{"id":"https://openalex.org/W4416031407","doi":"https://doi.org/10.1109/iccv51701.2025.01368","title":"2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos","display_name":"2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416031407","doi":"https://doi.org/10.1109/iccv51701.2025.01368"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.09320","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011079393","display_name":"Marvin Heidinger","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marvin Heidinger","raw_affiliation_strings":["Technische Universit¨at Darmstadt,Computer Science Department,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit¨at Darmstadt,Computer Science Department,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023965680","display_name":"Snehal Jauhri","orcid":"https://orcid.org/0000-0001-9134-3989"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Snehal Jauhri","raw_affiliation_strings":["Technische Universit¨at Darmstadt,Computer Science Department,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit¨at Darmstadt,Computer Science Department,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024771523","display_name":"Vignesh Prasad","orcid":"https://orcid.org/0000-0002-9729-2454"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vignesh Prasad","raw_affiliation_strings":["Technische Universit¨at Darmstadt,Computer Science Department,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit¨at Darmstadt,Computer Science Department,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026055366","display_name":"Georgia Chalvatzaki","orcid":"https://orcid.org/0000-0002-5055-199X"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georgia Chalvatzaki","raw_affiliation_strings":["Technische Universit¨at Darmstadt,Computer Science Department,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit¨at Darmstadt,Computer Science Department,Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31512782"],"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":"14743","last_page":"14753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.6097000241279602,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.6097000241279602,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.09440000355243683,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.06300000101327896,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/affordance","display_name":"Affordance","score":0.9926000237464905},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7211999893188477},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6134999990463257},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.44040000438690186},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.36010000109672546}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.9926000237464905},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7211999893188477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6886000037193298},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6134999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5544000267982483},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5297999978065491},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36010000109672546},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.09320","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.09320","pdf_url":"https://arxiv.org/pdf/2503.09320","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,"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.2503.09320","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.09320","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.09320","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.09320","pdf_url":"https://arxiv.org/pdf/2503.09320","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,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"When":[0],"interacting":[1,114],"with":[2,115],"objects,":[3],"humans":[4],"effectively":[5],"reason":[6],"about":[7],"which":[8],"regions":[9,21,34,152],"of":[10,22,98],"objects":[11],"are":[12,153],"viable":[13],"for":[14,29,74,106,142],"an":[15,160],"intended":[16],"action,":[17],"i.e.,":[18,109,155],"the":[19,23,37,60,99,130],"affordance":[20,55,76,90,94,124,139,151],"object.":[24],"They":[25],"can":[26,156],"also":[27,104],"account":[28],"subtle":[30],"differences":[31],"in":[32,138,167],"object":[33,64,89],"based":[35],"on":[36,129],"task":[38],"to":[39,49,62],"be":[40,50,157],"performed":[41],"and":[42,93,113,132],"whether":[43],"one":[44,116],"or":[45,117],"two":[46,110],"hands":[47,111],"need":[48],"used.":[51],"However,":[52],"current":[53],"vision-based":[54],"prediction":[56,125],"methods":[57],"often":[58],"reduce":[59],"problem":[61],"naive":[63],"part":[65],"segmentation.":[66],"In":[67],"this":[68],"work,":[69],"we":[70,146],"propose":[71],"a":[72,122,163],"framework":[73],"extracting":[75],"data":[77,103],"from":[78],"human":[79],"activity":[80,100],"video":[81],"datasets.":[82],"Our":[83],"extracted":[84],"2HANDS":[85],"dataset":[86,131],"contains":[87],"precise":[88],"region":[91,140],"segmentations":[92],"class-labels":[95],"as":[96],"narrations":[97],"performed.":[101],"The":[102],"accounts":[105],"bimanual":[107],"actions,":[108],"co-ordinating":[112],"more":[118],"objects.":[119],"We":[120],"present":[121],"VLM-based":[123],"model,":[126],"2HandedAfforder,":[127],"trained":[128],"demonstrate":[133],"superior":[134],"performance":[135],"over":[136],"baselines":[137],"segmentation":[141],"various":[143],"activities.":[144],"Finally,":[145],"show":[147],"that":[148],"our":[149],"predicted":[150],"actionable,":[154],"used":[158],"by":[159],"agent":[161],"performing":[162],"task,":[164],"through":[165],"demonstration":[166],"robotic":[168],"manipulation":[169],"scenarios.":[170],"Project-website:":[171],"https://sites.google.com/view/2handedafforder":[172]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}