{"id":"https://openalex.org/W4402916414","doi":"https://doi.org/10.1109/cvprw63382.2024.00067","title":"Gaze Scanpath Transformer: Predicting Visual Search Target by Spatiotemporal Semantic Modeling of Gaze Scanpath","display_name":"Gaze Scanpath Transformer: Predicting Visual Search Target by Spatiotemporal Semantic Modeling of Gaze Scanpath","publication_year":2024,"publication_date":"2024-06-17","ids":{"openalex":"https://openalex.org/W4402916414","doi":"https://doi.org/10.1109/cvprw63382.2024.00067"},"language":"en","primary_location":{"id":"doi:10.1109/cvprw63382.2024.00067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw63382.2024.00067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5035981523","display_name":"Takumi Nishiyasu","orcid":"https://orcid.org/0000-0002-8464-7500"},"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":false,"raw_author_name":"Takumi Nishiyasu","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","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":false,"raw_author_name":"Yoichi Sato","raw_affiliation_strings":["The University of Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":2.4667,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90016564,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"625","last_page":"635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9976000189781189,"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9976000189781189,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9544000029563904,"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/gaze","display_name":"Gaze","score":0.8688352704048157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.778276801109314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6262248754501343},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5313594341278076},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4688207805156708},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36781319975852966},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.058452457189559937}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8688352704048157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.778276801109314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6262248754501343},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5313594341278076},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4688207805156708},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36781319975852966},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.058452457189559937},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvprw63382.2024.00067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvprw63382.2024.00067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","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":51,"referenced_works":["https://openalex.org/W1566135517","https://openalex.org/W1970544143","https://openalex.org/W1994658111","https://openalex.org/W2020938553","https://openalex.org/W2024333247","https://openalex.org/W2033362164","https://openalex.org/W2034619334","https://openalex.org/W2052423441","https://openalex.org/W2060634628","https://openalex.org/W2098916361","https://openalex.org/W2124386111","https://openalex.org/W2126698740","https://openalex.org/W2147831380","https://openalex.org/W2151324917","https://openalex.org/W2162454958","https://openalex.org/W2163352848","https://openalex.org/W2312708194","https://openalex.org/W2313121588","https://openalex.org/W2577026679","https://openalex.org/W2625513908","https://openalex.org/W2805723548","https://openalex.org/W2884107779","https://openalex.org/W2889371542","https://openalex.org/W2891817692","https://openalex.org/W2910628332","https://openalex.org/W2922458387","https://openalex.org/W2964279441","https://openalex.org/W2967608553","https://openalex.org/W2971402829","https://openalex.org/W2982035692","https://openalex.org/W3000387804","https://openalex.org/W3021066554","https://openalex.org/W3022720704","https://openalex.org/W3034964972","https://openalex.org/W3094502228","https://openalex.org/W3131500185","https://openalex.org/W3154689434","https://openalex.org/W3176796859","https://openalex.org/W4200268870","https://openalex.org/W4211165038","https://openalex.org/W4229726131","https://openalex.org/W4292787432","https://openalex.org/W4292793998","https://openalex.org/W4312887977","https://openalex.org/W4386057737","https://openalex.org/W4386066204","https://openalex.org/W4389296917","https://openalex.org/W4394625686","https://openalex.org/W6636494156","https://openalex.org/W6795140394","https://openalex.org/W6860402221"],"related_works":["https://openalex.org/W1880689012","https://openalex.org/W3014378845","https://openalex.org/W4240909707","https://openalex.org/W2059546927","https://openalex.org/W3207760378","https://openalex.org/W4386072035","https://openalex.org/W2161294397","https://openalex.org/W2012644758","https://openalex.org/W2981907288","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,12,17,39,74,84],"new":[3],"method,":[4],"called":[5],"the":[6,31,41,50,60,80,102,105,111,116,123,143],"Gaze":[7],"Scanpath":[8],"Transformer,":[9],"for":[10,23,160],"predicting":[11],"search":[13,19,26,76,161],"target":[14,77,162],"category":[15],"during":[16],"visual":[18,25,75],"task.":[20],"Previous":[21],"methods":[22,43],"estimating":[24],"targets":[27],"focus":[28],"solely":[29],"on":[30,65,79,133],"image":[32,90,117,134],"features":[33,92,136],"at":[34,93,137],"gaze":[35,54,66,85,94,138],"fixation":[36,95,139],"positions.":[37,96,140],"As":[38],"result,":[40],"previous":[42],"are":[44],"unable":[45],"to":[46,127],"take":[47],"into":[48,115],"account":[49],"spatiotemporal":[51,81],"information":[52,82,129],"of":[53,59,83,107,113],"scanpaths":[55],"and":[56,87,104,110,120,131],"lack":[57],"consideration":[58],"semantic":[61,91,118,135],"interrelationships":[62,88],"between":[63],"objects":[64],"fixations.":[67],"In":[68],"contrast,":[69],"our":[70,148],"method":[71,150],"can":[72],"estimate":[73],"based":[78],"scanpath":[86],"among":[89],"This":[97],"is":[98],"achieved":[99],"by":[100,121],"embedding":[101],"position":[103],"duration":[106],"each":[108],"fixation,":[109],"order":[112],"fixations":[114],"features,":[119],"using":[122,142],"model\u2019s":[124],"attention":[125],"mechanism":[126],"facilitate":[128],"exchange":[130],"emphasis":[132],"Evaluation":[141],"COCO-Search18":[144],"dataset":[145],"demonstrates":[146],"that":[147],"proposed":[149],"achieves":[151],"significant":[152],"performance":[153],"improvements":[154],"over":[155],"other":[156],"state-ofthe-art":[157],"baseline":[158],"models":[159],"prediction.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}