{"id":"https://openalex.org/W3093309458","doi":"https://doi.org/10.1145/3394171.3416290","title":"XlanV Model with Adaptively Multi-Modality Feature Fusing for Video Captioning","display_name":"XlanV Model with Adaptively Multi-Modality Feature Fusing for Video Captioning","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093309458","doi":"https://doi.org/10.1145/3394171.3416290","mag":"3093309458"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3416290","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3416290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th 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/A5058825605","display_name":"Yiqing Huang","orcid":"https://orcid.org/0000-0002-2143-3329"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqing Huang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102341768","display_name":"Qiuyu Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuyu Cai","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086356513","display_name":"Siyu Xu","orcid":"https://orcid.org/0000-0002-2630-5895"},"institutions":[{"id":"https://openalex.org/I44675526","display_name":"Shanghai Ocean University","ror":"https://ror.org/04n40zv07","country_code":"CN","type":"education","lineage":["https://openalex.org/I44675526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Xu","raw_affiliation_strings":["Shanghai Ocean University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Ocean University, Shanghai, China","institution_ids":["https://openalex.org/I44675526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668653","display_name":"Jiansheng Chen","orcid":"https://orcid.org/0000-0002-2040-7938"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiansheng Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4600","last_page":"4604"},"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":0.9991999864578247,"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":0.9901999831199646,"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":0.958991289138794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8502827286720276},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7734754681587219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6537925004959106},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6108114719390869},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4909220337867737},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.490416020154953},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4789762496948242},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.47340521216392517},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3757729232311249},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35914748907089233},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.22608941793441772}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.958991289138794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8502827286720276},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7734754681587219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6537925004959106},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6108114719390869},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4909220337867737},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.490416020154953},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4789762496948242},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.47340521216392517},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3757729232311249},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35914748907089233},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22608941793441772},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3416290","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3416290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th 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":25,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1593271688","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2139501017","https://openalex.org/W2154652894","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2506483933","https://openalex.org/W2556388456","https://openalex.org/W2951390634","https://openalex.org/W2962990649","https://openalex.org/W2963084599","https://openalex.org/W2963177403","https://openalex.org/W2963403868","https://openalex.org/W2963524571","https://openalex.org/W2963971014","https://openalex.org/W2984862483","https://openalex.org/W2986670728","https://openalex.org/W2990818246","https://openalex.org/W3035284526","https://openalex.org/W3040468852"],"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":{"The":[0,95],"dynamic":[1,50,116],"feature":[2,12,51,117],"extracted":[3,13],"by":[4,14],"the":[5,10,33,49,60,79,83,89,100,104,115],"3D":[6],"convolutional":[7],"network":[8],"and":[9,38,64,71],"static":[11],"CNN":[15],"are":[16],"proved":[17],"to":[18],"be":[19],"beneficial":[20],"for":[21,42,106],"video":[22,43,70,73,107],"captioning.":[23,44],"We":[24],"adaptively":[25],"fuse":[26],"these":[27],"two":[28],"kinds":[29],"of":[30,68],"features":[31],"in":[32,92,103,124],"X-Linear":[34],"Attention":[35],"Network":[36],"Video":[37],"propose":[39],"XlanV":[40,80,97],"model":[41,81,98],"However,":[45],"we":[46,76],"notice":[47],"that":[48,112],"is":[52,118],"not":[53],"compatible":[54],"with":[55],"vision-language":[56,122],"pre-training":[57,87,105,123],"techniques":[58],"when":[59],"frame":[61],"length":[62],"distribution":[63],"average":[65],"pixel":[66],"difference":[67],"training":[69],"test":[72],"biases.":[74],"Consequently,":[75],"directly":[77],"train":[78],"on":[82,88],"MSR-VTT":[84],"dataset":[85,91],"without":[86],"GIF":[90],"this":[93,125],"challenge.":[94,126],"proposed":[96],"reaches":[99],"1st":[101],"place":[102],"captioning":[108],"challenge,":[109],"which":[110],"shows":[111],"substantially":[113],"exploiting":[114],"more":[119],"effective":[120],"than":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}