{"id":"https://openalex.org/W4411551045","doi":"https://doi.org/10.1109/tai.2025.3581897","title":"Exploring Mutual Cross-Modal Attention for Context-Aware Human Affordance Generation","display_name":"Exploring Mutual Cross-Modal Attention for Context-Aware Human Affordance Generation","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4411551045","doi":"https://doi.org/10.1109/tai.2025.3581897"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2025.3581897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3581897","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Prasun Roy","orcid":"https://orcid.org/0000-0002-1733-5670"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Prasun Roy","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia","University of Technology Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1733-5670","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"University of Technology Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079312227","display_name":"Saumik Bhattacharya","orcid":"https://orcid.org/0000-0003-1273-7969"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Saumik Bhattacharya","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur, India"],"raw_orcid":"https://orcid.org/0000-0003-1273-7969","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088628484","display_name":"Subhankar Ghosh","orcid":"https://orcid.org/0000-0003-3242-3406"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Subhankar Ghosh","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia","University of Technology Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3242-3406","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"University of Technology Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068803496","display_name":"Umapada Pal","orcid":"https://orcid.org/0000-0002-5426-2618"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Umapada Pal","raw_affiliation_strings":["Indian Statistical Institute, Kolkata, India","Umapada Pal is with the Indian Statistical Institute, Kolkata, India"],"raw_orcid":"https://orcid.org/0000-0002-5426-2618","affiliations":[{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]},{"raw_affiliation_string":"Umapada Pal is with the Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045600512","display_name":"Michael Blumenstein","orcid":"https://orcid.org/0000-0002-9908-3744"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Michael Blumenstein","raw_affiliation_strings":["University of Technology Sydney, Sydney, NSW, Australia","University of Technology Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9908-3744","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"University of Technology Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13956217,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"2","first_page":"806","last_page":"817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9936000108718872,"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":0.9936000108718872,"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":0.9934999942779541,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/affordance","display_name":"Affordance","score":0.9429115056991577},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6703678369522095},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6181575059890747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39784473180770874},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.32232221961021423},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2750226855278015},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.26904571056365967},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.17727920413017273}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.9429115056991577},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6703678369522095},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6181575059890747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39784473180770874},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.32232221961021423},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2750226855278015},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26904571056365967},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.17727920413017273},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2025.3581897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2025.3581897","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1891689858","https://openalex.org/W1965555277","https://openalex.org/W2013640163","https://openalex.org/W2080873731","https://openalex.org/W2083620785","https://openalex.org/W2105747153","https://openalex.org/W2108598243","https://openalex.org/W2507296351","https://openalex.org/W2519537448","https://openalex.org/W2559085405","https://openalex.org/W2769102608","https://openalex.org/W2883938080","https://openalex.org/W2916798096","https://openalex.org/W2962984928","https://openalex.org/W2963049618","https://openalex.org/W2963091558","https://openalex.org/W2963324990","https://openalex.org/W2963635127","https://openalex.org/W2983796203","https://openalex.org/W3035707711","https://openalex.org/W3110387477","https://openalex.org/W3176146104","https://openalex.org/W3176892444","https://openalex.org/W3199003182","https://openalex.org/W4213203506","https://openalex.org/W4230210808","https://openalex.org/W4288079574","https://openalex.org/W4293363567","https://openalex.org/W4313004678","https://openalex.org/W4313061091","https://openalex.org/W4323647495","https://openalex.org/W4377711491","https://openalex.org/W4386065649","https://openalex.org/W4386071839","https://openalex.org/W4386075553","https://openalex.org/W4386076076","https://openalex.org/W4386076520","https://openalex.org/W4387968992","https://openalex.org/W4402727359"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W2346831895","https://openalex.org/W2248634132","https://openalex.org/W3049116993","https://openalex.org/W1541884709","https://openalex.org/W2589081601"],"abstract_inverted_index":{"Human":[0],"affordance":[1,59,85,202],"learning":[2],"investigates":[3],"contextually":[4],"relevant":[5],"novel":[6,76],"pose":[7,13,41,140,148,180],"prediction":[8,60,86],"such":[9],"that":[10],"the":[11,20,23,35,46,52,68,81,108,121,130,154,159,163,172,178,185,197],"estimated":[12],"represents":[14],"a":[15,75,114,118,124,138,143,151],"valid":[16],"human":[17,58,147,201],"action":[18,43],"within":[19,120],"scene.":[21],"While":[22],"task":[24],"is":[25,100],"fundamental":[26],"to":[27,79,105,170],"machine":[28],"perception":[29],"and":[30,42,49,55,174,188],"automated":[31],"interactive":[32],"navigation":[33],"agents,":[34],"exponentially":[36],"large":[37],"number":[38],"of":[39,145,200],"probable":[40,115],"variations":[44],"make":[45],"problem":[47,109],"challenging":[48],"non-trivial.":[50],"However,":[51],"existing":[53,146],"datasets":[54],"methods":[56],"for":[57,84,117,177],"in":[61,67],"2D":[62,206],"scenes":[63],"are":[64],"significantly":[65],"limited":[66],"literature.":[69],"In":[70,162],"this":[71],"paper,":[72],"we":[73,112,136,166],"propose":[74],"cross-attention":[77],"mechanism":[78],"encode":[80],"scene":[82,122,132],"context":[83,133,156,187],"by":[87,182],"mutually":[88],"attending":[89],"spatial":[90],"feature":[91],"maps":[92],"from":[93,142],"two":[94,168],"different":[95],"modalities.":[96],"The":[97],"proposed":[98],"method":[99],"disentangled":[101],"among":[102],"individual":[103],"subtasks":[104],"efficiently":[106],"reduce":[107],"complexity.":[110],"First,":[111],"sample":[113,171],"location":[116],"person":[119],"using":[123,150],"variational":[125],"autoencoder":[126],"(VAE)":[127],"conditioned":[128],"on":[129,153,184],"global":[131],"encoding.":[134],"Next,":[135],"predict":[137],"potential":[139],"template":[141,181,189],"set":[144],"candidates":[149],"classifier":[152],"local":[155,186],"encoding":[157],"around":[158],"predicted":[160,179],"location.":[161],"subsequent":[164],"steps,":[165],"use":[167],"VAEs":[169],"scale":[173],"deformation":[175],"parameters":[176],"conditioning":[183],"class.":[190],"Our":[191],"experiments":[192],"show":[193],"significant":[194],"improvements":[195],"over":[196],"previous":[198],"baseline":[199],"injection":[203],"into":[204],"complex":[205],"scenes.":[207]},"counts_by_year":[],"updated_date":"2026-02-04T23:10:29.248076","created_date":"2025-10-10T00:00:00"}