{"id":"https://openalex.org/W4416033973","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1001","title":"Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning","display_name":"Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033973","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1001"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1001","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1001","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1001.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1001.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049930385","display_name":"Daeun Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daeun Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054456399","display_name":"Jaehong Yoon","orcid":"https://orcid.org/0000-0002-9653-9590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaehong Yoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101760065","display_name":"Jaemin Cho","orcid":"https://orcid.org/0000-0003-1148-5413"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaemin Cho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001987532","display_name":"Mohit Bansal","orcid":"https://orcid.org/0000-0001-5522-1351"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohit Bansal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.36776427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18435","last_page":"18449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.20319999754428864,"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":0.20319999754428864,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.10440000146627426,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.07100000232458115,"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/process","display_name":"Process (computing)","score":0.2815999984741211},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2703000009059906},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.2443999946117401},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24379999935626984},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.24220000207424164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6205999851226807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5299000144004822},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40119999647140503},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2443999946117401},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24379999935626984},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.24220000207424164},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.23399999737739563},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.23070000112056732}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1001","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1001","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1001.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1001","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1001","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1001.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2921176242","display_name":null,"funder_award_id":"W911NF2110220","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G5599941371","display_name":null,"funder_award_id":"N00014-23-1-2356","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G580734012","display_name":"AI Institute for Engaged Learning","funder_award_id":"2112635","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033973.pdf","grobid_xml":"https://content.openalex.org/works/W4416033973.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,96],"Chain-of-Thought":[3],"(CoT)":[4],"reasoning":[5,61,100],"have":[6],"improved":[7],"complex":[8],"video":[9,31,51,122,146],"understanding,":[10,26],"but":[11],"existing":[12],"methods":[13],"often":[14],"struggle":[15],"to":[16,18,80],"adapt":[17],"domain-specific":[19],"skills":[20,62,101,143],"(e.g.,":[21],"event":[22],"detection,":[23],"spatial":[24,153],"relation":[25],"emotion":[27],"understanding)":[28],"over":[29,144],"various":[30],"content.To":[32],"address":[33],"this,":[34],"we":[35,53,86],"propose":[36],"VIDEO-SKILL-COT":[37],"(a.k.a.VIDEO-SKOT)":[38],"a":[39,69,88,97],"framework":[40],"that":[41],"automatically":[42],"constructs":[43],"and":[44,73,102,141],"leverages":[45],"skill-aware":[46],"CoT":[47,56,77,111,138],"supervisions":[48],"for":[49,84],"domain-adaptive":[50],"reasoning.First,":[52],"construct":[54],"skill-based":[55],"annotations:":[57],"We":[58],"extract":[59],"domain-relevant":[60],"from":[63],"training":[64],"questions,":[65],"cluster":[66],"them":[67],"into":[68],"shared":[70],"skill":[71],"taxonomy,":[72],"create":[74],"detailed":[75],"multi-step":[76],"rationale":[78],"tailored":[79],"each":[81],"video-question":[82],"pair":[83],"training.Second,":[85],"introduce":[87],"skill-specific":[89],"expert":[90,93],"learning":[91],"framework.Each":[92],"module":[94],"specializes":[95],"subset":[98],"of":[99,116,155],"is":[103],"trained":[104],"with":[105],"lightweight":[106],"adapters":[107],"using":[108,162],"the":[109,114,117],"collected":[110],"supervision.We":[112],"demonstrate":[113],"effectiveness":[115],"proposed":[118],"approach":[119],"on":[120,135],"three":[121],"understanding":[123],"benchmarks,":[124],"where":[125],"VIDEO-SKOT":[126],"consistently":[127],"outperforms":[128],"strong":[129],"baselines.We":[130],"also":[131],"provide":[132],"in-depth":[133],"analyses":[134],"comparing":[136],"different":[137],"annotation":[139],"pipelines":[140],"learned":[142],"multiple":[145],"domains.*":[147],"Equal":[148],"contribution.'Locate":[149],"specific":[150],"objects":[151,161],"positions.','Assess":[152],"proximity":[154],"objects',":[156],"'Estimate":[157],"distance":[158],"between":[159],"two":[160],"visual":[163],"cues.":[164]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-11-08T00:00:00"}