_inverted_index":{"In":[0],"this":[1,151],"paper,":[2],"we":[3,83,130],"propose":[4,84],"a":[5,40,70,85,133],"unified":[6,86],"multi-modal":[7,42,71,80,87,102],"retrieval":[8,43,72,81,88],"framework":[9,55],"to":[10],"tackle":[11],"two":[12,77],"typical":[13],"video":[14,127],"understanding":[15,128],"tasks,":[16],"i.e.,":[17],"matching":[18,32],"movie":[19,33,65,126],"scenes":[20,34],"and":[21,24,35,142],"text":[22,36,143],"descriptions,":[23,37],"scene":[25,50],"sentiment":[26,51,61],"classification.":[27],"For":[28],"the":[29,47,53,96,111,123,148],"task":[30,48],"of":[31,49,95,117,150],"it":[38,107],"is":[39,68,108],"natural":[41],"problem,":[44],"while":[45],"for":[46,63,110],"classification,":[52],"proposed":[54],"aims":[56],"at":[57],"finding":[58],"most":[59],"related":[60],"tag":[62],"each":[64],"scene,":[66],"which":[67,90,113,138],"also":[69,131],"problem.":[73],"By":[74],"considering":[75],"these":[76],"tasks":[78,112],"as":[79],"problems,":[82],"framework,":[89],"can":[91],"make":[92],"full":[93],"use":[94],"models":[97],"pre-trained":[98],"on":[99,125],"large":[100,134],"scale":[101,135],"datasets,":[103],"experiments":[104],"show":[105],"that":[106],"critical":[109],"have":[114],"only":[115],"hundreds":[116],"training":[118],"examples.":[119],"To":[120],"further":[121],"improve":[122],"performance":[124],"task,":[129],"collect":[132],"video-text":[136],"dataset,":[137],"contains":[139],"427,603":[140],"movie-shot":[141],"pairs.":[144],"Experimental":[145],"results":[146],"validate":[147],"effectiveness":[149],"dataset.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}