{"id":"https://openalex.org/W7137938448","doi":"https://doi.org/10.1609/aaai.v40i13.38018","title":"VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning","display_name":"VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137938448","doi":"https://doi.org/10.1609/aaai.v40i13.38018"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i13.38018","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38018","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38018/41980","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38018/41980","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129649906","display_name":"Zikang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zikang Wang","raw_affiliation_strings":["Shanghai Jiao Tong University\nShanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University\nShanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129719239","display_name":"BoYu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyu Chen","raw_affiliation_strings":["Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences\nVIVO AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences\nSchool of Artificial Intelligence, University of Chinese Academy of Sciences\nVIVO AI Lab","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129719120","display_name":"Zhengrong Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengrong Yue","raw_affiliation_strings":["Shanghai Jiaotong University\nShanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University\nShanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694574","display_name":"Yi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences\nShanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences\nShanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129656005","display_name":"Yu Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145386","display_name":"National Intelligence University","ror":"https://ror.org/049sfwc36","country_code":"US","type":"education","lineage":["https://openalex.org/I4210145386"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["Shanghai Aritifcal Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Aritifcal Intelligence Laboratory","institution_ids":["https://openalex.org/I4210145386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129647960","display_name":"Limin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Limin Wang","raw_affiliation_strings":["Nanjing University\nShanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University\nShanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210164862"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129698537","display_name":"Yali Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yali Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory","Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences\nShanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shenzhen Key Lab of Computer Vision and Pattern Recognition, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences\nShanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16239316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"10467","last_page":"10475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8539999723434448,"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":0.8539999723434448,"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":0.04729999974370003,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02879999950528145,"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/key","display_name":"Key (lock)","score":0.5942999720573425},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5401999950408936},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.48069998621940613},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.39100000262260437},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.34200000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789900004863739},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.48069998621940613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47679999470710754},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3930000066757202},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i13.38018","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38018","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38018/41980","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38018","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38018","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38018/41980","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137938448.pdf","grobid_xml":"https://content.openalex.org/works/W7137938448.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,23,50,161,191],"video":[3,65,110,122,207],"understanding":[4,24,190],"have":[5,37],"been":[6,39],"driven":[7],"by":[8,229],"MLLMs.":[9],"But":[10],"these":[11,95,159],"MLLMs":[12,42],"are":[13],"good":[14],"at":[15],"analyzing":[16],"short":[17],"videos,":[18,137],"while":[19],"suffering":[20],"from":[21,77,126],"difficulties":[22],"videos":[25],"with":[26,68,135,250],"a":[27,51,63,78,119,139,162],"longer":[28],"context.":[29],"To":[30,112],"address":[31],"this":[32,114],"difficulty,":[33],"several":[34],"agent":[35,123],"paradigms":[36],"recently":[38],"proposed,":[40],"using":[41],"as":[43],"agents":[44,57,96],"for":[45,108,188],"retrieving":[46],"extra":[47],"contextual":[48],"knowledge":[49],"long":[52,64,79,109,121,136,192,206],"video.":[53],"However,":[54],"most":[55],"existing":[56],"ignore":[58],"the":[59,74,127,150,169,181,200,204],"key":[60],"fact":[61],"that":[62],"is":[66,82],"composed":[67],"multiple":[69],"shots,":[70],"i.e.,":[71],"to":[72,84,231,236],"answer":[73],"user":[75,154],"question":[76],"video,":[80],"it":[81,146,211],"critical":[83],"deeply":[85,133],"understand":[86],"its":[87,222],"relevant":[88,151],"shots":[89,152,160],"like":[90],"human.":[91],"Without":[92],"such":[93],"insight,":[94],"often":[97],"mistakenly":[98],"find":[99],"redundant":[100],"even":[101],"noisy":[102],"temporal":[103,186],"context,":[104],"restricting":[105],"their":[106],"capacity":[107],"understanding.":[111],"fill":[113],"gap,":[115],"we":[116],"propose":[117],"VideoChat-A1,":[118],"novel":[120],"paradigm.":[124,143],"Different":[125],"previous":[128],"works,":[129],"our":[130],"VideoChat-A1":[131,172,198,244],"can":[132,147,173],"think":[134],"via":[138],"distinct":[140],"chain-of-shot":[141],"reasoning":[142,167],"More":[144],"specifically,":[145],"progressively":[148],"select":[149],"of":[153,184],"question,":[155],"and":[156,217,227,233,240,254],"look":[157],"into":[158],"coarse-to-fine":[163],"partition.":[164],"By":[165],"multi-modal":[166],"along":[168],"shot":[170],"chain,":[171],"effectively":[174],"mimic":[175],"step-by-step":[176],"human":[177],"thinking":[178],"process,":[179],"allowing":[180],"interactive":[182],"discovery":[183],"preferable":[185],"context":[187],"thoughtful":[189],"videos.":[193],"Extensive":[194],"experiments":[195],"show":[196],"that,":[197],"achieves":[199,212],"state-of-the-art":[201],"performance":[202],"on":[203,214,219,258],"mainstream":[205],"QA":[208],"benchmarks,":[209],"e.g.,":[210],"77.0":[213],"VideoMME(w/":[215],"subs)":[216],"70.1":[218],"EgoSchema,":[220],"outperforming":[221],"strong":[223],"baselines":[224],"(e.g.,":[225],"InternVL2.5-8B":[226],"InternVideo2.5-8B),":[228],"up":[230],"10.1%":[232],"6.2%.":[234],"Compared":[235],"leading":[237],"closed-source":[238],"GPT-4o":[239],"Gemini":[241],"1.5":[242],"Pro,":[243],"offers":[245],"competitive":[246],"accuracy,":[247],"but":[248],"only":[249],"7%":[251],"input":[252],"frames":[253],"12%":[255],"inference":[256],"time":[257],"average.":[259]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}