{"id":"https://openalex.org/W4415537657","doi":"https://doi.org/10.1145/3746027.3754864","title":"AICL: Action In-Context Learning for Text-to-Video Generation","display_name":"AICL: Action In-Context Learning for Text-to-Video Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537657","doi":"https://doi.org/10.1145/3746027.3754864"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754864","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/A5053660894","display_name":"Junjia Liu","orcid":"https://orcid.org/0000-0003-0646-9523"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhi Liu","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0646-9523","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087225139","display_name":"Junchen Zhu","orcid":"https://orcid.org/0000-0002-3872-6689"},"institutions":[{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junchen Zhu","raw_affiliation_strings":["Skywork AI, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3872-6689","affiliations":[{"raw_affiliation_string":"Skywork AI, Beijing, China","institution_ids":["https://openalex.org/I53486688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087623065","display_name":"Pengpeng Zeng","orcid":"https://orcid.org/0000-0002-0672-3790"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengpeng Zeng","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0672-3790","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25935689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9414","last_page":"9423"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.998199999332428,"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":0.998199999332428,"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":0.9980000257492065,"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":0.9958999752998352,"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/action","display_name":"Action (physics)","score":0.7483999729156494},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5351999998092651},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48330000042915344},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4318000078201294},{"id":"https://openalex.org/keywords/action-learning","display_name":"Action learning","score":0.33559998869895935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7552000284194946},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7483999729156494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5777999758720398},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5351999998092651},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48330000042915344},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4318000078201294},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3637000024318695},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.33559998869895935},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26660001277923584},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754864","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754864","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/G1700256261","display_name":null,"funder_award_id":"62425208,82441006,U22A2097,U23A20315,62122018,62020106008,62402094","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":5,"referenced_works":["https://openalex.org/W4312933868","https://openalex.org/W4386076112","https://openalex.org/W4389524274","https://openalex.org/W4390873135","https://openalex.org/W4402727736"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"large-scale":[1],"video":[2,34,41],"datasets":[3],"have":[4,20],"facilitated":[5],"the":[6,49,58,91,99,121,141,153,161],"generation":[7,162],"of":[8,11,65,163],"diverse":[9],"videos":[10,53,89],"Video":[12],"Diffusion":[13],"Models":[14],"(VDMs).":[15],"Nonetheless,":[16],"some":[17],"complex":[18,45],"actions":[19,50,83],"still":[21],"struggled":[22],"to":[23,30,39,57,80,105],"be":[24],"generated":[25,52],"by":[26,84,136],"those":[27],"VDMs,":[28,125],"leading":[29],"a":[31,63,77,95,117],"reduction":[32],"in":[33,51,62,90,167],"generalization.":[35],"Some":[36],"researchers":[37],"attempt":[38],"use":[40],"editing":[42],"methods":[43],"for":[44,130],"action":[46,107,133],"generation.":[47],"However,":[48],"are":[54],"often":[55],"identical":[56],"reference":[59,110],"video,":[60],"resulting":[61],"lack":[64],"diversity.":[66],"To":[67],"this":[68],"end,":[69],"we":[70],"first":[71],"propose":[72],"Acton":[73],"In-Context":[74],"Learning":[75],"(AICL),":[76],"novel":[78],"approach":[79],"generate":[81],"intricate":[82],"emulating":[85],"motions":[86],"from":[87,109,123,155],"pre-existing":[88],"inference":[92],"stage":[93],"using":[94],"plug-and-play":[96],"method.":[97],"Specifically,":[98],"Action":[100,126],"Perceiver":[101],"(AP),":[102],"is":[103,128,149],"introduced":[104,129],"distill":[106],"features":[108,134],"videos,":[111],"which":[112],"requires":[113],"training":[114],"on":[115],"only":[116],"small":[118],"dataset.":[119],"Leveraging":[120],"knowledge":[122],"pre-trained":[124],"Integration":[127],"incorporating":[131],"new":[132],"extracted":[135],"AP":[137],"into":[138],"VDMs":[139,171],"through":[140],"additional":[142],"layers.":[143],"Extensive":[144],"experiments":[145],"demonstrate":[146],"that":[147],"AICL":[148],"not":[150],"merely":[151],"replicating":[152],"motion":[154],"references,":[156],"and":[157],"it":[158],"significantly":[159],"improves":[160],"realistic":[164],"actions,":[165],"even":[166],"situations":[168],"where":[169],"existing":[170],"might":[172],"directly":[173],"fail.":[174]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}