{"id":"https://openalex.org/W4406729002","doi":"https://doi.org/10.1109/tsmc.2024.3524682","title":"ATMNet: Adaptive Two-Stage Modular Network for Accurate Video Captioning","display_name":"ATMNet: Adaptive Two-Stage Modular Network for Accurate Video Captioning","publication_year":2025,"publication_date":"2025-01-22","ids":{"openalex":"https://openalex.org/W4406729002","doi":"https://doi.org/10.1109/tsmc.2024.3524682"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2024.3524682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3524682","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","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":"https://openalex.org/A5049469328","display_name":"Tianyang Xu","orcid":"https://orcid.org/0000-0002-9015-3128"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyang Xu","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-9015-3128","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077163680","display_name":"Yunjie Zhang","orcid":"https://orcid.org/0000-0002-0622-4326"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjie Zhang","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-0622-4326","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018880478","display_name":"Xiaoning Song","orcid":"https://orcid.org/0000-0002-3967-4497"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoning Song","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-3967-4497","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025299678","display_name":"Zhenhua Feng","orcid":"https://orcid.org/0000-0002-4485-4249"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Feng","raw_affiliation_strings":["Department of Computer Science, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-4485-4249","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087450445","display_name":"Xiao\u2010Jun Wu","orcid":"https://orcid.org/0000-0002-0310-5778"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Jun Wu","raw_affiliation_strings":["School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"],"raw_orcid":"https://orcid.org/0000-0002-0310-5778","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80110932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"55","issue":"4","first_page":"2821","last_page":"2833"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9990000128746033,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9990000128746033,"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/T11019","display_name":"Image Enhancement Techniques","score":0.996399998664856,"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":0.994700014591217,"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":0.9055547714233398},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.7799267768859863},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.7161486148834229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6942433714866638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2745838463306427},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08042415976524353},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.053132057189941406},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.052220702171325684}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9055547714233398},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7799267768859863},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.7161486148834229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6942433714866638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2745838463306427},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08042415976524353},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.053132057189941406},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.052220702171325684},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2024.3524682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3524682","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2070706591","display_name":null,"funder_award_id":"62332008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5081062661","display_name":null,"funder_award_id":"62020106012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5773036057","display_name":null,"funder_award_id":"62106089","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8443129088","display_name":null,"funder_award_id":"62336004","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1601567445","https://openalex.org/W1956340063","https://openalex.org/W2029258652","https://openalex.org/W2074790422","https://openalex.org/W2104657103","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2152984213","https://openalex.org/W2334573335","https://openalex.org/W2425121537","https://openalex.org/W2524701588","https://openalex.org/W2554906389","https://openalex.org/W2559044135","https://openalex.org/W2807913282","https://openalex.org/W2905145027","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2957634299","https://openalex.org/W2962681491","https://openalex.org/W2962990649","https://openalex.org/W2963177403","https://openalex.org/W2963351113","https://openalex.org/W2963563276","https://openalex.org/W2963971014","https://openalex.org/W2981873476","https://openalex.org/W2984862483","https://openalex.org/W3034221024","https://openalex.org/W3035237998","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3045610411","https://openalex.org/W3096609285","https://openalex.org/W3176425931","https://openalex.org/W3186621246","https://openalex.org/W3192261211","https://openalex.org/W3205021045","https://openalex.org/W3216659302","https://openalex.org/W4214692497","https://openalex.org/W4285600262","https://openalex.org/W4285606530","https://openalex.org/W4312463400","https://openalex.org/W4312614039","https://openalex.org/W4323767275","https://openalex.org/W4385245566","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6683258052","https://openalex.org/W6779786894","https://openalex.org/W6784761581","https://openalex.org/W6791353385","https://openalex.org/W6842542540","https://openalex.org/W6864544085","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562"],"abstract_inverted_index":{"In":[0,69,120],"recent":[1],"years,":[2],"pretrained":[3],"language-image":[4],"models":[5],"(PLIMs)":[6],"have":[7],"delivered":[8],"advances":[9],"in":[10],"video":[11,93,110],"captioning.":[12],"However,":[13],"existing":[14],"PLIMs":[15],"primarily":[16],"focus":[17],"on":[18,190],"extracting":[19],"global":[20],"feature":[21],"representations":[22],"from":[23,139],"still":[24],"images":[25],"and":[26,34,39,51,61,85,177],"text":[27,40],"sequences,":[28],"while":[29],"neglecting":[30],"fine-grained":[31],"semantic":[32,92],"alignment":[33,49,73],"temporal":[35,53,62,96,106,116],"variations":[36],"between":[37,64],"vision":[38],"pairs.":[41],"To":[42],"this":[43],"end,":[44],"we":[45],"propose":[46],"a":[47,52,100],"global-local":[48,72],"module":[50,55,74,98],"parsing":[54,97],"to":[56,89,129,162,205],"reflect":[57],"the":[58,65,71,82,86,114,131,140,158,163,171,180,183,195,198],"detailed":[59],"correspondence":[60],"perception":[63],"two":[66,79],"modalities,":[67],"respectively.":[68],"particular,":[70],"enables":[75],"cross-modal":[76],"registration":[77],"at":[78],"levels,":[80],"i.e.,":[81],"sentence-video":[83],"level":[84],"word-frame":[87],"level,":[88],"obtain":[90],"mixed-granularity":[91],"features.":[94],"The":[95,135,186],"is":[99,127,144],"dedicated":[101],"self-attention":[102],"structure":[103,126,167],"that":[104],"highlights":[105],"order":[107],"cues":[108],"along":[109],"frames,":[111],"compensating":[112],"for":[113,153,174],"limited":[115],"capacity":[117],"of":[118,156,182,197],"PLIMs.":[119],"addition,":[121],"an":[122,148],"adaptive":[123,149],"two-stage":[124],"gating":[125],"designed":[128],"leverage":[130],"linguistic":[132,136],"predictions":[133],"further.":[134],"information":[137,159],"derived":[138],"first":[141],"stage":[142],"prediction":[143,184],"dynamically":[145],"routed":[146],"through":[147],"decision":[150],"gate,":[151],"allowing":[152],"quality":[154],"assessment":[155],"whether":[157],"should":[160],"proceed":[161],"second":[164],"stage.":[165],"This":[166],"can":[168],"effectively":[169],"reduce":[170],"computational":[172],"burden":[173],"easy":[175],"samples":[176],"further":[178],"improve":[179],"accuracy":[181],"results.":[185],"experimental":[187],"results":[188],"obtained":[189],"several":[191],"benchmark":[192],"datasets":[193],"demonstrate":[194],"effectiveness":[196],"proposed":[199],"solution,":[200],"with":[201],"improved":[202],"performance":[203],"compared":[204],"state-of-the-art":[206],"methods.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}