{"id":"https://openalex.org/W4404600626","doi":"https://doi.org/10.1007/s44267-024-00064-9","title":"ViTGaze: gaze following with interaction features in vision transformers","display_name":"ViTGaze: gaze following with interaction features in vision transformers","publication_year":2024,"publication_date":"2024-11-21","ids":{"openalex":"https://openalex.org/W4404600626","doi":"https://doi.org/10.1007/s44267-024-00064-9"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-024-00064-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-024-00064-9","pdf_url":null,"source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1007/s44267-024-00064-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111193633","display_name":"Yuehao Song","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehao Song","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-2711-944X","affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037191476","display_name":"Xinggang Wang","orcid":"https://orcid.org/0000-0001-6732-7823"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinggang Wang","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6732-7823","affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108920046","display_name":"Jingfeng Yao","orcid":"https://orcid.org/0009-0001-7775-0542"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingfeng Yao","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0001-7775-0542","affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665053","display_name":"Wenyu Liu","orcid":"https://orcid.org/0000-0002-4582-7488"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Liu","raw_affiliation_strings":["School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-4582-7488","affiliations":[{"raw_affiliation_string":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001770048","display_name":"J. L. Zhang","orcid":"https://orcid.org/0000-0002-6778-6664"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinglin Zhang","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-6778-6664","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007354180","display_name":"Xiangmin Xu","orcid":"https://orcid.org/0000-0003-4573-5820"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangmin Xu","raw_affiliation_strings":["School of Future Technology, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4573-5820","affiliations":[{"raw_affiliation_string":"School of Future Technology, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037191476"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":{"value":0,"currency":"USD","value_usd":0},"apc_paid":null,"fwci":4.7794,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.95323529,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"2","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9994999766349792,"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":0.9994999766349792,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9871000051498413,"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":0.8505812883377075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7857447862625122},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6897449493408203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6684773564338684},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6597728133201599},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6110357046127319},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47639551758766174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38813191652297974},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36472585797309875}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8505812883377075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857447862625122},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6897449493408203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6684773564338684},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6597728133201599},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6110357046127319},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47639551758766174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38813191652297974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36472585797309875},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44267-024-00064-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-024-00064-9","pdf_url":null,"source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:56d5f551680445bda2bd24e141184ffb","is_oa":true,"landing_page_url":"https://doaj.org/article/56d5f551680445bda2bd24e141184ffb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Visual Intelligence, Vol 2, Iss 1, Pp 1-15 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44267-024-00064-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-024-00064-9","pdf_url":null,"source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008","2097-3330"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G6140824842","display_name":null,"funder_award_id":"2022YFB4500602","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W2063012481","https://openalex.org/W2128592952","https://openalex.org/W2602856279","https://openalex.org/W2883284130","https://openalex.org/W2913668833","https://openalex.org/W2914304175","https://openalex.org/W2979812047","https://openalex.org/W2984401364","https://openalex.org/W2998221292","https://openalex.org/W3035735638","https://openalex.org/W3035747142","https://openalex.org/W3116489684","https://openalex.org/W3135367836","https://openalex.org/W3154013571","https://openalex.org/W3159481202","https://openalex.org/W3204171527","https://openalex.org/W4221148504","https://openalex.org/W4224992933","https://openalex.org/W4225464511","https://openalex.org/W4234552385","https://openalex.org/W4285116117","https://openalex.org/W4292793996","https://openalex.org/W4297792979","https://openalex.org/W4301409532","https://openalex.org/W4309137644","https://openalex.org/W4309800425","https://openalex.org/W4312567381","https://openalex.org/W4386221015","https://openalex.org/W4387542259","https://openalex.org/W4388009985","https://openalex.org/W4389987654","https://openalex.org/W4391853684","https://openalex.org/W4392883923","https://openalex.org/W4393156162","https://openalex.org/W4400721967","https://openalex.org/W4402715878","https://openalex.org/W6600565697","https://openalex.org/W6676297131","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6778485988","https://openalex.org/W6789010468","https://openalex.org/W6796761347","https://openalex.org/W6797466234","https://openalex.org/W6803870738","https://openalex.org/W6809869429","https://openalex.org/W6810774422","https://openalex.org/W6838376339","https://openalex.org/W6854715121"],"related_works":["https://openalex.org/W1880689012","https://openalex.org/W3014378845","https://openalex.org/W4240909707","https://openalex.org/W2059546927","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W3207760378"],"abstract_inverted_index":{"Abstract":[0],"Gaze":[1],"following":[2,81,95],"aims":[3],"to":[4,87,121,146,167,176],"interpret":[5],"human-scene":[6,148],"interactions":[7,115,122],"by":[8,65],"predicting":[9],"the":[10,29,37,45,48,66,113,178,181,196,204],"person\u2019s":[11],"focal":[12],"point":[13],"of":[14,39,47,69,135,180],"gaze.":[15],"Prevailing":[16],"approaches":[17],"often":[18],"adopt":[19],"a":[20,54,77,92,132,136,141],"two-stage":[21],"framework,":[22],"whereby":[23],"multi-modality":[24,212],"information":[25,150],"is":[26,111],"extracted":[27],"in":[28,195,203],"initial":[30],"stage":[31],"for":[32],"gaze":[33,80,94],"target":[34],"prediction.":[35],"Consequently,":[36],"efficacy":[38],"these":[40],"methods":[41,192,213],"highly":[42],"depends":[43],"on":[44,99],"precision":[46],"previous":[49,88],"modality":[50],"extraction.":[51],"Others":[52],"use":[53],"single-modality":[55,79,191],"approach":[56],"with":[57,160,214],"complex":[58],"decoders,":[59],"increasing":[60],"network":[61],"computational":[62],"load.":[63],"Inspired":[64],"remarkable":[67],"success":[68],"pre-trained":[70],"plain":[71],"vision":[72],"transformers":[73],"(ViTs),":[74],"we":[75,130],"introduce":[76],"novel":[78,93],"framework":[82,96,133],"called":[83],"ViTGaze.":[84],"In":[85],"contrast":[86],"methods,":[89],"it":[90],"creates":[91],"based":[97],"mainly":[98],"powerful":[100],"encoders":[101],"(relative":[102],"decoder":[103],"parameters":[104],"less":[105],"than":[106],"1%).":[107],"Our":[108,184],"principal":[109],"insight":[110],"that":[112,158],"inter-token":[114],"within":[116],"self-attention":[117,152],"can":[118],"be":[119],"transferred":[120],"between":[123],"humans":[124],"and":[125,140,207],"scenes.":[126],"Leveraging":[127],"this":[128],"presumption,":[129],"formulate":[131],"consisting":[134],"4D":[137],"interaction":[138,149],"encoder":[139],"2D":[142],"spatial":[143],"guidance":[144],"module":[145],"extract":[147,168],"from":[151],"maps.":[153],"Furthermore,":[154],"our":[155],"investigation":[156],"reveals":[157],"ViT":[159],"self-supervised":[161],"pre-training":[162],"has":[163],"an":[164],"enhanced":[165],"ability":[166],"correlation":[169],"information.":[170],"Many":[171],"experiments":[172],"have":[173],"been":[174],"conducted":[175],"demonstrate":[177],"performance":[179,188,210],"proposed":[182],"method.":[183],"method":[185],"achieves":[186],"state-of-the-art":[187],"among":[189],"all":[190],"(3.4%":[193],"improvement":[194,202],"area":[197],"under":[198],"curve":[199],"score,":[200],"5.1%":[201],"average":[205],"precision)":[206],"very":[208],"comparable":[209],"against":[211],"59%":[215],"fewer":[216],"parameters.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":8}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}