{"id":"https://openalex.org/W4400850904","doi":"https://doi.org/10.1145/3679203","title":"Action-aware Linguistic Skeleton Optimization Network for Non-autoregressive Video Captioning","display_name":"Action-aware Linguistic Skeleton Optimization Network for Non-autoregressive Video Captioning","publication_year":2024,"publication_date":"2024-07-20","ids":{"openalex":"https://openalex.org/W4400850904","doi":"https://doi.org/10.1145/3679203"},"language":"en","primary_location":{"id":"doi:10.1145/3679203","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3679203","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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":null,"display_name":"Shuqin Chen","orcid":"https://orcid.org/0000-0001-6449-5063"},"institutions":[{"id":"https://openalex.org/I4210154851","display_name":"Hubei University of Education","ror":"https://ror.org/04f41cb79","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210154851"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqin Chen","raw_affiliation_strings":["School of Computer Science and Hubei Provincial Collaborative Innovation Center for Basic Education Information Technology Services, Hubei University of Education, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6449-5063","affiliations":[{"raw_affiliation_string":"School of Computer Science and Hubei Provincial Collaborative Innovation Center for Basic Education Information Technology Services, Hubei University of Education, Wuhan, China","institution_ids":["https://openalex.org/I4210154851"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064738683","display_name":"Xian Zhong","orcid":"https://orcid.org/0000-0002-5242-0467"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Xian Zhong","raw_affiliation_strings":["Hubei Key Lab of Transportation Internet of Things, School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China and Rapid-Rich Object Search Lab, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5242-0467","affiliations":[{"raw_affiliation_string":"Hubei Key Lab of Transportation Internet of Things, School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China and Rapid-Rich Object Search Lab, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005","https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yi Zhang","orcid":"https://orcid.org/0009-0001-1050-163X"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0001-1050-163X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016081925","display_name":"Lei Zhu","orcid":"https://orcid.org/0000-0003-3871-663X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["ROAS Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-3871-663X","affiliations":[{"raw_affiliation_string":"ROAS Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435494","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-1503-0240"},"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":"Ping Li","raw_affiliation_strings":["Department of Computing and School of Design, The Hong Kong Polytechnic University, China"],"raw_orcid":"https://orcid.org/0000-0002-1503-0240","affiliations":[{"raw_affiliation_string":"Department of Computing and School of Design, The Hong Kong Polytechnic University, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019708391","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0000-0003-4029-3322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["MOE Key Laboratory of AI, School of Electronic, Information, and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4029-3322","affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of AI, School of Electronic, Information, and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009598072","display_name":"Bin Sheng","orcid":"https://orcid.org/0000-0001-8678-2784"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Sheng","raw_affiliation_strings":["Department of Computer Science and Engineering, School of Electronic, Information, and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8678-2784","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, School of Electronic, Information, and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2766,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.95853467,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"20","issue":"10","first_page":"1","last_page":"24"},"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":0.9993000030517578,"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":0.9848999977111816,"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":0.9138331413269043},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8440920114517212},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6131157279014587},{"id":"https://openalex.org/keywords/skeleton","display_name":"Skeleton (computer programming)","score":0.5555021166801453},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.49557483196258545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41976410150527954},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3854939341545105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3802972137928009},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3734707236289978},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1621379852294922},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10297048091888428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9138331413269043},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8440920114517212},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6131157279014587},{"id":"https://openalex.org/C18969341","wikidata":"https://www.wikidata.org/wiki/Q1169129","display_name":"Skeleton (computer programming)","level":2,"score":0.5555021166801453},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.49557483196258545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41976410150527954},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3854939341545105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3802972137928009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3734707236289978},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1621379852294922},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10297048091888428},{"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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3679203","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3679203","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-146453","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-146453","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G1285557638","display_name":null,"funder_award_id":"2023AFB206","funder_id":"https://openalex.org/F4320322186","funder_display_name":"Natural Science Foundation of Hubei Province"},{"id":"https://openalex.org/G1441895017","display_name":null,"funder_award_id":"WHUTIOT2023-006","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G1629549548","display_name":null,"funder_award_id":"62271361","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/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2142900973","https://openalex.org/W2154652894","https://openalex.org/W2425121537","https://openalex.org/W2890550430","https://openalex.org/W2952132648","https://openalex.org/W2953461088","https://openalex.org/W2962681491","https://openalex.org/W2962861647","https://openalex.org/W2962990649","https://openalex.org/W2963524571","https://openalex.org/W2963536265","https://openalex.org/W2963616706","https://openalex.org/W2963916161","https://openalex.org/W2964018924","https://openalex.org/W2964110616","https://openalex.org/W2988975212","https://openalex.org/W2989322838","https://openalex.org/W2996843693","https://openalex.org/W3003478339","https://openalex.org/W3009192917","https://openalex.org/W3034216012","https://openalex.org/W3034221024","https://openalex.org/W3034593503","https://openalex.org/W3035237998","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3039060838","https://openalex.org/W3093300941","https://openalex.org/W3093309253","https://openalex.org/W3096935578","https://openalex.org/W3111947517","https://openalex.org/W3115684750","https://openalex.org/W3134875898","https://openalex.org/W3164646408","https://openalex.org/W3166366124","https://openalex.org/W3174046981","https://openalex.org/W3175164646","https://openalex.org/W3176425931","https://openalex.org/W3176514808","https://openalex.org/W3192261211","https://openalex.org/W3193296307","https://openalex.org/W3205898187","https://openalex.org/W3207461616","https://openalex.org/W3209229003","https://openalex.org/W4210842488","https://openalex.org/W4214692497","https://openalex.org/W4220790454","https://openalex.org/W4226109438","https://openalex.org/W4281560470","https://openalex.org/W4283688199","https://openalex.org/W4284692156","https://openalex.org/W4286488082","https://openalex.org/W4293518015","https://openalex.org/W4312477797","https://openalex.org/W4322730941","https://openalex.org/W4366996284","https://openalex.org/W4382240304","https://openalex.org/W4382464395","https://openalex.org/W4387398391","https://openalex.org/W4390871964","https://openalex.org/W6682631176","https://openalex.org/W6754140808"],"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":{"Non-autoregressive":[0],"video":[1,63,82,91,116],"captioning":[2,117],"methods":[3,124,137],"generate":[4],"visual":[5,39],"words":[6],"in":[7,90],"parallel":[8],"but":[9],"often":[10],"overlook":[11],"semantic":[12,36,78],"correlations":[13,79],"among":[14,38],"them,":[15],"especially":[16],"regarding":[17],"verbs,":[18],"leading":[19],"to":[20,34,76,85,134],"lower":[21],"caption":[22,99],"quality.":[23],"To":[24],"address":[25,95],"this,":[26],"we":[27],"integrate":[28],"action":[29,54,83],"information":[30,55],"of":[31,52,60,97,108],"highlighted":[32],"objects":[33],"enhance":[35,86],"connections":[37],"words.":[40],"Our":[41],"proposed":[42],"Action-aware":[43],"Language":[44],"Skeleton":[45],"Optimization":[46],"Network":[47],"(ALSO-Net)":[48],"tackles":[49],"the":[50],"challenge":[51],"extracting":[53],"across":[56],"frames,":[57],"improving":[58],"understanding":[59],"complex":[61],"context-dependent":[62],"actions":[64],"and":[65,80,101,129,142],"reducing":[66],"sentence":[67],"inconsistencies.":[68],"ALSO-Net":[69,121],"incorporates":[70],"a":[71,81,126],"linguistic":[72],"skeleton":[73],"tag":[74],"generator":[75],"refine":[77],"predictor":[84],"verb":[87],"prediction":[88,110],"accuracy":[89],"captions.":[92],"We":[93],"also":[94],"issues":[96],"unsatisfactory":[98],"length":[100],"quality":[102],"by":[103,125],"jointly":[104],"optimizing":[105],"different":[106],"levels":[107],"motion":[109],"loss.":[111],"Experimental":[112],"evaluation":[113],"on":[114],"prominent":[115],"datasets":[118],"demonstrates":[119],"that":[120],"outperforms":[122],"baseline":[123],"significant":[127],"margin":[128],"achieves":[130],"competitive":[131],"performance":[132],"compared":[133],"state-of-the-art":[135],"autoregressive":[136],"with":[138],"smaller":[139],"model":[140],"complexity":[141],"faster":[143],"inference":[144],"time.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
