{"id":"https://openalex.org/W4308066984","doi":"https://doi.org/10.48550/arxiv.2107.00434","title":"Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation","display_name":"Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W4308066984","doi":"https://doi.org/10.48550/arxiv.2107.00434"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2107.00434","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.00434","pdf_url":"https://arxiv.org/pdf/2107.00434","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/2107.00434","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074599806","display_name":"Zicong Fan","orcid":"https://orcid.org/0009-0003-5667-926X","observed_orcids":["https://orcid.org/0009-0003-5667-926X"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"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":["CH","DE"],"is_corresponding":false,"raw_author_name":"Fan, Zicong","raw_affiliation_strings":["ETH Z\u00fcrich , Switzerland","Max Planck Institute for Intelligent Systems , T\u00fcbingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich , Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems , T\u00fcbingen","institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068220806","display_name":"Adrian Spurr","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Spurr, Adrian","raw_affiliation_strings":["ETH Z\u00fcrich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042004395","display_name":"Muhammed Kocabas","orcid":"https://orcid.org/0000-0001-8593-0415","observed_orcids":["https://orcid.org/0000-0001-8593-0415"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"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":["CH","DE"],"is_corresponding":false,"raw_author_name":"Kocabas, Muhammed","raw_affiliation_strings":["ETH Z\u00fcrich , Switzerland","Max Planck Institute for Intelligent Systems , T\u00fcbingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich , Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems , T\u00fcbingen","institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056265728","display_name":"Siyu Tang","orcid":"https://orcid.org/0000-0002-1015-4770","observed_orcids":["https://orcid.org/0000-0002-1015-4770"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tang, Siyu","raw_affiliation_strings":["ETH Z\u00fcrich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065396778","display_name":"Michael J. Black","orcid":"https://orcid.org/0000-0001-6077-4540","observed_orcids":["https://orcid.org/0000-0001-6077-4540"]},"institutions":[{"id":"https://openalex.org/I149899117","display_name":"Max Planck Society","ror":"https://ror.org/01hhn8329","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117"]},{"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":"Black, Michael J.","raw_affiliation_strings":["Max Planck Institute for Intelligent Systems , T\u00fcbingen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems , T\u00fcbingen","institution_ids":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025000908","display_name":"Otmar Hilliges","orcid":"https://orcid.org/0000-0002-5068-3474","observed_orcids":["https://orcid.org/0000-0002-5068-3474"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hilliges, Otmar","raw_affiliation_strings":["ETH Z\u00fcrich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.6699000000953674,"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":0.6699000000953674,"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":0.3100999891757965,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.008299999870359898,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/3d-hand-pose-estimation","display_name":"3D hand pose estimation","score":0.8820000290870667},{"id":"https://openalex.org/keywords/self-similarity","display_name":"self-similarity","score":0.8100000023841858},{"id":"https://openalex.org/keywords/monocular-images","display_name":"monocular images","score":0.8600000143051147},{"id":"https://openalex.org/keywords/digits","display_name":"digits","score":0.515999972820282}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8080158829689026},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695410847663879},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7295814752578735},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6795258522033691},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6674315929412842},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6026986241340637},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5542311072349548},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.4830835163593292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46859636902809143},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45555078983306885},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4105511009693146},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2107.00434","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.00434","pdf_url":"https://arxiv.org/pdf/2107.00434","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.2107.00434","doi":"https://doi.org/10.48550/arxiv.2107.00434","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.00434","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:2107.00434","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.00434","pdf_url":"https://arxiv.org/pdf/2107.00434","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":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308066984.pdf","grobid_xml":"https://content.openalex.org/works/W4308066984.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403791298","https://openalex.org/W4312865353","https://openalex.org/W3081254563","https://openalex.org/W4391991042","https://openalex.org/W3202568410","https://openalex.org/W4298014233","https://openalex.org/W4405395621","https://openalex.org/W3158284840","https://openalex.org/W4394929372","https://openalex.org/W3201806127"],"abstract_inverted_index":{"In":[0,35,115],"natural":[1],"conversation":[2],"and":[3,42,54,110,156,188],"interaction,":[4],"our":[5,186],"hands":[6,31,53,85],"often":[7],"overlap":[8],"or":[9],"are":[10,150],"in":[11,46,138],"contact":[12],"with":[13,152],"each":[14],"other.":[15],"Due":[16],"to":[17,50,117,181,189],"the":[18,26,43,51,62,79,100,124,127,134,139,147,153,165,173,183,194],"homogeneous":[19],"appearance":[20],"of":[21,29,61,82,94,185,196],"hands,":[22],"this":[23,36,69],"makes":[24],"estimating":[25,78],"3D":[27,64,80,200],"pose":[28,65,128,141,202],"interacting":[30,84],"from":[32,86,126],"images":[33],"difficult.":[34],"paper":[37],"we":[38,71,120],"demonstrate":[39,182],"that":[40,98,164],"self-similarity,":[41],"resulting":[44],"ambiguities":[45],"assigning":[47],"pixel":[48,197],"observations":[49],"respective":[52],"their":[55],"parts,":[56],"is":[57],"a":[58,74,87,104,111],"major":[59],"cause":[60],"final":[63],"error.":[66],"Motivated":[67],"by":[68],"insight,":[70],"propose":[72],"DIGIT,":[73],"novel":[75],"method":[76,92,187],"for":[77],"poses":[81],"two":[83,95],"single":[88],"monocular":[89],"image.":[90],"The":[91],"consists":[93],"interwoven":[96],"branches":[97],"process":[99],"input":[101],"imagery":[102],"into":[103,192],"per-pixel":[105,135],"semantic":[106],"part":[107,148],"segmentation":[108,125],"mask":[109],"visual":[112,154],"feature":[113],"volume.":[114],"contrast":[116],"prior":[118],"work,":[119],"do":[121,145],"not":[122],"decouple":[123],"estimation":[129,142],"stage,":[130],"but":[131],"rather":[132],"leverage":[133],"probabilities":[136,149],"directly":[137],"downstream":[140],"task.":[143],"To":[144],"so,":[146],"merged":[151],"features":[155],"processed":[157],"via":[158],"fully-convolutional":[159],"layers.":[160],"We":[161,176],"experimentally":[162],"show":[163],"proposed":[166],"approach":[167],"achieves":[168],"new":[169],"state-of-the-art":[170],"performance":[171],"on":[172],"InterHand2.6M":[174],"dataset.":[175],"provide":[177,190],"detailed":[178],"ablation":[179],"studies":[180],"efficacy":[184],"insights":[191],"how":[193],"modelling":[195],"ownership":[198],"affects":[199],"hand":[201],"estimation.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2022-11-07T00:00:00"}