{"id":"https://openalex.org/W4416965831","doi":"https://doi.org/10.1109/tmm.2025.3639891","title":"TransGOP-R: Transformer-Based Real-World Gaze Object Prediction","display_name":"TransGOP-R: Transformer-Based Real-World Gaze Object Prediction","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416965831","doi":"https://doi.org/10.1109/tmm.2025.3639891"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2025.3639891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3639891","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5085773751","display_name":"Guangyu Guo","orcid":"https://orcid.org/0000-0002-5205-6319"},"institutions":[{"id":"https://openalex.org/I148099405","display_name":"Xi'an University of Architecture and Technology","ror":"https://ror.org/04v2j2k71","country_code":"CN","type":"education","lineage":["https://openalex.org/I148099405"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Guo","raw_affiliation_strings":["School of Information and Control Engineering, Xi&#x0027;an University of Architecture and Technology, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0002-5205-6319","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Xi&#x0027;an University of Architecture and Technology, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I148099405"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenxi Guo","orcid":"https://orcid.org/0009-0002-6307-5969"},"institutions":[{"id":"https://openalex.org/I148099405","display_name":"Xi'an University of Architecture and Technology","ror":"https://ror.org/04v2j2k71","country_code":"CN","type":"education","lineage":["https://openalex.org/I148099405"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Guo","raw_affiliation_strings":["School of Information and Control Engineering, Xi&#x0027;an University of Architecture and Technology, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0009-0002-6307-5969","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Xi&#x0027;an University of Architecture and Technology, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I148099405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062278877","display_name":"Zhaozhong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaozhong Wang","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0009-0008-9461-8237","affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043220498","display_name":"Binglu Wang","orcid":"https://orcid.org/0000-0002-9266-4685"},"institutions":[{"id":"https://openalex.org/I148099405","display_name":"Xi'an University of Architecture and Technology","ror":"https://ror.org/04v2j2k71","country_code":"CN","type":"education","lineage":["https://openalex.org/I148099405"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binglu Wang","raw_affiliation_strings":["School of Information and Control Engineering, Xi&#x0027;an University of Architecture and Technology, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0002-9266-4685","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Xi&#x0027;an University of Architecture and Technology, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I148099405"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33406414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"1689","last_page":"1703"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9835000038146973,"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":0.9835000038146973,"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":0.007300000172108412,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.8090000152587891},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5049999952316284},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48890000581741333},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.4738999903202057},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4569000005722046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.875},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.8090000152587891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.755299985408783},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6868000030517578},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5049999952316284},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4569000005722046},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3741999864578247},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C2780549717","wikidata":"https://www.wikidata.org/wiki/Q3409626","display_name":"Human