{"id":"https://openalex.org/W4415538746","doi":"https://doi.org/10.1145/3746027.3754990","title":"Decoupling Dense Video Captioning via Task-specific Prompts","display_name":"Decoupling Dense Video Captioning via Task-specific Prompts","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538746","doi":"https://doi.org/10.1145/3746027.3754990"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754990","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5103176295","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-2035-9737"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Chen","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053316728","display_name":"Jianwei Niu","orcid":"https://orcid.org/0000-0003-3946-5107"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwei Niu","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China and Zhongguancun Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China and Zhongguancun Laboratory, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400563","display_name":"Xuefeng Liu","orcid":"https://orcid.org/0000-0003-2705-8731"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Liu","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China and Zhongguancun Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China and Zhongguancun Laboratory, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085775609","display_name":"Xinghao Wu","orcid":"https://orcid.org/0000-0002-6987-3972"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghao Wu","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103176295"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29771178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3124","last_page":"3132"},"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":0.9976999759674072,"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":0.9907000064849854,"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":0.8356000185012817},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7264999747276306},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6237000226974487},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.49900001287460327},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4505000114440918},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3695000112056732}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8356000185012817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348000049591064},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7264999747276306},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6237000226974487},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4837000072002411},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4505000114440918},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754990","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1852338498","display_name":null,"funder_award_id":"2023YFB4503700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G1908610643","display_name":null,"funder_award_id":"62372027, 62372028","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2952132648","https://openalex.org/W2963351113","https://openalex.org/W2963916161","https://openalex.org/W2997296614","https://openalex.org/W3047922786","https://openalex.org/W3198377975","https://openalex.org/W4214663214","https://openalex.org/W4312310776","https://openalex.org/W4312651322","https://openalex.org/W4385800687","https://openalex.org/W4386065689","https://openalex.org/W4386066385","https://openalex.org/W4386071547","https://openalex.org/W4390874575","https://openalex.org/W4402726946","https://openalex.org/W4402780073"],"related_works":[],"abstract_inverted_index":{"Dense":[0],"video":[1,181],"captioning":[2,73],"aims":[3],"to":[4,35,83,89,111,120,136,161,177,179,187],"generate":[5],"descriptive":[6],"sentences":[7],"for":[8,59,168],"each":[9,60,117,169,175],"temporally":[10],"localized":[11],"event":[12,21,24,57,61,69,72,84,86,97,205,208],"in":[13,39],"a":[14,30,55,63,78,148],"video.":[15,79],"This":[16,153],"task":[17],"comprises":[18],"two":[19,130,156],"subtasks:":[20],"detection":[22,70,87,206],"and":[23,52,71,207],"captioning.":[25,209],"Existing":[26],"methods":[27,42],"commonly":[28],"adopt":[29],"DETR-like":[31],"(Detection":[32],"Transformer)":[33],"architecture":[34],"perform":[36],"both":[37,45,204],"subtasks":[38,46,131],"parallel.":[40],"These":[41,171],"assume":[43],"that":[44,68,183],"require":[47],"the":[48,93,106,109,113,129,180],"same":[49],"visual":[50],"information":[51],"thus":[53],"extract":[54],"single":[56],"representation":[58],"using":[62],"shared":[64,102,163],"query.":[65],"We":[66],"observe":[67],"emphasize":[74],"different":[75],"regions":[76,95,182],"of":[77,96,108,116,142,158],"In":[80,123],"particular,":[81],"compared":[82],"captioning,":[85],"tends":[88],"focus":[90],"more":[91,139],"on":[92,101,203],"boundary":[94],"proposals.":[98],"Therefore,":[99],"relying":[100],"queries":[103,135,164,166,173],"may":[104],"hinder":[105],"ability":[107],"model":[110],"meet":[112],"specific":[114],"needs":[115],"subtask,":[118],"leading":[119],"suboptimal":[121],"performance.":[122],"this":[124],"paper,":[125],"we":[126,146,199],"propose":[127],"decoupling":[128],"by":[132],"assigning":[133],"distinct":[134],"each,":[137],"enabling":[138],"accurate":[140],"capture":[141],"task-specific":[143,149,159,172],"features.":[144],"Specifically,":[145],"introduce":[147],"query":[150],"transformation":[151],"module.":[152],"module":[154],"utilizes":[155],"sets":[157],"prompts":[160],"transform":[162],"into":[165,195],"tailored":[167],"subtask.":[170],"enable":[174],"subtask":[176],"attend":[178],"are":[184],"most":[185],"beneficial":[186],"its":[188],"respective":[189],"objectives.":[190],"By":[191],"integrating":[192],"our":[193],"method":[194],"several":[196],"state-of-the-art":[197],"frameworks,":[198],"achieve":[200],"superior":[201],"performance":[202]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}
