{"id":"https://openalex.org/W2134429682","doi":null,"title":"Active Gesture Recognition using Learned Visual Attention","display_name":"Active Gesture Recognition using Learned Visual Attention","publication_year":1995,"publication_date":"1995-11-27","ids":{"openalex":"https://openalex.org/W2134429682","mag":"2134429682"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.872.9873","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.872.9873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.nips.cc/paper/1079-active-gesture-recognition-using-learned-visual-attention.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533","observed_orcids":["https://orcid.org/0000-0001-5453-8533"]},"institutions":[{"id":"https://openalex.org/I4405268810","display_name":"MIT Media Lab","ror":"https://ror.org/0253jyq40","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405268810"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["Perceptual Computing Group, MIT Media Lab, Cambridge, MA#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-5453-8533","affiliations":[{"raw_affiliation_string":"Perceptual Computing Group, MIT Media Lab, Cambridge, MA#TAB#","institution_ids":["https://openalex.org/I4405268810","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007176508","display_name":"Alex Pentland","orcid":"https://orcid.org/0000-0002-8053-9983","observed_orcids":["https://orcid.org/0000-0002-8053-9983"]},"institutions":[{"id":"https://openalex.org/I4405268810","display_name":"MIT Media Lab","ror":"https://ror.org/0253jyq40","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405268810"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Pentland","raw_affiliation_strings":["Perceptual Computing Group, MIT Media Lab, Cambridge, MA#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-8053-9983","affiliations":[{"raw_affiliation_string":"Perceptual Computing Group, MIT Media Lab, Cambridge, MA#TAB#","institution_ids":["https://openalex.org/I4405268810","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.28231293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"8","issue":null,"first_page":"858","last_page":"864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9574999809265137,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9574999809265137,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.024000000208616257,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.006899999920278788,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/gesture-recognition","display_name":"gesture recognition","score":0.9070000052452087},{"id":"https://openalex.org/keywords/foveated-vision","display_name":"foveated vision","score":0.7459999918937683},{"id":"https://openalex.org/keywords/visual-attention","display_name":"visual attention","score":0.8429999947547913},{"id":"https://openalex.org/keywords/active-camera","display_name":"active camera","score":0.7829999923706055},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7889999747276306},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.8190000057220459},{"id":"https://openalex.org/keywords/human-computer-interaction","display_name":"human-computer interaction","score":0.6119999885559082}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8804316520690918},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.78736412525177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764075994491577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6569256782531738},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6434476375579834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6333373785018921},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5508466362953186},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.4315168261528015},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42547979950904846},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.872.9873","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.872.9873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.nips.cc/paper/1079-active-gesture-recognition-using-learned-visual-attention.pdf","raw_type":"text"},{"id":"mag:2134429682","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/1079-active-gesture-recognition-using-learned-visual-attention.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1499371387","https://openalex.org/W1548502347","https://openalex.org/W2044375425","https://openalex.org/W2065087844","https://openalex.org/W2099873296","https://openalex.org/W2100677568","https://openalex.org/W2104652184","https://openalex.org/W2117732173","https://openalex.org/W2160067530","https://openalex.org/W2164832065","https://openalex.org/W2172246523","https://openalex.org/W3173880854"],"related_works":["https://openalex.org/W2089876633","https://openalex.org/W2940838617","https://openalex.org/W2136974942","https://openalex.org/W7097669201","https://openalex.org/W3217507067","https://openalex.org/W2039165719","https://openalex.org/W3151918095","https://openalex.org/W109693458","https://openalex.org/W7097673604","https://openalex.org/W7100094813"],"abstract_inverted_index":{"trevor,sandy~media.mit.edu":[0],"We":[1],"have":[2],"developed":[3],"a":[4,39,80,86,103],"foveated":[5],"gesture":[6],"recognition":[7],"system":[8,94],"that":[9],"runs":[10],"in":[11],"an":[12,17,26,43],"unconstrained":[13],"office":[14],"environment":[15],"with":[16],"active":[18,44],"camera.":[19],"Us-ing":[20],"vision":[21],"routines":[22],"previously":[23],"implemented":[24],"for":[25],"interactive":[27],"envi-ronment,":[28],"we":[29],"determine":[30],"the":[31,73],"spatial":[32],"location":[33],"of":[34,38,49,75,88],"salient":[35],"body":[36],"parts":[37],"user":[40],"and":[41,78,90],"guide":[42],"camera":[45],"to":[46,60,69,98,100],"obtain":[47],"images":[48],"gestures":[50],"or":[51],"expressions.":[52],"A":[53],"hidden-state":[54],"reinforcement":[55],"learning":[56],"paradigm":[57],"is":[58],"used":[59],"implement":[61],"visual":[62],"attention.":[63],"The":[64],"attention":[65],"module":[66],"selects":[67],"targets":[68],"foveate":[70,99],"based":[71],"on":[72],"goal":[74],"successful":[76],"recognition,":[77],"uses":[79],"new":[81],"multiple-model":[82],"Q-Iearning":[83],"formulation.":[84],"Given":[85],"set":[87],"target":[89],"distractor":[91],"gestures,":[92],"our":[93],"can":[95],"learn":[96],"where":[97],"maximally":[101],"discriminate":[102],"particular":[104],"gesture.":[105],"1":[106]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}