{"id":"https://openalex.org/W7162815075","doi":"https://doi.org/10.1145/3797246.3805853","title":"Towards Enhancing Visual Reasoning through Gaze-Semantic Alignment and Attention Correction","display_name":"Towards Enhancing Visual Reasoning through Gaze-Semantic Alignment and Attention Correction","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7162815075","doi":"https://doi.org/10.1145/3797246.3805853"},"language":null,"primary_location":{"id":"doi:10.1145/3797246.3805853","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3797246.3805853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Symposium on Eye Tracking Research and Applications","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/A5137360962","display_name":"Ramanand","orcid":"https://orcid.org/0009-0003-5473-5598"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]},{"id":"https://openalex.org/I4210091027","display_name":"Indian Institute of Advanced Research","ror":"https://ror.org/00c5q9r49","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210091027"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ramanand","raw_affiliation_strings":["Human-AI Interaction (HAIx) Lab, IIT Gandhinagar, Gandhinagar, Gujarat, India"],"raw_orcid":"https://orcid.org/0009-0003-5473-5598","affiliations":[{"raw_affiliation_string":"Human-AI Interaction (HAIx) Lab, IIT Gandhinagar, Gandhinagar, Gujarat, India","institution_ids":["https://openalex.org/I27674431","https://openalex.org/I4210091027"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137354052","display_name":"Yogesh Kumar Meena","orcid":"https://orcid.org/0000-0003-3429-8426"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]},{"id":"https://openalex.org/I4210091027","display_name":"Indian Institute of Advanced Research","ror":"https://ror.org/00c5q9r49","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210091027"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yogesh Kumar Meena","raw_affiliation_strings":["Human-AI Interaction (HAIx) Lab, IIT Gandhinagar, Gandhinagar, Gujarat, India"],"raw_orcid":"https://orcid.org/0000-0003-3429-8426","affiliations":[{"raw_affiliation_string":"Human-AI Interaction (HAIx) Lab, IIT Gandhinagar, Gandhinagar, Gujarat, India","institution_ids":["https://openalex.org/I27674431","https://openalex.org/I4210091027"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.60451706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.49390000104904175,"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":0.49390000104904175,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3070000112056732,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.10270000249147415,"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/eye-tracking","display_name":"Eye tracking","score":0.31690001487731934},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.31529998779296875},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3034999966621399},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2903999984264374},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.2743000090122223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6173999905586243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5349000096321106},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39649999141693115},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797246.3805853","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3797246.3805853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Symposium on Eye Tracking Research and Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5805284380912781}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2013112874","https://openalex.org/W2022732461","https://openalex.org/W2594780739","https://openalex.org/W2962884579","https://openalex.org/W2963503775","https://openalex.org/W3037725825"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"eye":[1],"tracking":[2],"is":[3,28],"a":[4,26,38,43,66,83,121],"fundamental":[5],"tool":[6],"for":[7,124],"understanding":[8],"how":[9],"humans":[10],"distribute":[11],"visual":[12,72,115,129],"attention":[13,55],"during":[14],"complex":[15],"cognitive":[16],"tasks.":[17],"However,":[18],"traditional":[19],"metrics":[20],"often":[21],"fail":[22],"to":[23,30,36,51,104,138],"capture":[24],"whether":[25],"user":[27,63],"attending":[29],"the":[31,102],"specific":[32],"semantic":[33,54],"information":[34],"required":[35],"solve":[37],"problem.":[39],"Here,":[40],"we":[41,74],"present":[42],"multimodal":[44],"framework":[45,78],"that":[46,76,94,109],"leverages":[47],"large":[48],"language":[49],"models":[50],"generate":[52],"benchmark":[53],"maps,":[56],"enabling":[57],"automated":[58,110],"alignment":[59],"and":[60,87,108],"correction":[61],"of":[62,69],"attention.":[64],"Using":[65],"curated":[67],"dataset":[68],"37":[70],"diverse":[71],"stimuli,":[73],"demonstrate":[75],"this":[77],"successfully":[79],"identifies":[80],"discrepancies":[81],"between":[82],"user\u2019s":[84],"explored":[85],"areas":[86],"semantically":[88],"relevant":[89],"regions.":[90],"This":[91,118],"work":[92],"confirms":[93],"combining":[95],"gaze":[96],"coordinates":[97],"with":[98],"AI-generated":[99],"heatmaps":[100],"enables":[101],"system":[103],"provide":[105],"granular":[106],"insights":[107],"feedback":[111],"can":[112],"help":[113],"improve":[114],"exploration":[116],"strategies.":[117],"methodology":[119],"provides":[120],"scalable":[122],"foundation":[123],"enhancing":[125],"human":[126],"performance":[127],"in":[128],"reasoning,":[130],"extending":[131],"eye-tracking":[132],"research":[133],"from":[134],"simple":[135],"text-based":[136],"paradigms":[137],"complex,":[139],"infographic-based":[140],"environments.":[141]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-05-30T00:00:00"}
