{"id":"https://openalex.org/W4328008203","doi":"https://doi.org/10.1109/tcsvt.2023.3258962","title":"Spatio-Temporal Feature Pyramid Interactive Attention Network for Egocentric Gaze Prediction","display_name":"Spatio-Temporal Feature Pyramid Interactive Attention Network for Egocentric Gaze Prediction","publication_year":2023,"publication_date":"2023-03-20","ids":{"openalex":"https://openalex.org/W4328008203","doi":"https://doi.org/10.1109/tcsvt.2023.3258962"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2023.3258962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3258962","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5102814931","display_name":"Ming Yuan","orcid":"https://orcid.org/0000-0002-6577-5611"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yuan","raw_affiliation_strings":["School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6577-5611","affiliations":[{"raw_affiliation_string":"School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086765632","display_name":"Xu Dong","orcid":"https://orcid.org/0000-0002-0116-2760"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Xu","raw_affiliation_strings":["School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.5318,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.64858608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"33","issue":"10","first_page":"5790","last_page":"5801"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T13731","display_name":"Advanced Computing and Algorithms","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8101534843444824},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.7485214471817017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7251811027526855},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6058858036994934},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5616480112075806},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5265905261039734},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49694278836250305},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4842255115509033},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47048547863960266},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4699452221393585},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.46569737792015076},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12286803126335144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07562384009361267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101534843444824},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.7485214471817017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7251811027526855},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6058858036994934},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5616480112075806},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5265905261039734},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49694278836250305},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4842255115509033},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47048547863960266},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4699452221393585},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.46569737792015076},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12286803126335144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07562384009361267},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2023.3258962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2023.3258962","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7337877799","display_name":null,"funder_award_id":"81772005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W1510835000","https://openalex.org/W1517086206","https://openalex.org/W1522301498","https://openalex.org/W1934890906","https://openalex.org/W1971022913","https://openalex.org/W2037328649","https://openalex.org/W2071555787","https://openalex.org/W2078903912","https://openalex.org/W2098702446","https://openalex.org/W2102148524","https://openalex.org/W2112845172","https://openalex.org/W2114873786","https://openalex.org/W2119577735","https://openalex.org/W2128272608","https://openalex.org/W2133589685","https://openalex.org/W2135957164","https://openalex.org/W2136668269","https://openalex.org/W2145725161","https://openalex.org/W2146103513","https://openalex.org/W2148383759","https://openalex.org/W2160754664","https://openalex.org/W2162216530","https://openalex.org/W2163292664","https://openalex.org/W2163588226","https://openalex.org/W2164084182","https://openalex.org/W2169561119","https://openalex.org/W2212216676","https://openalex.org/W2212494831","https://openalex.org/W2288514685","https://openalex.org/W2550553598","https://openalex.org/W2558906385","https://openalex.org/W2585592883","https://openalex.org/W2612135493","https://openalex.org/W2755981968","https://openalex.org/W2791303549","https://