{"id":"https://openalex.org/W1981127554","doi":"https://doi.org/10.1109/ipta.2014.7001916","title":"Sensing, predicting, and utilizing human visual attention","display_name":"Sensing, predicting, and utilizing human visual attention","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W1981127554","doi":"https://doi.org/10.1109/ipta.2014.7001916","mag":"1981127554"},"language":"en","primary_location":{"id":"doi:10.1109/ipta.2014.7001916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta.2014.7001916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 4th International Conference on Image Processing Theory, Tools and Applications (IPTA)","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/A5045996641","display_name":"Yoichi Sato","orcid":"https://orcid.org/0000-0003-0097-4537"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yoichi Sato","raw_affiliation_strings":["Institute of Industrial Science, The University of Tokyo, Japan","Institute of Industrial Science, The University of Tokyo,,Japan"],"affiliations":[{"raw_affiliation_string":"Institute of Industrial Science, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Institute of Industrial Science, The University of Tokyo,,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5045996641"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05851055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.995199978351593,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.995199978351593,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9837999939918518,"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/computer-science","display_name":"Computer science","score":0.7767015099525452},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.7513822317123413},{"id":"https://openalex.org/keywords/fixation","display_name":"Fixation (population genetics)","score":0.7323133945465088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7078737020492554},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6345475316047668},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.6254427433013916},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.6105788350105286},{"id":"https://openalex.org/keywords/visual-field","display_name":"Visual field","score":0.562712550163269},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.551374614238739},{"id":"https://openalex.org/keywords/kadir\u2013brady-saliency-detector","display_name":"Kadir\u2013Brady saliency detector","score":0.5400605201721191},{"id":"https://openalex.org/keywords/gaze-contingency-paradigm","display_name":"Gaze-contingency paradigm","score":0.4321445822715759},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.42861244082450867},{"id":"https://openalex.org/keywords/saliency-map","display_name":"Saliency map","score":0.42375633120536804},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.33145272731781006},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14927396178245544},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.11169305443763733},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09803873300552368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767015099525452},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.7513822317123413},{"id":"https://openalex.org/C146249460","wikidata":"https://www.wikidata.org/wiki/Q2914991","display_name":"Fixation (population genetics)","level":3,"score":0.7323133945465088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7078737020492554},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6345475316047668},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.6254427433013916},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.6105788350105286},{"id":"https://openalex.org/C2776058522","wikidata":"https://www.wikidata.org/wiki/Q2364768","display_name":"Visual field","level":2,"score":0.562712550163269},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.551374614238739},{"id":"https://openalex.org/C202227193","wikidata":"https://www.wikidata.org/wiki/Q6345568","display_name":"Kadir\u2013Brady saliency detector","level":4,"score":0.5400605201721191},{"id":"https://openalex.org/C164280684","wikidata":"https://www.wikidata.org/wiki/Q5529040","display_name":"Gaze-contingency paradigm","level":4,"score":0.4321445822715759},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.42861244082450867},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.42375633120536804},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.33145272731781006},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14927396178245544},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.11169305443763733},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09803873300552368},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipta.2014.7001916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipta.2014.7001916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 4th International Conference on Image Processing Theory, Tools and Applications (IPTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4099999964237213,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2805433183","https://openalex.org/W2001667162","https://openalex.org/W1978345117","https://openalex.org/W2998848029","https://openalex.org/W2399628449","https://openalex.org/W2782976991","https://openalex.org/W2007136456","https://openalex.org/W2384593126","https://openalex.org/W2762783218","https://openalex.org/W1981127554"],"abstract_inverted_index":{"Summary":[0],"is":[1,97,131,144],"only":[2],"given:":[3],"In":[4],"this":[5,110],"talk,":[6],"I":[7,170,181],"will":[8,171,182],"describe":[9],"our":[10,66,71,105,176,186,212,248],"recent":[11,187],"works":[12],"on":[13,55,109],"human":[14,221,236],"visual":[15,24,34,60,78,88,94,121,196,209,227,249],"attention":[16],"from":[17],"three":[18],"aspects:":[19],"sensing,":[20],"predicting,":[21],"and":[22,36,53,80,178,231,273],"utilizing":[23],"attention.":[25],"Over":[26],"the":[27,31,48,134,138,148,152,173,207,215,218,226],"last":[28],"two":[29],"decades,":[30],"concept":[32],"of":[33,44,59,104,137,151,175,195,220,243,267],"saliency":[35,63,89,95,122,135,197,210,250],"its":[37],"computational":[38,57,193],"models":[39,64],"have":[40],"attracted":[41],"a":[42,56,87,93,114,142,164,191,240,256],"lot":[43],"interest,":[45],"inspired":[46],"by":[47,51,70,77,92],"seminal":[49],"work":[50],"Koch":[52],"Ullman":[54],"model":[58,96,194,213,251],"saliency.":[61],"Visual":[62],"predict":[65],"eye":[67,268],"fixations":[68],"driven":[69],"vision":[72],"system's":[73],"bottom-up":[74],"control":[75],"triggered":[76],"stimuli,":[79],"it":[81],"has":[82],"been":[83],"shown":[84],"experimentally":[85],"that":[86,141,156,217,247],"map":[90],"computed":[91],"highly":[98],"correlated":[99],"with":[100],"an":[101],"actual":[102],"distribution":[103],"fixation":[106,204,237],"points.":[107,205],"Based":[108],"observation,":[111],"we":[112,157,261],"introduce":[113],"method":[115,177],"for":[116,198,270],"estimating":[117],"gaze":[118,153,203],"directions":[119],"using":[120,235],"maps":[123,136],"without":[124],"explicit":[125],"personal":[126],"calibration.":[127],"The":[128],"key":[129],"idea":[130],"to":[132,166,189],"use":[133],"video":[139],"frames":[140],"person":[143],"looking":[145],"at":[146],"as":[147],"probability":[149],"distributions":[150],"points":[154],"so":[155],"can":[158],"avoid":[159],"cumbersome":[160],"calibration":[161,168],"procedures":[162],"asking":[163],"user":[165],"fixate":[167],"targets.":[169],"explain":[172],"details":[174],"experimental":[179],"results.":[180],"also":[183],"talk":[184,263],"about":[185,264],"attempt":[188],"develop":[190],"new":[192],"better":[199],"accuracy":[200,254],"in":[201,239],"predicting":[202],"Unlike":[206],"existing":[208],"models,":[211],"elaborates":[214],"fact":[216],"characteristics":[219],"eyes":[222],"vary":[223],"significantly":[224],"within":[225],"field,":[228],"e.g.,":[229],"fovea":[230],"peripheral":[232],"vision.":[233],"Experiments":[234],"data":[238],"wide":[241],"field":[242],"view":[244],"setting":[245],"demonstrate":[246],"achieves":[252],"higher":[253],"than":[255],"current":[257],"state-of-the-art":[258],"model.":[259],"Lastly,":[260],"briefly":[262],"several":[265],"applications":[266],"movements":[269],"activity":[271],"recognition":[272],"image":[274],"analysis.":[275]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}