head","level":3,"score":0.35989999771118164},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.29170000553131104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3639891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3639891","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3851001399","display_name":null,"funder_award_id":"62306101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6713625503","display_name":null,"funder_award_id":"2024GX-YBXM-051","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"},{"id":"https://openalex.org/G858926059","display_name":null,"funder_award_id":"62401447","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"},{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W109919546","https://openalex.org/W1861492603","https://openalex.org/W2077324971","https://openalex.org/W2167020116","https://openalex.org/W2194775991","https://openalex.org/W2417299834","https://openalex.org/W2510659016","https://openalex.org/W2570343428","https://openalex.org/W2594566384","https://openalex.org/W2765629358","https://openalex.org/W2776312359","https://openalex.org/W2796850409","https://openalex.org/W2798558457","https://openalex.org/W2883284130","https://openalex.org/W2884915206","https://openalex.org/W2897890508","https://openalex.org/W2910307394","https://openalex.org/W2962766617","https://openalex.org/W2963351448","https://openalex.org/W2963556443","https://openalex.org/W2982717194","https://openalex.org/W2986102820","https://openalex.org/W3025784200","https://openalex.org/W3035735638","https://openalex.org/W3096609285","https://openalex.org/W3100100339","https://openalex.org/W3123364653","https://openalex.org/W3165924482","https://openalex.org/W3171660447","https://openalex.org/W3174359952","https://openalex.org/W3188642398","https://openalex.org/W3203003533","https://openalex.org/W4210800317","https://openalex.org/W4210889190","https://openalex.org/W4214732542","https://openalex.org/W4225763874","https://openalex.org/W4280584658","https://openalex.org/W4285116117","https://openalex.org/W4292793996","https://openalex.org/W4293253477","https://openalex.org/W4312312588","https://openalex.org/W4312446817","https://openalex.org/W4312510569","https://openalex.org/W4312567381","https://openalex.org/W4312996499","https://openalex.org/W4313061846","https://openalex.org/W4313287871","https://openalex.org/W4319300857","https://openalex.org/W4361986707","https://openalex.org/W4385245566","https://openalex.org/W4386065416","https://openalex.org/W4386075646","https://openalex.org/W4386075833","https://openalex.org/W4386075862","https://openalex.org/W4386076325","https://openalex.org/W4386076438","https://openalex.org/W4387010030","https://openalex.org/W4388692601","https://openalex.org/W4390871672","https://openalex.org/W4390872741","https://openalex.org/W4390872917","https://openalex.org/W4390874396","https://openalex.org/W4391248885","https://openalex.org/W4391743392","https://openalex.org/W4393147659"],"related_works":[],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,99,136,188],"gaze":[3,11,106,116,138,153,209],"object":[4,167],"prediction":[5,126],"(GOP)":[6],"is":[7,29,104,109,159,170],"to":[8,79,140,164,184,206],"predict":[9],"human":[10,81,147],"objects":[12,149],"and":[13,69,148,181,194,216],"categories.":[14],"However,":[15],"existing":[16,101],"methods":[17,211],"require":[18],"additional":[19],"head":[20,66,76,82,87],"priors":[21],"or":[22],"filter":[23],"the":[24,95,100,112,128,133,137,142,145,152,166,186,192,198,207,213],"results":[25],"before":[26,150],"evaluation,":[27],"which":[28,60,108],"an":[30,90],"obstacle":[31],"for":[32],"real-world":[33],"applications.":[34],"To":[35],"this":[36,38,162],"end,":[37],"paper":[39],"proposes":[40],"a":[41,75,86],"<bold":[42,45,48,51,55],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[43,46,49,52,56],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Trans</b>former-based":[44],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">G</b>aze":[47],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">O</b>bject":[50],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">P</b>rediction":[53],"under":[54],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</b>eal-world":[57],"setting":[58],"(TransGOP-R),":[59],"does":[61],"not":[62,171],"rely":[63],"on":[64,191,212],"any":[65],"prior":[67],"input":[68],"evaluates":[70],"end-to-end.":[71],"We":[72],"first":[73],"design":[74],"location":[77,83],"module":[78],"generate":[80],"information":[84],"from":[85],"query.":[88],"Then,":[89],"error":[91,97],"analysis":[92],"demonstrates":[93],"that":[94],"primary":[96],"source":[98],"GOP":[102],"model":[103,129],"in":[105,114,161],"estimation,":[107],"caused":[110],"by":[111,118,173],"difficulty":[113],"predicting":[115],"points":[117],"directly":[119],"regressing":[120,151],"heatmaps.":[121],"Therefore,":[122],"we":[123,177,201],"introduce":[124],"cone":[125,174],"into":[127],"training":[130],"stage,":[131],"allowing":[132],"middle-layer":[134],"features":[135],"regressor":[139],"build":[141],"relationship":[143],"between":[144],"target":[146],"point.":[154],"An":[155],"oriented":[156],"gradient":[157],"mechanism":[158],"proposed":[160],"process":[163],"ensure":[165],"detection":[168],"performance":[169],"affected":[172],"information.":[175],"Finally,":[176],"conducted":[178],"very":[179],"detailed":[180],"sufficient":[182],"experiments":[183],"verify":[185],"superiority":[187],"our":[189],"method":[190],"GOO-Synth":[193],"GOO-Real":[195],"datasets.":[196,218],"At":[197],"same":[199],"time,":[200],"also":[202],"achieve":[203],"advantages":[204],"compared":[205],"human-target":[208],"estimation":[210],"GazeFollowing,":[214],"VideoAttentionTarget,":[215],"ChildPlay":[217]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-03T00:00:00"}