{"id":"https://openalex.org/W3015378547","doi":"https://doi.org/10.1109/icassp40776.2020.9054167","title":"A Deep Learning Approach to Object Affordance Segmentation","display_name":"A Deep Learning Approach to Object Affordance Segmentation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015378547","doi":"https://doi.org/10.1109/icassp40776.2020.9054167","mag":"3015378547"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.08644","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015117681","display_name":"Spyridon Thermos","orcid":"https://orcid.org/0000-0001-5458-6906"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Spyridon Thermos","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071585254","display_name":"Petros Daras","orcid":"https://orcid.org/0000-0003-3814-6710"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Petros Daras","raw_affiliation_strings":["Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2358","last_page":"2362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991999864578247,"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":0.9991999864578247,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10036","display_name":"Advanced Neural Network Applications","score":0.9902999997138977,"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":0.8957411050796509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7928011417388916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7346749305725098},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6425919532775879},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5738131999969482},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.5501176714897156},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5355837941169739},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4949755072593689},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.475025475025177},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4630705416202545},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35457032918930054},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3296544849872589},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.24632757902145386}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.8957411050796509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928011417388916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7346749305725098},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6425919532775879},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5738131999969482},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.5501176714897156},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5355837941169739},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4949755072593689},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.475025475025177},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4630705416202545},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35457032918930054},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3296544849872589},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.24632757902145386},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.08644","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.08644","pdf_url":"https://arxiv.org/pdf/2004.08644","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ir.lib.uth.gr:11615/79695","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/79695","pdf_url":null,"source":{"id":"https://openalex.org/S4306400243","display_name":"University of Thessaly Institutional Repository (University of Thessaly)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145722265","host_organization_name":"University of Thessaly","host_organization_lineage":["https://openalex.org/I145722265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings","raw_type":"conferenceItem"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.08644","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.08644","pdf_url":"https://arxiv.org/pdf/2004.08644","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":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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W623420257","https://openalex.org/W639708223","https://openalex.org/W1495986922","https://openalex.org/W1522301498","https://openalex.org/W1524405667","https://openalex.org/W1533861849","https://openalex.org/W1580568969","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W2108598243","https://openalex.org/W2124351162","https://openalex.org/W2145546283","https://openalex.org/W2149173366","https://openalex.org/W2170946858","https://openalex.org/W2302255633","https://openalex.org/W2397563792","https://openalex.org/W2561523096","https://openalex.org/W2605910384","https://openalex.org/W2741998915","https://openalex.org/W2773765248","https://openalex.org/W2798897443","https://openalex.org/W2807052771","https://openalex.org/W2884561390","https://openalex.org/W2899771611","https://openalex.org/W2904070579","https://openalex.org/W2962835968","https://openalex.org/W2962984928","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963727650","https://openalex.org/W2964121744","https://openalex.org/W2981750895","https://openalex.org/W2983465317","https://openalex.org/W3106250896","https://openalex.org/W4385490361","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6634616096","https://openalex.org/W6637373629","https://openalex.org/W6639824700","https://openalex.org/W6698183232","https://openalex.org/W6735463952","https://openalex.org/W6756040250","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W3014080459","https://openalex.org/W4386875794","https://openalex.org/W2951631158","https://openalex.org/W4288313544","https://openalex.org/W2976611405","https://openalex.org/W3039174484","https://openalex.org/W4287728368","https://openalex.org/W3163786145"],"abstract_inverted_index":{"Learning":[0],"to":[1,103,179,188],"understand":[2],"and":[3,53,58,100,111,122,153],"infer":[4,104],"object":[5,24,51,59,120],"functionalities":[6],"is":[7,87,101],"an":[8,84],"important":[9],"step":[10],"towards":[11],"robust":[12],"visual":[13],"intelligence.":[14],"Significant":[15],"research":[16],"efforts":[17],"have":[18],"recently":[19],"focused":[20],"on":[21,50,55,183],"segmenting":[22],"the":[23,33,71,94,98,117,132,136,144],"parts":[25],"that":[26,69,86,130,172],"enable":[27],"specific":[28],"types":[29,156],"of":[30,74,92,97,135,149,157,161,167],"human-object":[31,75,150],"interaction,":[32],"so-called":[34],"\"object":[35],"affordances\".":[36],"However,":[37],"most":[38],"works":[39],"treat":[40],"it":[41],"as":[42],"a":[43,66,127],"static":[44,112],"semantic":[45],"segmentation":[46],"problem,":[47],"focusing":[48],"solely":[49],"appearance":[52],"relying":[54],"strong":[56],"supervision":[57],"detection.":[60],"In":[61,80],"this":[62],"paper,":[63],"we":[64,82,142],"propose":[65],"novel":[67],"approach":[68],"exploits":[70],"spatio-temporal":[72],"nature":[73],"interaction":[76,137,151],"for":[77,119,191],"affordance":[78,106,197],"segmentation.":[79],"particular,":[81],"design":[83],"autoencoder":[85],"trained":[88],"using":[89,126],"ground-truth":[90],"labels":[91,107,121],"only":[93],"last":[95],"frame":[96],"sequence,":[99],"able":[102,187],"pixel-wise":[105,162],"in":[108,159,195],"both":[109],"videos":[110],"images.":[113],"Our":[114],"model":[115,174],"surpasses":[116],"need":[118],"bounding":[123],"boxes":[124],"by":[125],"soft-attention":[128],"mechanism":[129],"enables":[131],"implicit":[133],"localization":[134],"hotspot.":[138],"For":[139],"evaluation":[140],"purposes,":[141],"introduce":[143],"SOR3D-AFF":[145],"corpus,":[146],"which":[147],"consists":[148],"sequences":[152],"supports":[154],"9":[155],"affordances":[158,190],"terms":[160],"annotation,":[163],"covering":[164],"typical":[165],"manipulations":[166],"tool-like":[168],"objects.":[169],"We":[170],"show":[171],"our":[173],"achieves":[175],"competitive":[176],"results":[177],"compared":[178],"strongly":[180],"supervised":[181],"methods":[182],"SOR3D-AFF,":[184],"while":[185],"being":[186],"predict":[189],"similar":[192],"unseen":[193],"objects":[194],"two":[196],"image-only":[198],"datasets.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}