{"id":"https://openalex.org/W7203882979","doi":"https://doi.org/10.48550/arxiv.2608.20312","title":"Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis","display_name":"Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis","publication_year":2026,"publication_date":"2026-08-20","ids":{"openalex":"https://openalex.org/W7203882979","doi":"https://doi.org/10.48550/arxiv.2608.20312"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.20312","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20312","pdf_url":"https://arxiv.org/pdf/2608.20312","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.20312","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136995887","display_name":"Liang Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024672721","display_name":"Chengqun Yang","orcid":"https://orcid.org/0000-0003-1972-0086","observed_orcids":["https://orcid.org/0000-0003-1972-0086"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Chengqun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114042443","display_name":"Zili Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Zili","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045460091","display_name":"Xintao Lv","orcid":"https://orcid.org/0009-0005-9986-4080","observed_orcids":["https://orcid.org/0009-0005-9986-4080"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Xintao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147704176","display_name":"Yichao Yan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Yichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130239270","display_name":"Xin Jin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147809389","display_name":"Zhibo Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128833932","display_name":"Xiaokang Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xiaokang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124287967","display_name":"Wenjun Zeng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Wenjun","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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9564999938011169,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T12290","display_name":"Human Motion and Animation","score":0.9564999938011169,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.013700000010430813,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.008500000461935997,"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/human-human-interaction","display_name":"human-human interaction","score":0.9520000219345093},{"id":"https://openalex.org/keywords/multimodal-interaction-analysis","display_name":"multimodal interaction analysis","score":0.7329999804496765},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.8489999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7835000157356262},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6721000075340271},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5709999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5217999815940857},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5217000246047974},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46869999170303345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40529999136924744},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C2987082051","wikidata":"https://www.wikidata.org/wiki/Q223642","display_name":"Human interaction","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.20312","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20312","pdf_url":"https://arxiv.org/pdf/2608.20312","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.20312","doi":"https://doi.org/10.48550/arxiv.2608.20312","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.20312","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:2608.20312","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20312","pdf_url":"https://arxiv.org/pdf/2608.20312","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203882979.pdf","grobid_xml":"https://content.openalex.org/works/W7203882979.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2936695845","https://openalex.org/W3092442149","https://openalex.org/W4298186886","https://openalex.org/W4303647933","https://openalex.org/W4323076533","https://openalex.org/W4386072465","https://openalex.org/W4387839234","https://openalex.org/W4389820900","https://openalex.org/W4393196385","https://openalex.org/W4403578559","https://openalex.org/W4403730416","https://openalex.org/W4405767293","https://openalex.org/W4406272912","https://openalex.org/W4407760095","https://openalex.org/W4415160805","https://openalex.org/W4415951589","https://openalex.org/W4416154757","https://openalex.org/W4417152681","https://openalex.org/W7090837097","https://openalex.org/W7117122519","https://openalex.org/W7117803519","https://openalex.org/W7124273921","https://openalex.org/W7133212334","https://openalex.org/W7133218515","https://openalex.org/W7133312476","https://openalex.org/W7138333338","https://openalex.org/W7148492987"],"related_works":["https://openalex.org/W4402778086","https://openalex.org/W4413144746","https://openalex.org/W7106862297","https://openalex.org/W4402951619","https://openalex.org/W4415160805","https://openalex.org/W7117122519","https://openalex.org/W7215859064","https://openalex.org/W4417286512","https://openalex.org/W7159819641","https://openalex.org/W7080044555"],"abstract_inverted_index":{"The":[0],"capability":[1],"to":[2,10,70,180],"perceive":[3],"and":[4,19,34,46,53,66,89,97,122,133,158,171,185,189,197,211,225],"synthesize":[5],"human-human":[6],"interactions":[7],"is":[8],"fundamental":[9],"developing":[11],"intelligent":[12],"digital":[13],"human":[14],"systems.":[15],"However,":[16],"existing":[17],"datasets":[18],"modeling":[20,190],"approaches":[21],"are":[22],"fundamentally":[23],"constrained":[24],"by":[25],"low-fidelity":[26],"kinematics,":[27],"the":[28,104,120,125,168],"omission":[29],"of":[30,38,124,150],"dexterous":[31],"hand":[32],"gestures":[33],"a":[35,64,77,143,183],"severe":[36],"lack":[37],"rich":[39],"multimodal":[40],"annotations.":[41],"Furthermore,":[42],"fragmented":[43],"interaction":[44,87,115,118,169,195,223],"representations":[45,170],"inconsistent":[47],"evaluation":[48,172],"protocols":[49],"also":[50],"impede":[51],"fair":[52],"rigorous":[54],"benchmarking.":[55],"To":[56,161],"systematically":[57,166],"address":[58],"these":[59,138],"bottlenecks,":[60],"we":[61,102,141,165,175],"present":[62],"Inter-X++,":[63],"comprehensive":[65],"large-scale":[67],"benchmark":[68],"designed":[69],"empower":[71],"versatile":[72],"HHI":[73,187],"analysis.":[74],"Captured":[75],"via":[76],"novel":[78],"hybrid":[79],"motion":[80],"capture":[81],"system,":[82],"Inter-X++":[83],"provides":[84],"11,388":[85],"high-fidelity":[86],"sequences":[88],"over":[90],"8.1M":[91],"frames,":[92],"featuring":[93],"precise":[94],"whole-body":[95],"movements":[96],"detailed":[98],"finger":[99],"articulations.":[100],"Meanwhile,":[101],"enrich":[103],"data":[105],"foundation":[106],"with":[107],"multifaceted":[108],"annotations,":[109,140],"including":[110],"hierarchical":[111],"fine-grained":[112],"textual":[113],"descriptions,":[114],"categories,":[116],"causal":[117],"orders,":[119],"relationship":[121],"personality":[123],"subjects,":[126],"as":[127,129],"well":[128],"vertex-level":[130],"contact":[131],"maps":[132],"physically":[134],"regularized":[135],"constraints.":[136],"Leveraging":[137],"elaborate":[139],"formulate":[142],"unified":[144,186,219],"testing":[145],"ground":[146],"comprising":[147],"four":[148],"categories":[149],"downstream":[151],"tasks":[152],"that":[153,192,203,217],"symmetrically":[154],"span":[155],"both":[156,209],"generative":[157],"perceptive":[159],"paradigms.":[160],"eliminate":[162],"benchmarking":[163],"ambiguities,":[164],"standardize":[167],"protocols.":[173],"Finally,":[174],"go":[176],"beyond":[177],"dataset":[178],"construction":[179],"propose":[181],"OpenHHI,":[182],"single":[184],"representation":[188,220],"framework":[191],"jointly":[193],"optimizes":[194],"reconstruction":[196],"semantic":[198],"understanding.":[199],"Extensive":[200],"experiments":[201],"reveal":[202],"OpenHHI":[204],"achieves":[205],"state-of-the-art":[206],"performance":[207],"on":[208],"generation":[210,226],"perception":[212],"tasks.":[213],"This":[214],"definitively":[215],"proves":[216],"our":[218],"successfully":[221],"bridges":[222],"understanding":[224],"simultaneously.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-22T00:00:00"}