{"id":"https://openalex.org/W4406457553","doi":"https://doi.org/10.1109/3dv69130.2026.00087","title":"Predicting 4D Hand Trajectory from Monocular Videos","display_name":"Predicting 4D Hand Trajectory from Monocular Videos","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W4406457553","doi":"https://doi.org/10.1109/3dv69130.2026.00087"},"language":"en","primary_location":{"id":"doi:10.1109/3dv69130.2026.00087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.08329","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028764753","display_name":"Yufei Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufei Ye","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102813327","display_name":"Yao Feng","orcid":"https://orcid.org/0000-0002-9481-9783"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yao Feng","raw_affiliation_strings":["Max Planck Institute for Intelligent Systems,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems,USA","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111226930","display_name":"Omid Taheri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Omid Taheri","raw_affiliation_strings":["Max Planck Institute for Intelligent Systems,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems,USA","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034400901","display_name":"Haiwen Feng","orcid":"https://orcid.org/0009-0005-7629-0547"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Haiwen Feng","raw_affiliation_strings":["Max Planck Institute for Intelligent Systems,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems,USA","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029932788","display_name":"Shubham Tulsiani","orcid":"https://orcid.org/0000-0001-5651-9424"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubham Tulsiani","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105696049","display_name":"Michael J. Black","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael J. Black","raw_affiliation_strings":["Max Planck Institute for Intelligent Systems,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems,USA","institution_ids":["https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00167752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"860","last_page":"870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9711999893188477,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9711999893188477,"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":0.9562000036239624,"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/trajectory","display_name":"Trajectory","score":0.7454431056976318},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6873476505279541},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5261903405189514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5144815444946289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4431765377521515},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3437635004520416},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09627896547317505},{"id":"https://openalex.org/keywords/astronomy","display_name":"Astronomy","score":0.05912286043167114}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7454431056976318},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6873476505279541},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5261903405189514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5144815444946289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4431765377521515},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3437635004520416},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09627896547317505},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.05912286043167114}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/3dv69130.2026.00087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.08329","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.08329","pdf_url":"https://arxiv.org/pdf/2501.08329","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.08329","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.08329","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:2501.08329","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.08329","pdf_url":"https://arxiv.org/pdf/2501.08329","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320322434","display_name":"Max-Planck-Gesellschaft","ror":"https://ror.org/01hhn8329"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406457553.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,80,121],"present":[1],"HaPTIC,":[2],"an":[3],"approach":[4],"that":[5],"infers":[6,105],"coherent":[7,78],"4D":[8,34,106],"hand":[9,16,35,107],"trajectories":[10,36,108],"from":[11],"monocular":[12],"videos.":[13,130],"Current":[14],"videobased":[15],"pose":[17,26,148],"reconstruction":[18],"methods":[19,50,135],"primarily":[20],"focus":[21],"on":[22],"improving":[23],"frame-wise":[24],"3D":[25],"using":[27],"adjacent":[28],"frames":[29,73],"rather":[30],"than":[31],"studying":[32],"consistent":[33],"in":[37,71,99,136,146],"space.":[38],"Despite":[39],"the":[40,53,111,123,144],"additional":[41],"temporal":[42,92],"cues,":[43],"they":[44],"generally":[45],"underperform":[46],"compared":[47],"to":[48,52,69,90,97,110,125,143],"image-based":[49,67],"due":[51],"scarcity":[54],"of":[55,84],"annotated":[56],"video":[57],"data.":[58],"To":[59],"address":[60],"these":[61],"issues,":[62],"we":[63],"repurpose":[64],"a":[65,77],"state-of-the-art":[66,145],"transformer":[68],"take":[70],"multiple":[72],"and":[74,94,128],"directly":[75],"predict":[76],"trajectory.":[79],"introduce":[81],"two":[82],"types":[83],"lightweight":[85],"attention":[86],"layers:":[87],"cross-view":[88],"self-attention":[89],"fuse":[91],"information,":[93],"global":[95,137],"cross-attention":[96],"bring":[98],"larger":[100],"spatial":[101],"context.":[102],"Our":[103],"method":[104,124],"similar":[109],"ground":[112],"truth":[113],"while":[114,140],"maintaining":[115],"strong":[116],"2":[117],"D":[118],"reprojection":[119],"alignment.":[120],"apply":[122],"both":[126],"egocentric":[127],"allocentric":[129],"It":[131],"significantly":[132],"outperforms":[133],"existing":[134],"trajectory":[138],"accuracy":[139],"being":[141],"comparable":[142],"single-image":[147],"estimation.":[149]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
