{"id":"https://openalex.org/W4415540433","doi":"https://doi.org/10.1145/3746027.3758299","title":"HVEval: Towards Unified Evaluation of Human-Centric Video Generation and Understanding","display_name":"HVEval: Towards Unified Evaluation of Human-Centric Video Generation and Understanding","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540433","doi":"https://doi.org/10.1145/3746027.3758299"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758299","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758299","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":"conference-paper","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/A5019148813","display_name":"Sijing Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijing Wu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-7753-1596","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778543","display_name":"Yunhao Li","orcid":"https://orcid.org/0000-0002-7337-1748"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhao Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7337-1748","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015291775","display_name":"Huiyu Duan","orcid":"https://orcid.org/0000-0002-6519-4067"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyu Duan","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6519-4067","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111343906","display_name":"Yanwei Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Jiang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-6700-8110","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034718093","display_name":"Yucheng Zhu","orcid":"https://orcid.org/0000-0002-3069-060X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucheng Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3069-060X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8165-9322","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13376","last_page":"13383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9991000294685364,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9991000294685364,"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":0.9962999820709229,"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":0.9947999715805054,"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/perception","display_name":"Perception","score":0.36419999599456787},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35249999165534973},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3441999852657318},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3142000138759613},{"id":"https://openalex.org/keywords/evaluation-methods","display_name":"Evaluation methods","score":0.2939999997615814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638000249862671},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4438999891281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44029998779296875},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.358599990606308},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3172000050544739},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26420000195503235}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758299","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758299","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/G3014884258","display_name":null,"funder_award_id":"62401365, 62225112, 62101326, 62132006, U24A20220","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4507737079","display_name":null,"funder_award_id":"BX20250411, 2025M773473","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3167030277","https://openalex.org/W4225292576","https://openalex.org/W4394841775","https://openalex.org/W4402660110","https://openalex.org/W4402727736","https://openalex.org/W4402753874","https://openalex.org/W4415541184"],"related_works":[],"abstract_inverted_index":{"Human-centric":[0],"videos":[1,29,92],"play":[2],"a":[3],"significant":[4,147],"role":[5],"in":[6,104,136,157],"the":[7,15,39,74,94,146],"pervasive":[8],"video":[9,159],"content":[10],"of":[11,17,50,123,149],"modern":[12],"life.":[13],"However,":[14],"capabilities":[16],"text-to-video":[18],"(T2V)":[19],"generation":[20,139,160],"models":[21,26,88],"and":[22,64,67,106,129,140,143,152,161],"video-to-text":[23],"(V2T)":[24],"understanding":[25,105],"for":[27,117],"human-centric":[28,46,91,108,119,158],"remain":[30],"largely":[31],"unexplored.":[32],"To":[33],"this":[34,77],"end,":[35],"we":[36],"present":[37],"HVEval,":[38],"first":[40],"comprehensive":[41],"evaluation":[42],"dataset":[43,151],"focusing":[44],"on":[45,73],"videos,":[47,52],"which":[48],"consists":[49],"20,000":[51],"60k":[53],"MOS":[54],"annotations":[55],"across":[56],"3":[57],"dimensions":[58],"(i.e.,":[59],"spatial":[60],"quality,":[61,63],"temporal":[62],"text-video":[65],"correspondence),":[66],"20k":[68],"category-specific":[69],"Q&A":[70],"pairs.":[71],"Based":[72],"HVEval":[75],"dataset,":[76],"paper":[78],"aims":[79],"to":[80,154],"answer":[81],"three":[82],"questions:":[83],"(1)":[84],"can":[85],"today's":[86,101],"T2V":[87,125],"effectively":[89],"generate":[90],"following":[93],"given":[95],"prompts?":[96],"(2)":[97],"how":[98],"effective":[99],"are":[100,111],"V2T":[102],"LMMs":[103],"evaluating":[107,118],"videos?":[109,120],"(3)":[110],"current":[112],"VQA":[113,131],"metrics":[114,132],"good":[115],"enough":[116],"Comprehensive":[121],"evaluations":[122],"24":[124],"models,":[126],"20":[127],"LMMs,":[128],"18":[130],"reveal":[133],"their":[134],"limitations":[135],"fine-grained":[137],"text-controlled":[138],"human-aligned":[141],"perception":[142],"understanding,":[144],"highlighting":[145],"potential":[148],"our":[150],"benchmarks":[153],"advance":[155],"research":[156],"understanding.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}