{"id":"https://openalex.org/W7135375204","doi":"https://doi.org/10.1145/3799429","title":"Transition-aware Path and Direction Variation Modeling for Gaze Target Detection in Video","display_name":"Transition-aware Path and Direction Variation Modeling for Gaze Target Detection in Video","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7135375204","doi":"https://doi.org/10.1145/3799429"},"language":"en","primary_location":{"id":"doi:10.1145/3799429","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3799429","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5101119108","display_name":"Xingming Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingming Yang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, ChinaChina"],"raw_orcid":"https://orcid.org/0009-0008-3801-1377","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, ChinaChina","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I39774598"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Jin","orcid":"https://orcid.org/0000-0002-5232-7086"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Jin","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, ChinaChina"],"raw_orcid":"https://orcid.org/0000-0002-5232-7086","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, ChinaChina","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I39774598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100609001","display_name":"Kewei Wu","orcid":"https://orcid.org/0000-0002-7332-5653"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kewei Wu","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7332-5653","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457290","display_name":"Zhao Xie","orcid":"https://orcid.org/0000-0001-9834-4730"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Xie","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9834-4730","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057642740","display_name":"Chongjia Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongjia Zhu","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0009-6540-1159","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129314320","display_name":"Dan Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137491","display_name":"National Science Centre","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"government","lineage":["https://openalex.org/I4210137491"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China and Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2594-254X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China and Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":["https://openalex.org/I4210137491"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.29731597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"5","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.5659000277519226,"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":0.5659000277519226,"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":0.08959999680519104,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.04610000178217888,"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":0.9103000164031982},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5253999829292297},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4966000020503998},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.47530001401901245},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.41589999198913574},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4009000062942505}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.9103000164031982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8571000099182129},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7475000023841858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.725600004196167},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.47530001401901245},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3799429","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3799429","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6648456597","display_name":null,"funder_award_id":"62576131, 62272144","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":19,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2950995827","https://openalex.org/W3096609285","https://openalex.org/W3113416056","https://openalex.org/W3165695488","https://openalex.org/W4210811389","https://openalex.org/W4221166276","https://openalex.org/W4280584658","https://openalex.org/W4296899505","https://openalex.org/W4309660795","https://openalex.org/W4310457794","https://openalex.org/W4312956100","https://openalex.org/W4322706693","https://openalex.org/W4386883051","https://openalex.org/W4391216149","https://openalex.org/W4396671396","https://openalex.org/W4405717846","https://openalex.org/W4406812011","https://openalex.org/W4410856048"],"related_works":[],"abstract_inverted_index":{"Gaze":[0,38],"target":[1,29,123,152,200,206,222],"detection":[2,223],"aims":[3],"to":[4,25,47,86,106,136,164],"localize":[5],"a":[6,36,59,181,191],"person\u2019s":[7,182],"gaze":[8,11,28,61,79,160,166,221],"target.":[9],"During":[10],"transition":[12,92,225],"in":[13,27,224],"video,":[14],"the":[15,75,88,103,108,120,126,133,138,149,177],"absence":[16],"of":[17,111,180],"accurate":[18,49,205],"temporal":[19,45],"variation":[20,51,116,145,172],"modeling":[21],"(TVM)":[22],"may":[23],"lead":[24],"errors":[26],"localization.":[30],"In":[31],"this":[32,155,210],"work,":[33],"we":[34,94,208],"propose":[35],"Transition-aware":[37],"Model":[39],"(TGM),":[40],"which":[41,118,147,195,218],"focuses":[42],"on":[43,236],"analyzing":[44],"differences":[46],"achieve":[48],"location":[50,80,104],"modeling.":[52],"The":[53],"TGM":[54],"contains":[55],"four":[56],"key":[57],"components:":[58],"frame":[60,76,214],"model,":[62],"and":[63,71,81,170,241],"three":[64],"transition-aware":[65,99,139,193,211],"modules":[66],"(path":[67],"variation,":[68,70,169],"direction":[69,82,134,140,144,171],"fusion).":[72],"First":[73],",":[74,85,129,158],"Transformer":[77],"extracts":[78],"features.":[83],"Second":[84],"analyze":[87],"feature":[89,212],"difference":[90],"among":[91],"frames,":[93],"introduce":[95],"TVM":[96,101,130],"guided":[97],"by":[98],"loss.":[100],"analyzes":[102,132],"features":[105,135,215],"capture":[107,137],"moving":[109],"trajectory":[110],"targets":[112],"(defined":[113,142],"as":[114,143],"path":[115,168],"),":[117,146],"facilitates":[119,148],"search":[121,150,203],"for":[122,151,204],"locations":[124,153],"near":[125],"path.":[127],"Third":[128],"also":[131],"area":[141],"within":[154],"area.":[156],"Fourth":[157],"since":[159],"directions":[161],"dynamically":[162],"adjust":[163],"track":[165],"targets,":[167],"are":[173,188],"inherently":[174],"aligned":[175],"with":[176,216],"natural":[178],"movement":[179],"gaze.":[183],"Thus,":[184],"these":[185],"two":[186,237],"variations":[187],"fused":[189],"into":[190,213],"unified":[192],"feature,":[194],"helps":[196],"cover":[197],"all":[198],"potential":[199],"locations.":[201],"To":[202],"locations,":[207],"embed":[209],"cross-attention,":[217],"can":[219],"enhance":[220],"frames.":[226],"Extensive":[227],"experiments":[228],"demonstrate":[229],"that":[230],"our":[231],"method":[232],"achieves":[233],"state-of-the-art":[234],"performance":[235],"datasets,":[238],"namely":[239],"VideoAttentionTarget":[240],"VideoCoAtt.":[242]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-15T00:00:00"}