{"id":"https://openalex.org/W4417182722","doi":"https://doi.org/10.48550/arxiv.2507.01255","title":"AIGVE-MACS: Unified Multi-Aspect Commenting and Scoring Model for AI-Generated Video Evaluation","display_name":"AIGVE-MACS: Unified Multi-Aspect Commenting and Scoring Model for AI-Generated Video Evaluation","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4417182722","doi":"https://doi.org/10.48550/arxiv.2507.01255"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.01255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01255","pdf_url":"https://arxiv.org/pdf/2507.01255","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.01255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100441075","display_name":"Xiao Liu","orcid":"https://orcid.org/0009-0008-1904-398X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100462844","display_name":"Jiawei Zhang","orcid":"https://orcid.org/0000-0002-8091-5045"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiawei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100441075"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6438999772071838,"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":0.6438999772071838,"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":0.22190000116825104,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.048500001430511475,"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/interpretability","display_name":"Interpretability","score":0.9449999928474426},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6334999799728394},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4733999967575073},{"id":"https://openalex.org/keywords/scoring-algorithm","display_name":"Scoring algorithm","score":0.46630001068115234},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44699999690055847},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.3472000062465668},{"id":"https://openalex.org/keywords/evaluation-methods","display_name":"Evaluation methods","score":0.3061000108718872}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9449999928474426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8360000252723694},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6334999799728394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6162999868392944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5493999719619751},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C83282275","wikidata":"https://www.wikidata.org/wiki/Q7435350","display_name":"Scoring algorithm","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38029998540878296},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.01255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01255","pdf_url":"https://arxiv.org/pdf/2507.01255","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.01255","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.01255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.01255","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01255","pdf_url":"https://arxiv.org/pdf/2507.01255","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,184],"AI-generated":[4,81,185],"video":[5,167],"models":[6],"has":[7],"created":[8],"a":[9,44,76,105,111,155,177],"pressing":[10],"need":[11],"for":[12,47,180],"robust":[13],"and":[14,33,83,88,110,126,139,148,192],"interpretable":[15],"evaluation":[16,35,94,183],"frameworks.":[17],"Existing":[18],"metrics":[19],"are":[20],"limited":[21],"to":[22,70,116,170],"producing":[23],"numerical":[24,56,89],"scores":[25,57,90],"without":[26],"explanatory":[27],"comments,":[28],"resulting":[29],"in":[30,64,135,166],"low":[31],"interpretability":[32],"human":[34,120],"alignment.":[36],"To":[37],"address":[38],"those":[39],"challenges,":[40],"we":[41,152],"introduce":[42],"AIGVE-MACS,":[43],"unified":[45],"model":[46],"AI-Generated":[48],"Video":[49],"Evaluation(AIGVE),":[50],"which":[51],"can":[52],"provide":[53],"not":[54],"only":[55],"but":[58],"also":[59],"multi-aspect":[60],"language":[61],"comment":[62,140],"feedback":[63,160],"evaluating":[65],"these":[66],"generated":[67],"videos.":[68,186],"Central":[69],"our":[71],"approach":[72],"is":[73],"AIGVE-BENCH":[74,97,190],"2,":[75,98],"large-scale":[77],"benchmark":[78],"comprising":[79],"2,500":[80],"videos":[82],"22,500":[84],"human-annotated":[85],"detailed":[86],"comments":[87],"across":[91,124],"nine":[92],"critical":[93],"aspects.":[95],"Leveraging":[96],"AIGVE-MACS":[99,131,162,193],"incorporates":[100],"recent":[101],"Vision-Language":[102],"Models":[103],"with":[104,119],"novel":[106],"token-wise":[107],"weighted":[108],"loss":[109],"dynamic":[112],"frame":[113],"sampling":[114],"strategy":[115],"better":[117],"align":[118],"evaluators.":[121],"Comprehensive":[122],"experiments":[123],"supervised":[125],"zero-shot":[127],"benchmarks":[128],"demonstrate":[129],"that":[130],"achieves":[132],"state-of-the-art":[133],"performance":[134],"both":[136],"scoring":[137],"correlation":[138],"quality,":[141],"significantly":[142],"outperforming":[143],"prior":[144],"baselines":[145],"including":[146],"GPT-4o":[147],"VideoScore.":[149],"In":[150],"addition,":[151],"further":[153],"showcase":[154],"multi-agent":[156],"refinement":[157],"framework":[158],"where":[159],"from":[161],"drives":[163],"iterative":[164],"improvements":[165],"generation,":[168],"leading":[169],"53.5%":[171],"quality":[172],"enhancement.":[173],"This":[174],"work":[175],"establishes":[176],"new":[178],"paradigm":[179],"comprehensive,":[181],"human-aligned":[182],"We":[187],"release":[188],"the":[189],"2":[191],"at":[194],"https://huggingface.co/xiaoliux/AIGVE-MACS.":[195]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}