{"id":"https://openalex.org/W4415539618","doi":"https://doi.org/10.1145/3746027.3755102","title":"FingER: Content Aware Fine-grained Evaluation with Reasoning for AI-Generated Videos","display_name":"FingER: Content Aware Fine-grained Evaluation with Reasoning for AI-Generated Videos","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539618","doi":"https://doi.org/10.1145/3746027.3755102"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755102","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/A5100403652","display_name":"Rui Chen","orcid":"https://orcid.org/0000-0002-6249-6780"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Chen","raw_affiliation_strings":["AMAP, Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6249-6780","affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100574263","display_name":"Lei Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Sun","raw_affiliation_strings":["AMAP, Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-9550-8098","affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Tang","orcid":"https://orcid.org/0009-0006-1739-1548"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Tang","raw_affiliation_strings":["AMAP, Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-1739-1548","affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101359855","display_name":"Geng Li","orcid":"https://orcid.org/0009-0009-2289-5558"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Geng Li","raw_affiliation_strings":["AMAP, Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-2289-5558","affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101512474","display_name":"Xiangxiang Chu","orcid":"https://orcid.org/0000-0003-2548-0605"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxiang Chu","raw_affiliation_strings":["AMAP, Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2548-0605","affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25440386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3517","last_page":"3526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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":0.9980000257492065,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9976999759674072,"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/leverage","display_name":"Leverage (statistics)","score":0.7827000021934509},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5879999995231628},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5382999777793884},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5198000073432922},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.3188000023365021},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.28450000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098999857902527},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7827000021934509},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5879999995231628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400000214576721},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5382999777793884},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43639999628067017},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3407999873161316},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28029999136924744},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2766000032424927},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755102","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755102","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W3109908659","https://openalex.org/W4392172801","https://openalex.org/W4393160302","https://openalex.org/W4402660110","https://openalex.org/W4402753790"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,9,29],"video":[3,53],"generation":[4],"have":[5,232],"posed":[6],"great":[7],"challenges":[8],"the":[10,17,45,116,165,189,221],"assessment":[11],"of":[12,19,48,115,139,168,202,220],"AI-generated":[13],"content,":[14,117],"particularly":[15],"with":[16,80,150,184,210],"emergence":[18],"increasingly":[20],"sophisticated":[21],"models.":[22],"The":[23],"various":[24,159],"inconsistencies":[25],"and":[26,71,127,143,206,230],"defects":[27],"observed":[28],"such":[30],"videos":[31,142],"are":[32,129],"inherently":[33],"complex,":[34],"making":[35,119],"overall":[36,90],"scoring":[37,122],"notoriously":[38],"difficult.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,96,133,156],"emphasize":[44],"critical":[46],"importance":[47],"integrating":[49],"fine-grained":[50,146],"reasoning":[51,61,166,179],"into":[52],"evaluation.":[54],"We":[55],"propose":[56],"FingER,":[57],"a":[58,77,135,178,185,199],"novel":[59],"entity-level":[60,101],"evaluation":[62],"framework":[63],"that":[64,177],"first":[65],"automatically":[66],"generates":[67],"Fine-grained":[68],"Entity-level":[69],"questions,":[70],"then":[72],"answers":[73],"those":[74],"questions":[75,102],"by":[76,198,225],"Reasoning":[78],"model":[79,180,194],"scores,":[81],"which":[82,107,215],"can":[83],"be":[84],"subsequently":[85],"weighted":[86],"summed":[87],"to":[88,99,162],"an":[89],"score":[91],"for":[92,125,170],"different":[93],"applications.":[94],"Specifically,":[95],"leverage":[97],"LLMs":[98],"derive":[100],"across":[103],"five":[104],"distinct":[105],"perspectives,":[106],"(i)":[108],"often":[109],"focus":[110],"on":[111,154,204,208],"some":[112],"specific":[113],"entities":[114],"thereby":[118],"answering":[120],"or":[121],"much":[123],"easier":[124],"MLLMs,":[126],"(ii)":[128],"more":[130],"interpretable.":[131],"Then":[132],"construct":[134],"FingER":[136],"dataset,":[137],"consisting":[138],"approximately":[140],"3.3k":[141,212],"corresponding":[144],"60k":[145],"QA":[147],"annotations,":[148],"each":[149],"detailed":[151],"reasons.":[152],"Based":[153],"that,":[155],"further":[157],"investigate":[158],"training":[160,213,222],"protocols":[161],"best":[163,190],"incentivize":[164],"capability":[167],"MLLMs":[169],"correct":[171],"answer":[172],"prediction.":[173],"Extensive":[174],"experiments":[175],"demonstrate":[176],"trained":[181],"using":[182],"GRPO":[183],"cold-start":[186],"strategy":[187],"achieves":[188],"performance.":[191],"Notably,":[192],"our":[193],"surpasses":[195],"existing":[196],"methods":[197],"relative":[200],"margin":[201],"11.8%":[203],"GenAI-Bench":[205],"5.5%":[207],"MonetBench":[209],"only":[211],"videos,":[214],"is":[216],"at":[217],"most":[218],"one-tenth":[219],"samples":[223],"utilized":[224],"other":[226],"methods.":[227],"Our":[228],"codes":[229],"datasets":[231],"been":[233],"released.":[234]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-25T00:00:00"}