{"id":"https://openalex.org/W4415537838","doi":"https://doi.org/10.1145/3746027.3762059","title":"IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning","display_name":"IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537838","doi":"https://doi.org/10.1145/3746027.3762059"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762059","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/A5102617416","display_name":"Tianheng Qiu","orcid":"https://orcid.org/0009-0005-6793-7628"},"institutions":[{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianheng Qiu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China and Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-6793-7628","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China and Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I2802624667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111488600","display_name":"J. Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingchun Gao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-5273-8212","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107953382","display_name":"Jingyu Li","orcid":"https://orcid.org/0000-0002-9561-7550"},"institutions":[{"id":"https://openalex.org/I4210137491","display_name":"National Science Centre","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"government","lineage":["https://openalex.org/I4210137491"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jingyu Li","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China and State Key Lab. for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9561-7550","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China and State Key Lab. for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I4210137491"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huiyi Leong","orcid":"https://orcid.org/0009-0005-7274-0811"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiyi Leong","raw_affiliation_strings":["University of Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0009-0005-7274-0811","affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004449189","display_name":"Xuan Huang","orcid":"https://orcid.org/0000-0001-5747-3341"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2802624667","display_name":"Hefei Institutes of Physical Science","ror":"https://ror.org/046n57345","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Huang","raw_affiliation_strings":["Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5747-3341","affiliations":[{"raw_affiliation_string":"Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I2802624667","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xi Wang","orcid":"https://orcid.org/0009-0005-7668-3965"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0005-7668-3965","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaocheng Zhang","orcid":"https://orcid.org/0009-0001-4864-2008"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaocheng Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0001-4864-2008","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-5997-5169","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100322320","display_name":"Lan Zhang","orcid":"https://orcid.org/0000-0003-1004-8588"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-1004-8588","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5102617416"],"corresponding_institution_ids":["https://openalex.org/I2802624667"],"apc_list":null,"apc_paid":null,"fwci":1.1332,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83514539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"13822","last_page":"13829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9983000159263611,"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":0.9857000112533569,"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":0.8726999759674072},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6358000040054321},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.47119998931884766},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4523000121116638},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4429999887943268},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4422000050544739},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.3889999985694885},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.3824000060558319},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.36500000953674316}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8726999759674072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331999778747559},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6358000040054321},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4429999887943268},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41429999470710754},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3824000060558319},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37560001015663147},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762059","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/G1867529467","display_name":null,"funder_award_id":"2025M771515","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2596543464","https://openalex.org/W2948358897","https://openalex.org/W2981851019","https://openalex.org/W2984862483","https://openalex.org/W3174770825","https://openalex.org/W3217340782","https://openalex.org/W4285200050","https://openalex.org/W4387969035","https://openalex.org/W4390871765","https://openalex.org/W4390873054","https://openalex.org/W4391454521","https://openalex.org/W4403792461"],"related_works":[],"abstract_inverted_index":{"Intent-oriented":[0],"controlled":[1,195],"video":[2,14,130,186],"captioning":[3],"aims":[4],"to":[5,50,61,69,95,115,118,181,192],"generate":[6,194],"targeted":[7],"descriptions":[8],"for":[9],"specific":[10],"targets":[11],"in":[12,40,55,58,74,93,146,185,204,213],"a":[13,81,110,135,157],"based":[15],"on":[16,221],"customized":[17],"user":[18,127,162],"intent.":[19,163],"Current":[20],"Large":[21],"Visual":[22],"Language":[23],"Models":[24],"(LVLMs)":[25],"have":[26],"gained":[27],"strong":[28],"instruction":[29],"following":[30],"and":[31,42,88,103,129,188,209],"visual":[32,149,154],"comprehension":[33],"capabilities.":[34],"Although":[35],"the":[36,86,97,120,142,147,153,161,169,172,178,190,211,214],"LVLMs":[37,94,191,208],"demonstrated":[38],"proficiency":[39],"spatial":[41,53,89,183],"temporal":[43,87],"understanding":[44,90],"respectively,":[45],"it":[46],"was":[47,210],"not":[48],"able":[49],"perform":[51],"fine-grained":[52,71],"control":[54,73],"time":[56],"sequences":[57],"direct":[59],"response":[60],"instructions.":[62],"This":[63],"substantial":[64],"spatio-temporal":[65,98],"gap":[66,99],"complicates":[67],"efforts":[68],"achieve":[70],"intention-oriented":[72],"video.":[75],"Towards":[76],"this":[77],"end,":[78],"we":[79,107],"propose":[80,109,134],"novel":[82],"IntentVCNet":[83],"that":[84,125,140,152,168],"unifies":[85],"knowledge":[91],"inherent":[92],"bridge":[96],"from":[100],"both":[101],"prompting":[102],"model":[104,119,182],"perspectives.":[105],"Specifically,":[106],"first":[108],"prompt":[111],"combination":[112,170],"strategy":[113],"designed":[114],"enable":[116],"LLM":[117],"implicit":[121],"relationship":[122],"between":[123],"prompts":[124],"characterize":[126],"intent":[128],"sequences.":[131],"We":[132],"then":[133],"parameter":[136],"efficient":[137],"box":[138],"adapter":[139],"augments":[141],"object":[143],"semantic":[144],"information":[145,159],"global":[148],"context":[150],"so":[151],"token":[155],"has":[156],"priori":[158],"about":[160],"The":[164],"final":[165],"experiment":[166],"proves":[167],"of":[171],"two":[173],"strategies":[174],"can":[175],"further":[176],"enhance":[177],"LVLM's":[179],"ability":[180],"details":[184],"sequences,":[187],"facilitate":[189],"accurately":[193],"intent-oriented":[196],"captions.":[197],"Our":[198,217],"proposed":[199],"method":[200],"achieved":[201],"state-of-the-art":[202],"results":[203],"several":[205],"open":[206],"source":[207],"runner-up":[212],"IntentVC":[215],"challenge.":[216],"code":[218],"is":[219],"available":[220],"https://github.com/thqiu0419/IntentVCNet.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}
