{"id":"https://openalex.org/W7138171391","doi":"https://doi.org/10.1609/aaai.v40i16.38355","title":"OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward","display_name":"OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138171391","doi":"https://doi.org/10.1609/aaai.v40i16.38355"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i16.38355","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38355","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38355/42317","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38355/42317","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078020939","display_name":"Chunlin Zhong","orcid":"https://orcid.org/0009-0006-7070-3504"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Zhong","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129727242","display_name":"Qiuxia Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129149","display_name":"Postmaster Psychologie Opleidingen","ror":"https://ror.org/03naar428","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210129149"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Qiuxia Hou","raw_affiliation_strings":["Oppo AI center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oppo AI center","institution_ids":["https://openalex.org/I4210129149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129750757","display_name":"Zhangjun Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangjun Zhou","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129697102","display_name":"Yanhao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129149","display_name":"Postmaster Psychologie Opleidingen","ror":"https://ror.org/03naar428","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210129149"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yanhao Zhang","raw_affiliation_strings":["Oppo AI center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oppo AI center","institution_ids":["https://openalex.org/I4210129149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129644334","display_name":"Shuang Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Hao","raw_affiliation_strings":["Huazhong University of Science and Technology,\nXi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,\nXi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129693160","display_name":"Haonan Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129149","display_name":"Postmaster Psychologie Opleidingen","ror":"https://ror.org/03naar428","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210129149"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Haonan Lu","raw_affiliation_strings":["Oppo AI center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oppo AI center","institution_ids":["https://openalex.org/I4210129149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129749369","display_name":"He Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Tang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129648730","display_name":"Xiang Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bai","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"16","first_page":"13503","last_page":"13511"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9692999720573425,"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":0.9692999720573425,"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":0.007199999876320362,"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":0.006300000008195639,"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":0.9488000273704529},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5979999899864197},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5842999815940857},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.5690000057220459},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5428000092506409},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5390999913215637},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.38519999384880066}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9488000273704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922999858856201},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5979999899864197},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.5690000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5508999824523926},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32190001010894775},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C22561748","wikidata":"https://www.wikidata.org/wiki/Q854954","display_name":"Videoconferencing","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i16.38355","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38355","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38355/42317","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38355","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38355","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38355","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38355/42317","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.42941686511039734,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4189157326","display_name":null,"funder_award_id":"62225603","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138171391.pdf","grobid_xml":"https://content.openalex.org/works/W7138171391.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"captioning":[1,146],"aims":[2],"to":[3,14,34,52,164],"generate":[4],"comprehensive":[5],"and":[6,21,60,90,115,121,126,135,175],"coherent":[7],"descriptions":[8],"of":[9,17,55],"the":[10,15,40,77,99,131,170,176],"video":[11,19,58,145],"content,":[12],"contributing":[13],"advancement":[16],"both":[18,119],"understanding":[20,59],"generation.":[22,61],"However,":[23],"existing":[24],"methods":[25],"often":[26],"suffer":[27],"from":[28,69],"motion-detail":[29,153],"imbalance,":[30],"as":[31],"models":[32,166],"tend":[33],"overemphasize":[35],"one":[36],"aspect":[37],"while":[38],"neglecting":[39],"other.":[41],"This":[42],"imbalance":[43],"results":[44,156],"in":[45,49,57,117],"incomplete":[46],"captions,":[47],"which":[48],"turn":[50],"leads":[51],"a":[53,84,143],"lack":[54],"consistency":[56],"To":[62],"address":[63],"this":[64],"issue,":[65],"we":[66,140],"propose":[67],"solutions":[68],"two":[70,168],"aspects:":[71],"1)":[72],"Data":[73],"aspect:":[74,96],"We":[75,97],"constructed":[76],"Harmonizing":[78],"Motion-Detail":[79,87],"270K":[80],"(HMD-270K)":[81],"dataset":[82],"through":[83,123],"two-stage":[85],"pipeline:":[86],"Fusion":[88],"(MDF)":[89],"Fine-Grained":[91],"Examination":[92],"(FGE).":[93],"2)":[94],"Optimization":[95,110],"introduce":[98],"Caption":[100],"Set":[101],"Equivalence":[102],"Reward":[103],"(CSER)":[104],"based":[105],"on":[106,130,167],"Group":[107],"Relative":[108],"Policy":[109],"(GRPO).":[111],"CSER":[112],"enhances":[113],"completeness":[114],"accuracy":[116],"capturing":[118],"motion":[120],"details":[122],"unit-to-set":[124],"matching":[125],"bidirectional":[127],"validation.":[128],"Based":[129],"HMD-270K":[132],"supervised":[133],"fine-tuning":[134],"GRPO":[136],"post-training":[137],"with":[138,152],"CSER,":[139],"developed":[141],"OwlCap,":[142],"powerful":[144],"Multi-modal":[147],"Large":[148],"Language":[149],"Model":[150],"(MLLM)":[151],"balance.":[154],"Experimental":[155],"demonstrate":[157],"that":[158],"OwlCap":[159],"achieves":[160],"significant":[161],"improvements":[162],"compared":[163],"baseline":[165],"benchmarks:":[169],"detail-focused":[171],"VDC":[172],"(+4.2":[173],"Acc)":[174],"motion-focused":[177],"DREAM-1K":[178],"(+4.6":[179],"F1).":[180]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}