{"id":"https://openalex.org/W4415538346","doi":"https://doi.org/10.1145/3746027.3762060","title":"CMA-VC: Large Vision-Language Model for Cross-Modal Alignment in Intention-Oriented Video Captioning","display_name":"CMA-VC: Large Vision-Language Model for Cross-Modal Alignment in Intention-Oriented Video Captioning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538346","doi":"https://doi.org/10.1145/3746027.3762060"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762060","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762060","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":"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/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"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":"Jun Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3197-8103","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/A5032096290","display_name":"Xilong Lu","orcid":"https://orcid.org/0009-0002-4655-6517"},"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":"Xilong Lu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0002-4655-6517","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/A5090623425","display_name":"Yunxiang Zhang","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":"Yunxiang Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-1980-7859","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007719477","display_name":"Qiang Ling","orcid":"https://orcid.org/0000-0001-5688-4130"},"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":"Qiang Ling","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5688-4130","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32767114,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13830","last_page":"13836"},"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":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.992900013923645,"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":0.8744000196456909},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5503000020980835},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5385000109672546},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5314000248908997},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41449999809265137},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3684000074863434},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3671000003814697},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.3555999994277954}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8744000196456909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184000253677368},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5503000020980835},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4246000051498413},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40720000863075256},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2935999929904938},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762060","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762060","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2891033863","https://openalex.org/W2963177403","https://openalex.org/W2963184176","https://openalex.org/W2963524571","https://openalex.org/W4280589619","https://openalex.org/W4312910992","https://openalex.org/W4321605134","https://openalex.org/W4386071957"],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"video":[1,32,56,176,187],"captioning":[2,33],"methods":[3],"often":[4],"produce":[5],"generic":[6],"descriptions":[7],"that":[8],"fail":[9],"to":[10,73,156],"align":[11],"with":[12,70,96],"specific":[13],"user":[14],"intentions,":[15],"limiting":[16],"their":[17],"applicability":[18],"in":[19,92,179],"scenarios":[20],"requiring":[21],"customized":[22],"information":[23],"extraction.":[24],"This":[25,159],"paper":[26],"proposes":[27],"a":[28,62],"novel":[29],"intention-oriented":[30],"controllable":[31],"approach,":[34],"which":[35],"leverages":[36],"large-scale":[37],"vision-language":[38],"models":[39],"(InternViT":[40],"and":[41,43,58,76,109,119,125,131,146,185],"InternLM)":[42],"achieves":[44],"parameter-efficient":[45],"fine-tuning":[46],"through":[47],"Low-Rank":[48],"Adaptation":[49],"(LoRA).":[50],"The":[51],"proposed":[52,90],"framework":[53],"processes":[54],"both":[55],"content":[57],"user-specified":[59],"intentions":[60],"via":[61],"unified":[63],"cross-modal":[64],"pipeline,":[65],"dynamically":[66],"aligning":[67],"visual":[68],"features":[69],"intent":[71],"semantics":[72],"generate":[74],"focused":[75],"contextually":[77],"accurate":[78],"captions.":[79],"Experiments":[80],"on":[81,104,111,144],"the":[82,86,89,97,105,112,137,152,162,172],"IntentVC":[83],"dataset":[84],"validate":[85],"effectiveness":[87,139],"of":[88,140,154,175],"method":[91],"generating":[93],"intention-aligned":[94],"captions,":[95],"following":[98],"performance":[99,155],"metrics:":[100],"BLEU@4":[101],"scores":[102,117,123,129],"44.38":[103],"public":[106],"test":[107,114],"set":[108],"40.21":[110],"private":[113],"set;":[115],"METEOR":[116],"63.79":[118],"60.07":[120],"respectively;":[121,127],"CIDEr":[122],"230.33":[124],"208.15":[126],"ROUGE-L":[128],"61.75":[130],"57.14":[132],"respectively.":[133],"Ablation":[134],"studies":[135],"confirm":[136],"significant":[138],"joint":[141],"LoRA":[142,157],"adaptation":[143],"vision":[145],"language":[147],"modules,":[148],"as":[149,151,182],"well":[150],"sensitivity":[153],"parameters.":[158],"work":[160],"advances":[161],"field":[163],"by":[164],"enabling":[165],"precise":[166],"control":[167],"over":[168],"caption":[169],"generation,":[170],"enhancing":[171],"practical":[173],"utility":[174],"understanding":[177],"systems":[178],"applications":[180],"such":[181],"accessibility":[183],"services":[184],"targeted":[186],"retrieval.":[188]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}
