{"id":"https://openalex.org/W7204545009","doi":"https://doi.org/10.48550/arxiv.2608.26517","title":"HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence","display_name":"HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204545009","doi":"https://doi.org/10.48550/arxiv.2608.26517"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.26517","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26517","pdf_url":"https://arxiv.org/pdf/2608.26517","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.26517","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128801829","display_name":"Fei Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053952600","display_name":"Zebang Cheng","orcid":"https://orcid.org/0009-0001-2854-7425","observed_orcids":["https://orcid.org/0009-0001-2854-7425"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Zebang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148527243","display_name":"Minghui Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Minghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148532963","display_name":"Hongbo Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Hongbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148523206","display_name":"Yuyong Tan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Yuyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148524973","display_name":"Yihua Shao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Yihua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028523597","display_name":"Hanling Wang","orcid":"https://orcid.org/0009-0005-5778-4007","observed_orcids":["https://orcid.org/0009-0005-5778-4007"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hanling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148566638","display_name":"Zhou Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148534933","display_name":"Yuqing Gao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yuqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148499354","display_name":"Dong Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148564348","display_name":"Long Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Long","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134781212","display_name":"Laizhong Cui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Laizhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027171279","display_name":"Nicu Sebe","orcid":"https://orcid.org/0000-0002-6597-7248","observed_orcids":["https://orcid.org/0000-0002-6597-7248"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebe, Nicu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133681753","display_name":"Qi Tian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Qi","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":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/T10667","display_name":"Emotion and Mood Recognition","score":0.5145999789237976,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.5145999789237976,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.40230000019073486,"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/T10860","display_name":"Speech and Audio Processing","score":0.01510000042617321,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/multimodal-benchmark","display_name":"multimodal benchmark","score":0.9739999771118164},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"emotion recognition","score":0.8579999804496765},{"id":"https://openalex.org/keywords/voice-cloning","display_name":"voice cloning","score":0.9900000095367432},{"id":"https://openalex.org/keywords/video-matting","display_name":"video matting","score":0.8090000152587891},{"id":"https://openalex.org/keywords/zero-shot-evaluation","display_name":"zero-shot evaluation","score":0.5899999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6809999942779541},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.527899980545044},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4691999852657318},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C105409693","wikidata":"https://www.wikidata.org/wiki/Q5937824","display_name":"Human intelligence","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3255999982357025},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.26517","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26517","pdf_url":"https://arxiv.org/pdf/2608.26517","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.26517","doi":"https://doi.org/10.48550/arxiv.2608.26517","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.26517","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.26517","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26517","pdf_url":"https://arxiv.org/pdf/2608.26517","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4405768231","https://openalex.org/W4415540433","https://openalex.org/W4417070253","https://openalex.org/W7084139451","https://openalex.org/W7155097922","https://openalex.org/W7138230636","https://openalex.org/W7071631223","https://openalex.org/W4386566480","https://openalex.org/W7154262361","https://openalex.org/W7203952726"],"abstract_inverted_index":{"Visual":[0,109],"intelligence":[1,20],"seeks":[2],"to":[3,14],"perceive,":[4],"interpret,":[5],"and":[6,11,46,61,72,84,91,106,139,146,165,190,195,222,230,238],"synthesize":[7],"the":[8,123,150,215],"visual":[9,19,181],"world":[10],"is":[12,21,35,184,214],"central":[13],"modern":[15],"computer":[16],"vision.":[17],"Human-centered":[18,104],"especially":[22],"demanding":[23],"because":[24],"it":[25],"studies":[26],"people":[27],"as":[28],"expressive,":[29],"socially":[30],"situated":[31],"subjects":[32],"whose":[33],"meaning":[34],"rarely":[36],"conveyed":[37],"by":[38],"appearance":[39],"alone.":[40],"It":[41,111],"couples":[42],"vision":[43],"with":[44,98,134,232],"audio":[45],"language":[47],"across":[48,149,227],"four":[49,151],"representative":[50],"tasks:":[51],"human":[52,55,58,62,196,220],"emotion":[53,177],"recognition,":[54,178],"video":[56,63,188],"generation,":[57],"voice":[59,191],"cloning,":[60,192],"matting.":[64],"Yet":[65],"existing":[66],"resources":[67],"remain":[68],"task-specific,":[69],"providing":[70],"modalities":[71],"annotations":[73],"for":[74,103,219],"individual":[75],"problems":[76],"rather":[77],"than":[78],"a":[79,100,129,154],"shared":[80],"foundation":[81],"coordinating":[82],"understanding":[83],"generation.":[85],"This":[86],"limits":[87],"multimodal":[88],"signal":[89],"use":[90],"broader":[92],"research.":[93],"We":[94,142],"address":[95],"this":[96],"gap":[97],"HUG-VIS,":[99],"unified":[101,155],"benchmark":[102],"Understanding":[105],"Generation":[107],"in":[108,187,202],"Intelligence.":[110],"contains":[112],"8,400":[113],"seated":[114],"half-body":[115],"videos":[116],"of":[117],"30":[118],"professional":[119],"actors,":[120],"each":[121],"performing":[122],"same":[124],"280":[125],"emotion-action-prompt":[126],"assignments":[127],"under":[128,153,212],"controlled":[130],"Mandarin":[131],"studio":[132],"protocol,":[133],"synchronized":[135],"video,":[136],"audio,":[137],"text,":[138],"alpha":[140],"mattes.":[141],"evaluate":[143],"diverse":[144],"open-":[145],"closed-source":[147],"models":[148],"tasks":[152],"zero-shot":[156],"protocol":[157],"using":[158],"automatic":[159,193],"metrics,":[160,231],"criterion-specific":[161],"mean":[162],"opinion":[163],"scores,":[164],"multiple":[166],"cross-task":[167,234],"analyses.":[168],"Results":[169],"show":[170],"that":[171],"(i)":[172],"linguistic":[173],"content":[174],"dominates":[175],"current":[176],"while":[179],"purely":[180],"affect":[182],"recognition":[183],"weakest;":[185],"(ii)":[186],"generation":[189],"metrics":[194],"judgment":[197],"agree":[198],"overall":[199],"but":[200],"differ":[201],"their":[203],"top":[204],"rankings,":[205],"requiring":[206],"joint":[207],"reporting;":[208],"(iii)":[209],"boundary":[210],"fidelity":[211],"motion":[213],"main":[216],"remaining":[217],"obstacle":[218],"matting;":[221],"(iv)":[223],"task":[224],"difficulty":[225],"varies":[226],"emotions,":[228],"models,":[229],"notable":[233],"correlations.":[235],"The":[236],"dataset":[237],"results":[239],"are":[240],"available":[241],"at":[242],"https://github.com/GML-MMGroup/HUG-VIS.":[243]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-29T00:00:00"}