openalex.org/W2792312609","https://openalex.org/W2793668851","https://openalex.org/W2795307598","https://openalex.org/W2804743778","https://openalex.org/W2807663718","https://openalex.org/W2883429621","https://openalex.org/W2891726870","https://openalex.org/W2921653116","https://openalex.org/W2962762462","https://openalex.org/W2962965915","https://openalex.org/W2963091558","https://openalex.org/W2963503775","https://openalex.org/W2963524571","https://openalex.org/W2963581854","https://openalex.org/W2964114039","https://openalex.org/W2965638232","https://openalex.org/W2969741484","https://openalex.org/W2980565715","https://openalex.org/W2981165461","https://openalex.org/W2986131415","https://openalex.org/W2997304642","https://openalex.org/W2999458807","https://openalex.org/W3011154664","https://openalex.org/W3022565501","https://openalex.org/W3030520226","https://openalex.org/W3043142510","https://openalex.org/W3082940248","https://openalex.org/W3086763124","https://openalex.org/W3099561715","https://openalex.org/W3101840568","https://openalex.org/W3102582269","https://openalex.org/W3115654959","https://openalex.org/W3138095408","https://openalex.org/W3160344247","https://openalex.org/W3190399926","https://openalex.org/W3194945615","https://openalex.org/W3202477427","https://openalex.org/W4214612132","https://openalex.org/W4221078550","https://openalex.org/W4226051135","https://openalex.org/W4226056010","https://openalex.org/W4285176798","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6630781460","https://openalex.org/W6631190155","https://openalex.org/W6638444622","https://openalex.org/W6680437723","https://openalex.org/W6684745935","https://openalex.org/W6739901393","https://openalex.org/W6744446066","https://openalex.org/W6764953915","https://openalex.org/W6766978945","https://openalex.org/W6778485988","https://openalex.org/W6795360677","https://openalex.org/W6800389682"],"related_works":["https://openalex.org/W1880689012","https://openalex.org/W3014378845","https://openalex.org/W2378211422","https://openalex.org/W4240909707","https://openalex.org/W2059546927","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2161294397","https://openalex.org/W2012644758","https://openalex.org/W2047559669"],"abstract_inverted_index":{"Over":[0],"the":[1,25,29,81,102,126,160,177,197,217],"past":[2],"few":[3],"years,":[4],"gaze":[5,42,121,189],"prediction":[6,26,43],"technology":[7],"has":[8],"rapidly":[9],"developed":[10],"in":[11],"human":[12,30,75,89,103,161],"visual":[13,31,95,104,165],"attention":[14,105,115,153,166],"mechanism":[15],"research.":[16,44],"However,":[17],"there":[18],"is":[19],"still":[20],"a":[21,48,66,94,110,150,187],"large":[22,67,204],"gap":[23],"between":[24,129],"models":[27],"and":[28,97,136,144,163,194,207],"system":[32],"(HVS).":[33],"This":[34],"work":[35],"makes":[36],"four":[37],"contributions":[38],"to":[39,168],"video":[40,54,63],"egocentric":[41,120],"First,":[45],"we":[46,92,108,148,185],"introduce":[47],"new":[49,188],"benchmark":[50],"named":[51],"ECVG":[52,79],"(egocentric":[53],"gaze),":[55],"which":[56,100,123,156],"consists":[57],"of":[58,69,83,176,199],"3K":[59],"high-quality,":[60],"elaborately":[61],"selected":[62],"sequences":[64],"spanning":[65],"range":[68],"scenes.":[70],"Existing":[71],"eye-tracking":[72],"datasets":[73,205],"limit":[74],"activities.":[76],"In":[77,146],"contrast,":[78],"achieves":[80,137],"collection":[82],"eye":[84],"movement":[85],"data":[86],"under":[87],"real":[88],"activity.":[90],"Second,":[91],"establish":[93],"attention-selection":[96],"gaze-tracking":[98],"model,":[99],"summarizes":[101],"process.":[106],"Third,":[107],"propose":[109,149,186],"novel":[111],"feature":[112,138,172,175],"pyramid":[113],"interactive":[114,152],"3D":[116],"network":[117],"(FPIANet)":[118],"for":[119],"prediction,":[122],"directly":[124],"captures":[125],"long-term":[127],"relationship":[128],"spatiotemporal":[130,171],"features":[131],"at":[132],"different":[133],"time":[134],"steps":[135],"nonlocal":[139],"interactions":[140],"across":[141],"temporal,":[142],"spatial,":[143],"scales.":[145],"addition,":[147],"multiscale":[151],"(MSIA)":[154],"module,":[155],"first":[157],"explicitly":[158],"integrates":[159],"top-down":[162],"bottom-up":[164],"mechanisms":[167],"transform":[169],"any":[170],"into":[173],"another":[174],"same":[178],"size":[179],"but":[180],"with":[181],"richer":[182],"contexts.":[183],"Furthermore,":[184],"transfer":[190],"path":[191],"consistency":[192],"evaluation":[193],"thoroughly":[195],"examine":[196],"performance":[198],"our":[200,214],"model":[201,215],"on":[202],"two":[203],"(ECVG":[206],"LEDOV).":[208],"The":[209],"experimental":[210],"results":[211],"show":[212],"that":[213],"outperforms":[216],"existing":[218],"state-of-the-art":[219],"methods.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}