{"id":"https://openalex.org/W3206723373","doi":"https://doi.org/10.1145/3474085.3475173","title":"Multi-Perspective Video Captioning","display_name":"Multi-Perspective Video Captioning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206723373","doi":"https://doi.org/10.1145/3474085.3475173","mag":"3206723373"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475173","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475173","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":"conference-paper","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/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Bin","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017342089","display_name":"Xindi Shang","orcid":"https://orcid.org/0000-0002-9308-2927"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xindi Shang","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061202217","display_name":"Bo Peng","orcid":"https://orcid.org/0000-0002-6616-453X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Peng","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091807843","display_name":"Yujuan Ding","orcid":"https://orcid.org/0000-0003-2945-1107"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yujuan Ding","raw_affiliation_strings":["Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5110","last_page":"5118"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"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":0.9950000047683716,"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/closed-captioning","display_name":"Closed captioning","score":0.9699031114578247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8710737824440002},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.8036414384841919},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6539990305900574},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5529327392578125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48806440830230713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4448586702346802},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44001027941703796},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39213451743125916},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3586454391479492},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34676915407180786},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11592930555343628}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9699031114578247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8710737824440002},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.8036414384841919},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6539990305900574},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5529327392578125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48806440830230713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4448586702346802},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44001027941703796},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39213451743125916},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3586454391479492},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34676915407180786},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11592930555343628},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475173","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475173","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/G2464018058","display_name":null,"funder_award_id":"U20B2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8698487861","display_name":null,"funder_award_id":"BX2021055, 2021M690027","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123442489","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2152984213","https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2556388456","https://openalex.org/W2557264465","https://openalex.org/W2575842049","https://openalex.org/W2607119937","https://openalex.org/W2625940279","https://openalex.org/W2752191396","https://openalex.org/W2766237723","https://openalex.org/W2788277448","https://openalex.org/W2798959609","https://openalex.org/W2803620531","https://openalex.org/W2822349497","https://openalex.org/W2887712318","https://openalex.org/W2890585349","https://openalex.org/W2897964062","https://openalex.org/W2950178297","https://openalex.org/W2951323451","https://openalex.org/W2955956881","https://openalex.org/W2962799512","https://openalex.org/W2963062932","https://openalex.org/W2963150697","https://openalex.org/W2963266340","https://openalex.org/W2963594498","https://openalex.org/W2963758027","https://openalex.org/W2963811641","https://openalex.org/W2963843052","https://openalex.org/W2963916161","https://openalex.org/W2968101724","https://openalex.org/W2982260276","https://openalex.org/W3037773948","https://openalex.org/W3098682680","https://openalex.org/W3169472988"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"This":[0],"work":[1],"targets":[2],"at":[3],"the":[4,11,31,63,128,144],"problems":[5],"of":[6,13,61,146],"comprehensive":[7],"video":[8,36,40,68,85],"captioning":[9],"and":[10,25,69,90,150],"generation":[12],"multiple":[14,44,108,165],"descriptions":[15,45,109,166],"from":[16,46,73,167],"different":[17,47,168],"perspectives,":[18],"termed":[19],"asMulti-Perspective":[20],"Video":[21],"Captioning.":[22],"We":[23,49],"build":[24],"release":[26],"a":[27,52,67,71,78,93,111],"dataset":[28,33],"named":[29],"VidOR-MPVC,":[30],"first":[32],"for":[34,110,136],"multi-perspective":[35],"captioning,":[37],"where":[38],"each":[39,74],"is":[41,59,81,159],"annotated":[42],"with":[43,87,97,164],"perspectives.":[48,169],"also":[50],"propose":[51],"novel":[53],"model,":[54],"dubbedperspective-aware":[55],"captioner":[56],"(PAC),":[57],"which":[58,140],"capable":[60],"mining":[62],"various":[64],"perspectives":[65],"in":[66],"generating":[70],"description":[72],"perspective.":[75],"More":[76],"specifically,":[77],"perspective":[79,88],"generator":[80,95],"designed":[82],"to":[83,106,118,142,161],"perceive":[84],"content":[86],"preferences,":[89],"followed":[91],"by":[92],"language":[94],"equipped":[96],"perspective-aware":[98],"attention":[99],"mechanism.":[100],"As":[101],"our":[102,157],"new":[103],"task":[104],"expects":[105],"produce":[107],"video,":[112],"existing":[113,134],"evaluation":[114,139],"metrics":[115,135],"are":[116],"fail":[117],"handle":[119],"this":[120,124],"situation.":[121],"To":[122],"address":[123],"problem,":[125],"we":[126],"devise":[127],"maximum":[129],"matching":[130],"scores":[131],"based":[132],"on":[133],"an":[137],"overall":[138],"aims":[141],"cover":[143],"aspects":[145],"semantic":[147],"similarity,":[148],"completeness":[149],"compactness.":[151],"The":[152],"experimental":[153],"results":[154],"demonstrate":[155],"that":[156],"model":[158],"able":[160],"describe":[162],"videos":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
