{"id":"https://openalex.org/W4412888718","doi":"https://doi.org/10.18653/v1/2025.findings-acl.151","title":"Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation","display_name":"Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888718","doi":"https://doi.org/10.18653/v1/2025.findings-acl.151"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.151","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.151","pdf_url":"https://aclanthology.org/2025.findings-acl.151.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: ACL 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-acl.151.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071444362","display_name":"Qiji Zhou","orcid":"https://orcid.org/0000-0001-5297-4796"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiji Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107639889","display_name":"Yifan Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"YiFan Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010399428","display_name":"Guangsheng Bao","orcid":"https://orcid.org/0000-0003-3815-3988"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangsheng Bao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055762601","display_name":"Hongjie Qiu","orcid":"https://orcid.org/0009-0009-6463-0726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongjie Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083723714","display_name":"Jinqiang Li","orcid":"https://orcid.org/0000-0003-3399-9159"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinqiang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021211025","display_name":"Xiangrong Zhu","orcid":"https://orcid.org/0000-0002-3791-7942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangrong Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031895128","display_name":"Huajian Zhang","orcid":"https://orcid.org/0000-0002-2445-6286"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huajian Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100333712","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-4017-3681"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Zhang","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":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2939","last_page":"2957"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9932000041007996,"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":0.9932000041007996,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9035000205039978,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.861630916595459},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7568528652191162},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7567576766014099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6944088935852051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.538527250289917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4027891755104065},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3369702100753784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17629295587539673},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12492716312408447},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06216272711753845}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.861630916595459},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7568528652191162},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7567576766014099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6944088935852051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.538527250289917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4027891755104065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3369702100753784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17629295587539673},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12492716312408447},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06216272711753845},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.151","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.151","pdf_url":"https://aclanthology.org/2025.findings-acl.151.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.151","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.151","pdf_url":"https://aclanthology.org/2025.findings-acl.151.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318567","display_name":"Westlake University","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888718.pdf","grobid_xml":"https://content.openalex.org/works/W4412888718.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W4384133558","https://openalex.org/W3025615835","https://openalex.org/W173210993","https://openalex.org/W2390660599","https://openalex.org/W3028847759","https://openalex.org/W2393688264","https://openalex.org/W4225573578"],"abstract_inverted_index":{"Counterfactual":[0],"reasoning":[1,49,65,84,105],"is":[2,88,111],"crucial":[3],"for":[4,90,101],"robust":[5],"video":[6,74,95],"understanding":[7],"but":[8],"remains":[9],"underexplored":[10],"in":[11,73,107],"existing":[12],"multimodal":[13,25,38],"benchmarks.In":[14],"this":[15],"paper,":[16],"we":[17],"introduce":[18],"COVER":[19,40],"(COunterfactual":[20],"VidEo":[21],"Reasoning),":[22],"a":[23,57,79,98],"multidimensional":[24],"benchmark":[26],"that":[27],"systematically":[28],"evaluates":[29],"MLLMs":[30],"across":[31],"the":[32,68,83,92],"abstract-concrete":[33],"and":[34,53,63],"perception-cognition":[35],"dimensions.Beyond":[36],"prior":[37],"benchmarks,":[39],"decomposes":[41],"complex":[42],"queries":[43],"into":[44],"structured":[45,71],"sub-questions,":[46],"enabling":[47],"fine-grained":[48],"analysis.Experiments":[50],"on":[51],"commercial":[52],"open-source":[54],"models":[55,87],"reveal":[56],"strong":[58],"correlation":[59],"between":[60],"subquestion":[61],"accuracy":[62],"counterfactual":[64],"performance,":[66],"highlighting":[67],"role":[69],"of":[70,86,94],"inference":[72],"understanding.Furthermore,":[75],"our":[76],"results":[77],"suggest":[78],"key":[80],"insight:":[81],"enhancing":[82],"capability":[85],"essential":[89],"improving":[91],"robustness":[93],"understanding.COVER":[96],"establishes":[97],"new":[99],"standard":[100],"assessing":[102],"MLLMs'":[103],"logical":[104],"abilities":[106],"dynamic":[108],"environments.Our":[109],"work":[110],"available":[112],"at":[113],"https://github.com/gongyifan-hash/COVER-Benchmark.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
