{"id":"https://openalex.org/W4413945182","doi":"https://doi.org/10.1109/icra55743.2025.11127830","title":"Simultaneous Localization and Affordance Prediction of Tasks from Egocentric Video","display_name":"Simultaneous Localization and Affordance Prediction of Tasks from Egocentric Video","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945182","doi":"https://doi.org/10.1109/icra55743.2025.11127830"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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":"https://openalex.org/A5093402712","display_name":"Zach Chavis","orcid":null},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zach Chavis","raw_affiliation_strings":["University of Minnesota,Department of Computer, Science and Minneapolis, Engineering (CS&E),MN,US,55414"],"affiliations":[{"raw_affiliation_string":"University of Minnesota,Department of Computer, Science and Minneapolis, Engineering (CS&E),MN,US,55414","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101538702","display_name":"Hyun Soo Park","orcid":"https://orcid.org/0000-0001-6613-0738"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyun Soo Park","raw_affiliation_strings":["University of Minnesota,Department of Computer, Science and Minneapolis, Engineering (CS&E),MN,US,55414"],"affiliations":[{"raw_affiliation_string":"University of Minnesota,Department of Computer, Science and Minneapolis, Engineering (CS&E),MN,US,55414","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007324122","display_name":"Stephen J. Guy","orcid":"https://orcid.org/0000-0001-8986-5817"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen J. Guy","raw_affiliation_strings":["University of Minnesota,Department of Computer, Science and Minneapolis, Engineering (CS&E),MN,US,55414"],"affiliations":[{"raw_affiliation_string":"University of Minnesota,Department of Computer, Science and Minneapolis, Engineering (CS&E),MN,US,55414","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5093402712"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28758937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9525","last_page":"9532"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9922000169754028,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9922000169754028,"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":0.9814000129699707,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9753000140190125,"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":0.9591444134712219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7326841354370117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.445936918258667},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43902382254600525},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41013872623443604}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.9591444134712219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7326841354370117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.445936918258667},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43902382254600525},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41013872623443604}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1971086298","https://openalex.org/W2443846596","https://openalex.org/W2962984928","https://openalex.org/W3034578524","https://openalex.org/W3109597949","https://openalex.org/W3201312429","https://openalex.org/W3205786327","https://openalex.org/W4200150166","https://openalex.org/W4312396969","https://openalex.org/W4312878367","https://openalex.org/W4383108296","https://openalex.org/W4385430678","https://openalex.org/W4386065350","https://openalex.org/W4386083079","https://openalex.org/W4399070666","https://openalex.org/W4402727748","https://openalex.org/W4402754274","https://openalex.org/W4412684057"],"related_works":["https://openalex.org/W2417026147","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"shown":[4],"great":[5],"success":[6],"as":[7],"foundational":[8],"models":[9,24],"for":[10,70,158],"downstream":[11],"vision":[12],"and":[13,31,77,126],"natural":[14,163],"language":[15],"applications":[16],"in":[17,56,162],"a":[18,41,97,103,107,121],"variety":[19],"of":[20,80,95,102,109,156],"domains.":[21],"However,":[22],"these":[23],"are":[25,131],"limited":[26],"to":[27,44,53,73,84,99,133,145,149],"reasoning":[28],"over":[29,106],"objects":[30],"actions":[32],"currently":[33],"visible":[34],"on":[35,118,127],"the":[36,45,71,78,85,93,136],"image":[37],"plane.":[38],"We":[39,88],"present":[40],"spatial":[42,62],"extension":[43],"VLM,":[46],"which":[47],"leverages":[48],"spatially-localized":[49],"egocentric":[50,86,147],"video":[51],"demonstrations":[52],"augment":[54],"VLMs":[55],"two":[57],"ways":[58],"-":[59],"through":[60],"understanding":[61],"task-affordances,":[63],"i.e.":[64],"where":[65,120],"an":[66],"agent":[67],"must":[68],"be":[69],"task":[72,82,122],"physically":[74],"take":[75,124],"place,":[76],"localization":[79],"that":[81],"relative":[83],"viewer.":[87],"show":[89],"our":[90],"approach":[91,113],"outperforms":[92],"baseline":[94],"using":[96],"VLM":[98],"map":[100],"similarity":[101],"task's":[104],"description":[105],"set":[108],"location-tagged":[110],"images.":[111],"Our":[112],"has":[114],"less":[115],"error":[116],"both":[117],"predicting":[119,128],"may":[123],"place":[125],"what":[129],"tasks":[130,160],"likely":[132],"happen":[134],"at":[135],"current":[137],"location.":[138],"The":[139],"resulting":[140],"representation":[141],"will":[142],"enable":[143],"robots":[144],"use":[146],"sensing":[148],"navigate":[150],"to,":[151],"or":[152],"around,":[153],"physical":[154],"regions":[155],"interest":[157],"novel":[159],"specified":[161],"language.":[164]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}