{"id":"https://openalex.org/W3206818591","doi":"https://doi.org/10.1145/3474085.3479228","title":"Semantic Tag Augmented XlanV Model for Video Captioning","display_name":"Semantic Tag Augmented XlanV Model for Video Captioning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206818591","doi":"https://doi.org/10.1145/3474085.3479228","mag":"3206818591"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3479228","doi":"https://doi.org/10.1145/3474085.3479228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3479228","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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","observed_orcids":["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/A5110819662","display_name":"Hongwei Xue","orcid":null,"observed_orcids":[]},"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":"Hongwei Xue","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668653","display_name":"Jiansheng Chen","orcid":"https://orcid.org/0000-0002-2040-7938","observed_orcids":["https://orcid.org/0000-0002-2040-7938"]},"institutions":[{"id":"https://openalex.org/I4405271667","display_name":"Beijing National Research Center for Information Science and Technology","ror":"https://ror.org/02tcm9e24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405271667"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiansheng Chen","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing National Research Center for Information Science and Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing National Research Center for Information Science and Technology, Beijing, China","institution_ids":["https://openalex.org/I4405271667","https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006236325","display_name":"Huimin Ma","orcid":"https://orcid.org/0000-0001-5383-5667","observed_orcids":["https://orcid.org/0000-0001-5383-5667"]},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]},{"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":"Huimin Ma","raw_affiliation_strings":["Tsinghua University, Beijing, China","University of Science and Technology Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075551339","display_name":"Hongbing Ma","orcid":"https://orcid.org/0000-0002-1785-4024","observed_orcids":["https://orcid.org/0000-0002-1785-4024"]},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]},{"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":"Hongbing Ma","raw_affiliation_strings":["Tsinghua University, Beijing, China","University of Science and Technology Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3081,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5924399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4818","last_page":"4822"},"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":0.0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":1.0},{"id":"https://openalex.org/keywords/semantic-tags","display_name":"semantic tags","score":0.984000027179718},{"id":"https://openalex.org/keywords/cross-attention","display_name":"cross-attention","score":0.8289999961853027},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.5889999866485596},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.5680000185966492},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.4020000100135803}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9558827877044678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8768106698989868},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8009083271026611},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6845313906669617},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.5830663442611694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5552951097488403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5007224082946777},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.4967573285102844},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.44692346453666687},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43122372031211853},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.165883868932724},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.0917728841304779},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3479228","doi":"https://doi.org/10.1145/3474085.3479228","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3479228","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4687123925","display_name":null,"funder_award_id":"No. Z191100007419001","funder_id":"https://openalex.org/F4320335843","funder_display_name":"Beijing Science and Technology Planning Project"},{"id":"https://openalex.org/G6114247317","display_name":null,"funder_award_id":"No.U20B2062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335843","display_name":"Beijing Science and Technology Planning Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2108598243","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/W2560313346","https://openalex.org/W2619082050","https://openalex.org/W2883831329","https://openalex.org/W2896457183","https://openalex.org/W2950019618","https://openalex.org/W2951390634","https://openalex.org/W2962990649","https://openalex.org/W2963177403","https://openalex.org/W2963753226","https://openalex.org/W2963971014","https://openalex.org/W2964121744","https://openalex.org/W2984862483","https://openalex.org/W3003478339","https://openalex.org/W3040468852","https://openalex.org/W3091588028","https://openalex.org/W3093309253","https://openalex.org/W3093309458","https://openalex.org/W3175095612","https://openalex.org/W4394659899"],"related_works":["https://openalex.org/W3096396720","https://openalex.org/W3093309458","https://openalex.org/W6948352262","https://openalex.org/W4387587644","https://openalex.org/W7161542402","https://openalex.org/W4226216917","https://openalex.org/W4386858402","https://openalex.org/W3193767255","https://openalex.org/W4382458743","https://openalex.org/W2962994439"],"abstract_inverted_index":{"The":[0,47,123],"key":[1],"of":[2,91,140],"video":[3,134],"captioning":[4,135],"is":[5],"to":[6,19,24,37,113],"leverage":[7,20],"the":[8,21,26,38,44,51,55,69,75,110,115,120,127,131,138,141],"cross-modal":[9,121],"information":[10],"from":[11],"both":[12],"vision":[13],"and":[14,40,54,93],"language":[15],"perspectives.":[16],"We":[17],"propose":[18],"semantic":[22,48,76,94,142],"tags":[23,49,53,57],"bridge":[25],"gap":[27],"between":[28],"these":[29],"modalities":[30],"rather":[31],"than":[32],"directly":[33],"concatenating":[34],"or":[35],"attending":[36],"visual":[39,92],"linguistic":[41],"features":[42,95],"as":[43,65],"previous":[45],"works.":[46],"are":[50,106],"object":[52],"action":[56],"detected":[58],"in":[59,109,130],"videos,":[60],"which":[61,87],"can":[62],"be":[63,147],"viewed":[64],"partial":[66],"captions":[67],"for":[68,133],"input":[70],"video.":[71],"To":[72],"effectively":[73],"exploit":[74],"tags,":[77],"we":[78],"design":[79],"a":[80],"Semantic":[81],"Tag":[82],"augmented":[83],"XlanV":[84],"(ST-XlanV)":[85],"model":[86,116,125],"encodes":[88],"4":[89],"kinds":[90],"with":[96,137],"X-Linear":[97],"Attention":[98],"based":[99],"cross-attention":[100],"modules.":[101],"Moreover,":[102],"tag":[103],"related":[104],"tasks":[105],"also":[107],"designed":[108],"pre-training":[111,132],"stage":[112],"aid":[114],"more":[117],"fruitfully":[118],"exploits":[119],"information.":[122],"proposed":[124],"reaches":[126],"5th":[128],"place":[129],"challenge":[136],"help":[139],"tags.":[143],"Our":[144],"codes":[145],"will":[146],"available":[148],"at:":[149],"https://github.com/RubickH/ST-XlanV.":[150]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-10-25T00:00:00"}