{"id":"https://openalex.org/W4403792461","doi":"https://doi.org/10.1145/3664647.3681603","title":"Dual-path Collaborative Generation Network for Emotional Video Captioning","display_name":"Dual-path Collaborative Generation Network for Emotional Video Captioning","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792461","doi":"https://doi.org/10.1145/3664647.3681603"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681603","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5100842113","display_name":"Cheng Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cheng Ye","raw_affiliation_strings":["School of Information Science and Technology, USTC, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-4792-3576","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, USTC, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357392","display_name":"Weidong Chen","orcid":"https://orcid.org/0000-0003-2774-2875"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Chen","raw_affiliation_strings":["School of Information Science and Technology, USTC, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2774-2875","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, USTC, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingyu Li","orcid":"https://orcid.org/0000-0002-9561-7550"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyu Li","raw_affiliation_strings":["School of Information Science and Technology, USTC, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9561-7550","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, USTC, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616189","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-2839-8693"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["School of Information Science and Technology, USTC, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2839-8693","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, USTC, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023341829","display_name":"Zhendong Mao","orcid":"https://orcid.org/0000-0001-5739-8126"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Mao","raw_affiliation_strings":["School of Information Science and Technology, USTC, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5739-8126","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, USTC, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100842113"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.8569,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.92230225,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"496","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.9987999796867371,"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":0.9435133934020996},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7779962420463562},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6850577592849731},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.6666052937507629},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5154389142990112},{"id":"https://openalex.org/keywords/videoconferencing","display_name":"Videoconferencing","score":0.4506823420524597},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4151943027973175},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37150976061820984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25680670142173767},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1131708025932312}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9435133934020996},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7779962420463562},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6850577592849731},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6666052937507629},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5154389142990112},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.4506823420524597},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4151943027973175},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37150976061820984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25680670142173767},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1131708025932312},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681603","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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":44,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1956340063","https://openalex.org/W2006904655","https://openalex.org/W2108598243","https://openalex.org/W2159797991","https://openalex.org/W2173163709","https://openalex.org/W2188687388","https://openalex.org/W2194775991","https://openalex.org/W2200631819","https://openalex.org/W2600463316","https://openalex.org/W2904005741","https://openalex.org/W2958208506","https://openalex.org/W2962681491","https://openalex.org/W2962934715","https://openalex.org/W2963062932","https://openalex.org/W2963321416","https://openalex.org/W2963524571","https://openalex.org/W2982021328","https://openalex.org/W2996799978","https://openalex.org/W3035336958","https://openalex.org/W3039060838","https://openalex.org/W3045200674","https://openalex.org/W3114652457","https://openalex.org/W3174134652","https://openalex.org/W3175546442","https://openalex.org/W3182328899","https://openalex.org/W3206261212","https://openalex.org/W3206577156","https://openalex.org/W4206490662","https://openalex.org/W4285143708","https://openalex.org/W4285200050","https://openalex.org/W4285729260","https://openalex.org/W4304084115","https://openalex.org/W4312535570","https://openalex.org/W4312735840","https://openalex.org/W4360596109","https://openalex.org/W4385805042","https://openalex.org/W4388193026","https://openalex.org/W4388796930","https://openalex.org/W4389523981","https://openalex.org/W4390195594","https://openalex.org/W4391454521","https://openalex.org/W4392909927","https://openalex.org/W4393160811"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Emotional":[0],"Video":[1],"Captioning":[2],"(EVC)":[3],"is":[4,27,42,129],"an":[5,257],"emerging":[6],"task":[7,26],"that":[8],"aims":[9],"to":[10,28,69,102,200,214,225,245],"describe":[11],"factual":[12,133,250,315],"content":[13,134,251,316],"with":[14,65,109],"the":[15,24,38,45,66,71,80,87,92,96,104,124,174,179,202,240,247,267,287,292,303,312,328],"intrinsic":[16,93],"emotions":[17,94],"expressed":[18],"in":[19,91,178,239],"videos.":[20],"The":[21,165],"essential":[22],"of":[23,79,95,106,127,249,269,314,330],"EVC":[25,81],"effectively":[29],"perceive":[30,54],"subtle":[31,89],"and":[32,61,111,171,196,207,252,272,280,307,317,333],"ambiguous":[33],"visual":[34,56,154,194,204],"emotional":[35,50,57,72,119,155,160,205,211,253,270,282,293,318],"cues":[36,58,120,156,212,319],"during":[37,139],"caption":[39,73,198,242,274,288,309],"generation,":[40,74],"which":[41,75,98,131,151,191,261],"neglected":[43],"by":[44,162,229],"traditional":[46],"video":[47,51,67],"captioning.":[48],"Existing":[49],"captioning":[52],"methods":[53,85,117,297],"global":[55,203],"at":[59,217,276,302],"first,":[60],"then":[62,208],"combine":[63],"them":[64,224],"features":[68,195,199,271,275],"guide":[70],"neglects":[76],"two":[77,166],"characteristics":[78],"task.":[82],"Firstly,":[83],"their":[84,116],"neglect":[86],"dynamic":[88,180,187],"changes":[90],"video,":[97],"makes":[99,132],"it":[100],"difficult":[101],"meet":[103],"needs":[105],"common":[107],"scenes":[108],"diverse":[110],"changeable":[112],"emotions.":[113],"Secondly,":[114],"as":[115,220,222],"incorporate":[118,285],"into":[121,286],"each":[122,169,218,277,334],"step,":[123,279,306],"guidance":[125,283,313],"role":[126],"emotion":[128,181,188,227,258,264],"overemphasized,":[130],"more":[135],"or":[136,232],"less":[137],"ignored":[138],"generation.":[140],"To":[141],"this":[142],"end,":[143],"we":[144,184,255],"propose":[145,185,256],"a":[146,186],"dual-path":[147],"collaborative":[148,163],"generation":[149,175,243,278,289,310],"network,":[150],"dynamically":[152,209,230],"perceives":[153],"evolutions":[157],"while":[158],"generating":[159],"captions":[161],"learning.":[164],"paths":[167],"promote":[168],"other":[170],"significantly":[172],"improve":[173],"performance.":[176],"Specifically,":[177],"perception":[182],"path,":[183,244],"evolution":[189,228],"module,":[190],"first":[192],"aggregates":[193],"historical":[197,273],"summarize":[201],"cues,":[206,254],"selects":[210],"required":[213],"be":[215],"re-composed":[216,223],"stage":[219],"well":[221],"achieve":[226],"enhancing":[231],"suppressing":[233],"different":[234],"granularity":[235],"subspace's":[236],"semantics.":[237],"Besides,":[238],"adaptive":[241,259],"balance":[246],"description":[248],"decoder,":[260],"firstly":[262],"estimates":[263],"intensity":[265],"via":[266],"alignment":[268],"then,":[281],"adaptively":[284],"based":[290],"on":[291,323],"intensity.":[294],"Thus,":[295],"our":[296,308,331],"can":[298],"generate":[299],"emotion-related":[300],"words":[301],"necessary":[304],"time":[305],"balances":[311],"well.":[320],"Extensive":[321],"experiments":[322],"three":[324],"challenging":[325],"datasets":[326],"demonstrate":[327],"superiority":[329],"approach":[332],"proposed":[335],"module.":[336]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}