{"id":"https://openalex.org/W4415536450","doi":"https://doi.org/10.1145/3746027.3755837","title":"ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models","display_name":"ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536450","doi":"https://doi.org/10.1145/3746027.3755837"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755837","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755837","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":null,"display_name":"Yongheng Zhang","orcid":"https://orcid.org/0009-0004-2493-2950"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongheng Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, ChangSha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0004-2493-2950","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, ChangSha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu Liu","orcid":"https://orcid.org/0009-0008-6255-091X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, ChangSha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0008-6255-091X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, ChangSha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruihan Tao","orcid":"https://orcid.org/0009-0002-1824-4540"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihan Tao","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, ChangSha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0002-1824-4540","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, ChangSha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103207823","display_name":"Qiguang Chen","orcid":"https://orcid.org/0000-0002-9154-7858"},"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"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiguang Chen","raw_affiliation_strings":["Research Center for SCIR, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":"https://orcid.org/0000-0002-9154-7858","affiliations":[{"raw_affiliation_string":"Research Center for SCIR, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Fei","orcid":"https://orcid.org/0000-0003-3026-6347"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hao Fei","raw_affiliation_strings":["NExT Research Center, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3026-6347","affiliations":[{"raw_affiliation_string":"NExT Research Center, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019108029","display_name":"Wanxiang Che","orcid":"https://orcid.org/0000-0002-3907-0335"},"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"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanxiang Che","raw_affiliation_strings":["Research Center for SCIR, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":"https://orcid.org/0000-0002-3907-0335","affiliations":[{"raw_affiliation_string":"Research Center for SCIR, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029082837","display_name":"Libo Qin","orcid":"https://orcid.org/0000-0002-3619-675X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Qin","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, ChangSha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0002-3619-675X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, ChangSha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5267","last_page":"5276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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":0.9966999888420105,"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/boosting","display_name":"Boosting (machine learning)","score":0.5274999737739563},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5037999749183655},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4494999945163727},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.42399999499320984},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4178999960422516},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3991999924182892},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3849000036716461},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3617999851703644},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3465999960899353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012999892234802},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5266000032424927},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32170000672340393},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755837","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755837","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/G1745745304","display_name":null,"funder_award_id":"62306342, 62236004, 62206078, and 62476073","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2128951574","https://openalex.org/W4386066385","https://openalex.org/W4386076314","https://openalex.org/W4395470960","https://openalex.org/W4401362547","https://openalex.org/W4402582789","https://openalex.org/W4402671548"],"related_works":[],"abstract_inverted_index":{"Video":[0],"understanding":[1,138],"plays":[2],"a":[3,86],"vital":[4],"role":[5],"in":[6,66,135,161],"bridging":[7],"low-level":[8],"visual":[9,64,77],"signals":[10],"with":[11],"high-level":[12],"cognitive":[13],"reasoning,":[14,61],"and":[15,26,99,122,155],"is":[16,115],"fundamental":[17],"to":[18,149],"applications":[19],"such":[20],"as":[21],"autonomous":[22],"driving,":[23],"embodied":[24],"AI,":[25],"the":[27,63,67,104,109,129,132,136,150],"broader":[28],"pursuit":[29],"of":[30,35,131],"AGI.":[31],"The":[32],"rapid":[33],"development":[34],"large":[36],"language":[37],"models":[38],"(LLMs),":[39],"particularly":[40],"those":[41],"utilizing":[42],"Chain-of-Thought":[43],"(CoT)":[44],"technology,":[45],"has":[46],"significantly":[47,145],"advanced":[48],"video":[49,69,88,137],"reasoning":[50,70,89],"capabilities.":[51],"However,":[52],"current":[53],"approaches":[54],"primarily":[55],"depend":[56],"on":[57],"textual":[58],"information":[59],"for":[60,119],"overlooking":[62],"modality":[65],"actual":[68],"process.":[71],"In":[72],"contrast,":[73],"humans":[74],"naturally":[75],"re-examine":[76],"content":[78],"while":[79],"reasoning.":[80,102],"Motivated":[81],"by":[82],"this,":[83],"we":[84,107,126],"introduce":[85],"novel":[87],"paradigm:":[90],"Video-Text":[91,110],"Interleaved":[92,111],"CoT":[93,153],"(ViTCoT),":[94],"which":[95,114],"facilitates":[96],"more":[97,158],"intuitive":[98],"cognitively":[100],"aligned":[101],"To":[103],"end,":[105],"first,":[106],"construct":[108],"Benchmark":[112],"(ViTIB),":[113],"created":[116],"using":[117],"MLLMs":[118],"key-video":[120],"selection":[121],"manually":[123],"verified.":[124],"Furthermore,":[125],"extensively":[127],"explore":[128],"potential":[130],"ViTCoT":[133,144],"paradigm":[134,154],"field.":[139],"Extensive":[140],"experiments":[141],"demonstrate":[142],"that":[143],"enhances":[146],"performance":[147],"compared":[148],"traditional":[151],"text-only":[152],"effectively":[156],"activates":[157],"neuron":[159],"values":[160],"MLLMs.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-25T00:00:00"}