{"id":"https://openalex.org/W7138306929","doi":"https://doi.org/10.1609/aaai.v40i6.42466","title":"Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement","display_name":"Task-Aware 3D Affordance Segmentation via 2D Guidance and Geometric Refinement","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138306929","doi":"https://doi.org/10.1609/aaai.v40i6.42466"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i6.42466","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42466","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i6.42466","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102430731","display_name":"Lian He","orcid":"https://orcid.org/0009-0007-1042-9571"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4210162962","display_name":"Beijing Academy of Science and Technology","ror":"https://ror.org/05ct4fn38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210162962"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lian He","raw_affiliation_strings":["School of Computer Science & Technology, Beijing Institute of Technology\nZhongguancun Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Technology, Beijing Institute of Technology\nZhongguancun Academy","institution_ids":["https://openalex.org/I125839683","https://openalex.org/I4210162962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129683271","display_name":"Meng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Liu","raw_affiliation_strings":["Shandong Jianzhu University\nZhongguancun Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Jianzhu University\nZhongguancun Academy","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125707546","display_name":"Qilang Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132990","display_name":"State Key Laboratory of Cryptology","ror":"https://ror.org/02pn5rj08","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210132990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qilang Ye","raw_affiliation_strings":["VCIP & TMCC & DISSec, College of Computer Science & College of Cryptology and Cyber Science, Nankai University\nZhongguancun Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP & TMCC & DISSec, College of Computer Science & College of Cryptology and Cyber Science, Nankai University\nZhongguancun Academy","institution_ids":["https://openalex.org/I4210132990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129727305","display_name":"Yu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132990","display_name":"State Key Laboratory of Cryptology","ror":"https://ror.org/02pn5rj08","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210132990"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["VCIP & TMCC & DISSec, College of Computer Science & College of Cryptology and Cyber Science, Nankai University\nZhongguancun Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP & TMCC & DISSec, College of Computer Science & College of Cryptology and Cyber Science, Nankai University\nZhongguancun Academy","institution_ids":["https://openalex.org/I4210132990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129751192","display_name":"Xiang Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Deng","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129684506","display_name":"Gangyi Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangyi Ding","raw_affiliation_strings":["School of Computer Science & Technology, Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science & Technology, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":"40","issue":"6","first_page":"4654","last_page":"4662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5235999822616577,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5235999822616577,"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":0.18930000066757202,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.04190000146627426,"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/affordance","display_name":"Affordance","score":0.9664000272750854},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.6651999950408936},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6011000275611877},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5315999984741211},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.5285000205039978},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4781999886035919},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.43779999017715454},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43220001459121704}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.9664000272750854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.762499988079071},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6651999950408936},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6011000275611877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5620999932289124},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.5285000205039978},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.337799996137619},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C135798126","wikidata":"https://www.wikidata.org/wiki/Q2167279","display_name":"Top-down and bottom-up design","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C203527163","wikidata":"https://www.wikidata.org/wiki/Q262959","display_name":"Cuboid","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i6.42466","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42466","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/42466","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/42466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i6.42466","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42466","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"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":{"Understanding":[0],"3D":[1,69,85,124,128,141,149],"scene-level":[2,168],"affordances":[3,41],"from":[4,110],"natural":[5],"language":[6,111],"instructions":[7],"is":[8,132],"essential":[9],"for":[10,29],"enabling":[11],"embodied":[12],"agents":[13],"to":[14,26,47,106,134],"interact":[15],"meaningfully":[16],"in":[17,54,88,144,162,167],"complex":[18],"environments.":[19],"However,":[20],"this":[21],"task":[22],"remains":[23],"challenging":[24],"due":[25],"the":[27,94,116,160],"need":[28],"semantic":[30,82,137],"reasoning":[31,87],"and":[32,57,84,112,146,165],"spatial":[33],"grounding.":[34],"Existing":[35],"methods":[36],"mainly":[37],"focus":[38],"on":[39,153],"object-level":[40],"or":[42],"merely":[43],"lift":[44],"2D":[45,81,102,136],"predictions":[46],"3D,":[48],"neglecting":[49],"rich":[50],"geometric":[51,86,125],"structure":[52],"information":[53],"point":[55],"clouds":[56],"incurring":[58],"high":[59],"computational":[60],"costs.":[61],"To":[62,92,121],"address":[63],"these":[64],"limitations,":[65],"we":[66],"introduce":[67],"Task-Aware":[68],"Scene-level":[70],"Affordance":[71],"segmentation":[72],"(TASA),":[73],"a":[74,89,100,127],"novel":[75],"geometry-optimized":[76],"framework":[77],"that":[78,156],"jointly":[79],"leverages":[80],"cues":[83],"coarse-to-fine":[90],"manner.":[91],"improve":[93],"affordance":[95,103,129,150,169],"detection":[96,104],"efficiency,":[97],"TASA":[98,157],"features":[99],"task-aware":[101],"module":[105,131],"identify":[107],"manipulable":[108],"points":[109],"visual":[113],"inputs,":[114],"guiding":[115],"selection":[117],"of":[118],"task-relevant":[119],"views.":[120],"fully":[122],"exploit":[123],"information,":[126],"refinement":[130],"proposed":[133],"integrate":[135],"priors":[138],"with":[139],"local":[140],"geometry,":[142],"resulting":[143],"accurate":[145],"spatially":[147],"coherent":[148],"masks.":[151],"Experiments":[152],"SceneFun3D":[154],"demonstrate":[155],"significantly":[158],"outperforms":[159],"baselines":[161],"both":[163],"accuracy":[164],"efficiency":[166],"segmentation.":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}