{"id":"https://openalex.org/W7118310634","doi":"https://doi.org/10.1109/tmm.2026.3651095","title":"Natural Cognizing Video: A Decoupling and Integration Network for General Event Boundary Captioning","display_name":"Natural Cognizing Video: A Decoupling and Integration Network for General Event Boundary Captioning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7118310634","doi":"https://doi.org/10.1109/tmm.2026.3651095"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651095","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5122211984","display_name":"Yutao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutao Liu","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8049-0163","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071889746","display_name":"Wanru Xu","orcid":"https://orcid.org/0000-0003-2206-5051"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanru Xu","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2206-5051","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122158687","display_name":"Zhenjiang Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjiang Miao","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8032-5769","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122216614","display_name":"Kaijie Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaijie Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120131964","display_name":"Wangsheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangsheng He","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049471423","display_name":"Ruiying Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiying Yao","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02912646,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"3313","last_page":"3327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6434000134468079,"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":0.6434000134468079,"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":0.07670000195503235,"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":0.047200001776218414,"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":0.8841999769210815},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5788000226020813},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.554099977016449},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4968000054359436},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42419999837875366},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41119998693466187},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4050999879837036},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.3928999900817871}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8841999769210815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8529999852180481},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5788000226020813},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.554099977016449},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4893999993801117},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42419999837875366},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37869998812675476},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25270000100135803},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651095","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1594688182","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u7f51\u7edc\u7684\u540c\u7c7b\u6848\u4f8b\u533b\u5b66\u56fe\u50cf\u8de8\u6a21\u6001\u591a\u6807\u7b7e\u7ba1\u7406\u548c\u591a\u6a21\u5f0f\u68c0\u7d22\u7814\u7a76","funder_award_id":"61971446","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G199262001","display_name":null,"funder_award_id":"2024JBMC003","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2514987004","display_name":null,"funder_award_id":"L231012","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G3532120079","display_name":null,"funder_award_id":"202400550M5002","funder_id":"https://openalex.org/F4320327472","funder_display_name":"Chinese Aeronautical Establishment"},{"id":"https://openalex.org/G638245565","display_name":null,"funder_award_id":"MMC202401","funder_id":"https://openalex.org/F4320321435","funder_display_name":"Anhui University"},{"id":"https://openalex.org/G6946996161","display_name":null,"funder_award_id":"2023Z0710M5001","funder_id":"https://openalex.org/F4320327472","funder_display_name":"Chinese Aeronautical Establishment"},{"id":"https://openalex.org/G7593126260","display_name":null,"funder_award_id":"62576028","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7853727141","display_name":null,"funder_award_id":"62006015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8212755626","display_name":null,"funder_award_id":"4242028","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321435","display_name":"Anhui University","ror":"https://ror.org/05th6yx34"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320327472","display_name":"Chinese Aeronautical Establishment","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":31,"referenced_works":["https://openalex.org/W2425121537","https://openalex.org/W2739107216","https://openalex.org/W2794144851","https://openalex.org/W2883891001","https://openalex.org/W2887712318","https://openalex.org/W2889418103","https://openalex.org/W2945223572","https://openalex.org/W2969844053","https://openalex.org/W3019301826","https://openalex.org/W3034464851","https://openalex.org/W3034815696","https://openalex.org/W3035365026","https://openalex.org/W3036900224","https://openalex.org/W3047922786","https://openalex.org/W3134875898","https://openalex.org/W3216659302","https://openalex.org/W3217340782","https://openalex.org/W4214663214","https://openalex.org/W4220790454","https://openalex.org/W4226396383","https://openalex.org/W4313152851","https://openalex.org/W4377235499","https://openalex.org/W4382464395","https://openalex.org/W4384161812","https://openalex.org/W4386057717","https://openalex.org/W4386066385","https://openalex.org/W4386108345","https://openalex.org/W4387934928","https://openalex.org/W4389161308","https://openalex.org/W4389524555","https://openalex.org/W4396878071"],"related_works":[],"abstract_inverted_index":{"Video":[0,146],"captioning":[1,41],"is":[2,44,108,122,137,158,217,255],"a":[3,31,50,70,78,90,125,145,165],"prominent":[4],"and":[5,34,89,105,112,116,149,155,220],"challenging":[6],"research":[7],"area.":[8],"Previous":[9],"studies":[10],"have":[11],"focused":[12],"predominantly":[13],"on":[14,59,245],"describing":[15,80,92],"entire":[16],"video":[17,51,67],"segments,":[18],"often":[19],"overlooking":[20],"the":[21,47,73,81,85,93,96,131,134,140,150,153,161,169,179,185,193,196,202,208,214,221,227,232,246],"more":[22],"significant":[23],"status":[24,55,86,97],"changes":[25],"within":[26],"these":[27],"segments.":[28],"We":[29],"propose":[30],"novel":[32],"decoupling":[33,111],"integration":[35],"network":[36],"for":[37,65,72,110,168],"general":[38],"event":[39,82,94,162,186,228],"boundary":[40],"(DIN-GEBC),":[42],"which":[43,130,201],"applied":[45,225],"to":[46,84,183,212,226,230],"Kinetics-GEBC":[48,247],"dataset,":[49],"dataset":[52,248],"with":[53,124,144,164,250],"fine-grained":[54],"descriptions.":[56],"DIN-GEBC":[57,107,121,177],"focuses":[58,104],"generating":[60],"three":[61],"types":[62],"of":[63,133,152],"captions":[64,157],"each":[66],"segment":[68],"boundary:":[69],"caption":[71,79,91,136],"dominant":[74,141,180,209],"subject":[75,135,142,181,194,210],"(subject":[76],"caption),":[77],"prior":[83],"moment":[87,98],"(status-before),":[88],"after":[95],"(status-after).":[99],"To":[100],"address":[101],"different":[102],"descriptive":[103],"characteristics,":[106],"proposed":[109],"integrating":[113],"both":[114],"tasks":[115],"features.":[117],"For":[118,174],"task":[119,175],"decoupling,":[120],"designed":[123],"dual":[126],"branch":[127,143,163,182,187,211,229],"structure,":[128],"in":[129,188,200],"generation":[132,151],"addressed":[138,159],"by":[139,160,207],"Q-former":[147],"encoder":[148],"status-before":[154],"status-after":[156],"Reinventing":[166],"RNNs":[167],"Transformer":[170],"Era":[171],"(RWKV)":[172],"encoder.":[173],"integration,":[176],"enables":[178],"guide":[184],"producing":[189],"detailed":[190],"information":[191],"regarding":[192],"experiencing":[195],"change.":[197],"Feature":[198],"disentanglement,":[199],"common":[203],"features":[204,223],"are":[205,224],"used":[206],"capture":[213,231],"unchanging":[215],"information,":[216],"also":[218],"performed,":[219],"difference":[222],"changing":[233],"information.":[234],"The":[235,253],"experimental":[236],"results":[237],"show":[238],"that":[239],"our":[240],"model":[241],"outperforms":[242],"existing":[243],"models":[244],"even":[249],"fewer":[251],"parameters.":[252],"code":[254],"available":[256],"athttps://github.com/Mrliu001219/DIN-GEBC.":[257]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-01-08T00:00:00"}
