{"id":"https://openalex.org/W4411635459","doi":"https://doi.org/10.1145/3731715.3733347","title":"From Skeleton to Flesh: Aggregated Relational Transformer Towards Controllable Video Captioning with Two-Step Decoding","display_name":"From Skeleton to Flesh: Aggregated Relational Transformer Towards Controllable Video Captioning with Two-Step Decoding","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635459","doi":"https://doi.org/10.1145/3731715.3733347"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733347","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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/A5022081570","display_name":"Qianwen Cao","orcid":"https://orcid.org/0000-0001-7491-5201"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianwen Cao","raw_affiliation_strings":["China University of Petroleum (Beijing), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7491-5201","affiliations":[{"raw_affiliation_string":"China University of Petroleum (Beijing), Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087631670","display_name":"Heyan Huang","orcid":"https://orcid.org/0000-0002-0320-7520"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heyan Huang","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0320-7520","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108924738","display_name":"Boran Wang","orcid":"https://orcid.org/0009-0001-1948-5154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boran Wang","raw_affiliation_strings":["Bytedance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-1948-5154","affiliations":[{"raw_affiliation_string":"Bytedance, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8273,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9059116,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"70"},"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":0.9995999932289124,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9947999715805054,"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/decoding-methods","display_name":"Decoding methods","score":0.7596842646598816},{"id":"https://openalex.org/keywords/flesh","display_name":"Flesh","score":0.7273211479187012},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6451998353004456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6323398351669312},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5762609243392944},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3684096932411194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3389604091644287},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15065473318099976},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14901036024093628},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11638584733009338},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07031583786010742},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06566229462623596},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0578078031539917}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7596842646598816},{"id":"https://openalex.org/C2776327621","wikidata":"https://www.wikidata.org/wiki/Q13119823","display_name":"Flesh","level":2,"score":0.7273211479187012},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6451998353004456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6323398351669312},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5762609243392944},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3684096932411194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3389604091644287},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15065473318099976},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14901036024093628},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11638584733009338},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07031583786010742},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06566229462623596},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0578078031539917},{"id":"https://openalex.org/C31903555","wikidata":"https://www.wikidata.org/wiki/Q1637030","display_name":"Food science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733347","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1123908660","display_name":null,"funder_award_id":"62402526","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G2290195763","display_name":null,"funder_award_id":"2462023YJRC029","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2097117768","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2883429621","https://openalex.org/W2905145027","https://openalex.org/W2951390634","https://openalex.org/W2962990649","https://openalex.org/W2963524571","https://openalex.org/W2964187781","https://openalex.org/W2984862483","https://openalex.org/W2989322838","https://openalex.org/W2997591391","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3081168214","https://openalex.org/W3091588028","https://openalex.org/W3170494780","https://openalex.org/W3176425931","https://openalex.org/W3176689360","https://openalex.org/W3216659302","https://openalex.org/W3217340782","https://openalex.org/W4214692497","https://openalex.org/W4299527668","https://openalex.org/W4309724203","https://openalex.org/W4312560592","https://openalex.org/W4362013208","https://openalex.org/W4378474069","https://openalex.org/W4386057717","https://openalex.org/W4388482029","https://openalex.org/W4390195594","https://openalex.org/W4391791458","https://openalex.org/W4391837206","https://openalex.org/W4393154592","https://openalex.org/W4394597628","https://openalex.org/W4394625850","https://openalex.org/W4396878071","https://openalex.org/W4400066924","https://openalex.org/W4400066978","https://openalex.org/W4400518679","https://openalex.org/W4401540757","https://openalex.org/W4401666710","https://openalex.org/W4402727512","https://openalex.org/W4402727824","https://openalex.org/W4402727885","https://openalex.org/W4402753874","https://openalex.org/W4402771391","https://openalex.org/W4402915865","https://openalex.org/W4402916396","https://openalex.org/W4402923149","https://openalex.org/W4403459022","https://openalex.org/W4403791860","https://openalex.org/W4403792529","https://openalex.org/W4404562753","https://openalex.org/W4406352507","https://openalex.org/W4406457518","https://openalex.org/W4407449399","https://openalex.org/W6600194071","https://openalex.org/W6858268588"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"is":[2,67,142,219],"the":[3,19,43,63,78,88,109,113,133,138,145,148,152,161,183,186,190,195,206],"task":[4],"of":[5,18,59,71,147,185,221],"automatically":[6],"producing":[7],"natural":[8],"language":[9],"descriptions":[10],"for":[11,36,74,129,189,215],"a":[12,56,68,118,157,175],"given":[13],"video.":[14],"The":[15],"great":[16],"success":[17],"Transformer":[20,123],"architecture":[21],"in":[22,112],"NLP":[23],"and":[24,94,116,159,212,218],"CV":[25],"has":[26],"inspired":[27],"recent":[28],"attempts":[29],"at":[30,84,194],"constructing":[31],"an":[32],"end-to-end":[33],"Transformer-based":[34,114],"model":[35],"video":[37,60,130,216],"captioning.":[38,131],"Although":[39],"achieving":[40],"impressive":[41],"performance,":[42],"one-step":[44],"framework":[45,115],"relies":[46],"on":[47,209],"brute":[48],"force":[49],"to":[50,100,125,164,224,226],"learn":[51],"highly":[52],"compressed":[53],"semantics":[54],"from":[55],"large":[57],"number":[58],"patches,":[61],"lacking":[62],"review":[64,91,110,162],"process,":[65],"which":[66],"common":[69],"behavior":[70],"human":[72],"beings":[73],"understanding":[75],"videos/papers/books.":[76],"Taking":[77],"rough":[79],"but":[80],"significant":[81],"impression":[82],"captured":[83],"first":[85],"sight":[86],"as":[87,98,144,156],"skeleton,":[89],"additional":[90],"can":[92,180],"verify":[93],"investigate":[95],"specific":[96],"information":[97],"flesh":[99],"deepen":[101],"precise":[102],"recognition.":[103],"In":[104],"this":[105],"work,":[106],"we":[107],"introduce":[108],"process":[111,163],"propose":[117],"novel":[119],"network,":[120],"Aggregated":[121],"Relational":[122],"(ART)":[124],"conduct":[126],"two-step":[127],"decoding":[128,197],"Since":[132],"relation":[134],"triplet":[135],"concisely":[136],"summarizes":[137],"main":[139],"structure,":[140],"it":[141],"assigned":[143],"objective":[146],"first-pass":[149],"decoding.":[150],"Then":[151],"relations":[153,179],"are":[154],"utilized":[155],"skeleton":[158],"guide":[160],"potentially":[165],"obtain":[166],"better":[167],"captions":[168,223],"by":[169],"looking":[170],"into":[171],"semantic":[172,228],"components":[173],"with":[174],"global":[176],"view,":[177],"where":[178],"also":[181],"play":[182],"role":[184],"prompt":[187],"signal":[188],"controllable":[191],"caption":[192],"generation":[193],"second":[196],"pass.":[198],"Extensive":[199],"experiments":[200],"show":[201],"that":[202],"our":[203],"method":[204],"achieves":[205],"SOTA":[207],"performance":[208],"MSVD,":[210],"MSRVTT,":[211],"VATEX":[213],"datasets":[214],"captioning,":[217],"capable":[220],"controlling":[222],"respond":[225],"different":[227],"contexts.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}