{"id":"https://openalex.org/W7160255623","doi":"https://doi.org/10.1109/wacv61042.2026.00030","title":"TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors","display_name":"TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160255623","doi":"https://doi.org/10.1109/wacv61042.2026.00030"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5066429882","display_name":"Wei-Yuan Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Yuan Cheng","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101827449","display_name":"Kai-Po Chang","orcid":"https://orcid.org/0009-0008-5182-2019"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai-Po Chang","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104259508","display_name":"Chi-Pin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Pin Huang","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135347168","display_name":"Fu-En Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu-En Yang","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633632","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0098-5359"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Chiang Frank Wang","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50996815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9562000036239624,"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":0.9562000036239624,"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/T12031","display_name":"Speech and dialogue systems","score":0.00419999985024333,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8555999994277954},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3549000024795532},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.32659998536109924},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30730000138282776},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.27970001101493835}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8555999994277954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7167999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49939998984336853},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38370001316070557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3781999945640564},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.336899995803833},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W1956340063","https://openalex.org/W2222512263","https://openalex.org/W2952132648","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2968104955","https://openalex.org/W2997296614","https://openalex.org/W2997747012","https://openalex.org/W3047922786","https://openalex.org/W3096609285","https://openalex.org/W3097607319","https://openalex.org/W3178322352","https://openalex.org/W4214663214","https://openalex.org/W4386076661","https://openalex.org/W4386083024","https://openalex.org/W4386083094","https://openalex.org/W4390872764","https://openalex.org/W4390873341","https://openalex.org/W4390873423","https://openalex.org/W4402670231","https://openalex.org/W4402671548","https://openalex.org/W4402727272","https://openalex.org/W4402753774","https://openalex.org/W4402753824","https://openalex.org/W4402754238","https://openalex.org/W4403002096","https://openalex.org/W4403888320","https://openalex.org/W4404724811","https://openalex.org/W4404784276","https://openalex.org/W4409369885","https://openalex.org/W4413147769","https://openalex.org/W4415798265","https://openalex.org/W7108068597","https://openalex.org/W7133239970"],"related_works":[],"abstract_inverted_index":{"Dense":[0],"video":[1,30,79,148],"captioning":[2,149],"aims":[3],"to":[4,24,49,68,76,86,110],"interpret":[5],"and":[6,72,120,150,157],"describe":[7],"all":[8],"temporally":[9],"localized":[10],"events":[11,71,98,119],"throughout":[12],"an":[13,94,105],"input":[14],"video.":[15,126],"Recent":[16],"state-of-the-art":[17,141],"methods":[18],"leverage":[19],"large":[20],"language":[21],"models":[22],"(LLMs)":[23],"provide":[25],"detailed":[26],"moment":[27,155],"descriptions":[28],"for":[29],"data.":[31],"However,":[32],"existing":[33],"VideoLLMs":[34,62,75],"remain":[35],"challenging":[36],"in":[37,42,84],"identifying":[38],"precise":[39],"event":[40,80,106,112],"boundaries":[41],"untrimmed":[43],"videos,":[44],"causing":[45],"the":[46,74,89,124],"generated":[47],"captions":[48,113],"be":[50],"not":[51],"properly":[52,87],"grounded.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,103,133],"propose":[58],"TA-Prompting,":[59],"which":[60],"enhances":[61],"via":[63],"Temporal":[64],"Anchors":[65],"that":[66,135],"learn":[67],"precisely":[69],"localize":[70],"prompt":[73],"perform":[77],"temporal-aware":[78],"understanding.":[81],"During":[82],"inference,":[83],"order":[85],"determine":[88],"output":[90],"caption":[91],"sequence":[92],"from":[93],"arbitrary":[95],"number":[96],"of":[97],"presented":[99],"within":[100],"a":[101],"video,":[102],"introduce":[104],"coherent":[107],"sampling":[108],"strategy":[109],"select":[111],"with":[114,123],"sufficient":[115],"coherence":[116],"across":[117],"temporal":[118,151],"cross-modal":[121],"similarity":[122],"given":[125],"Through":[127],"extensive":[128],"experiments":[129],"on":[130,146],"benchmark":[131],"datasets,":[132],"show":[134],"our":[136],"TA-Prompting":[137],"is":[138],"favorable":[139],"against":[140],"VideoLLMs,":[142],"yielding":[143],"superior":[144],"performance":[145],"dense":[147],"understanding":[152],"tasks":[153],"including":[154],"retrieval":[156],"temporalQA.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}