{"id":"https://openalex.org/W4377235410","doi":"https://doi.org/10.1109/tai.2023.3278650","title":"Generative Augmentation-Driven Prediction of Diverse Visual Scanpaths in Images","display_name":"Generative Augmentation-Driven Prediction of Diverse Visual Scanpaths in Images","publication_year":2023,"publication_date":"2023-05-22","ids":{"openalex":"https://openalex.org/W4377235410","doi":"https://doi.org/10.1109/tai.2023.3278650"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2023.3278650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3278650","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","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/A5101423308","display_name":"Ashish Verma","orcid":"https://orcid.org/0009-0007-3427-3196"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Verma","raw_affiliation_strings":["Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology (IIT) Kharagpur, Kharagpur, India"],"raw_orcid":"https://orcid.org/0009-0007-3427-3196","affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology (IIT) Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063471945","display_name":"Debashis Sen","orcid":"https://orcid.org/0000-0002-9756-1191"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Debashis Sen","raw_affiliation_strings":["Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology (IIT) Kharagpur, Kharagpur, India"],"raw_orcid":"https://orcid.org/0000-0002-9756-1191","affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology (IIT) Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":0.5555,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66780425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5","issue":"2","first_page":"940","last_page":"955"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9843000173568726,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7454977035522461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6808342337608337},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.5740988850593567},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5145460963249207},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5078189969062805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.452465295791626},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4300113022327423},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4256148040294647},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4238455295562744},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4206567704677582},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41846179962158203},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3332463502883911}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454977035522461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6808342337608337},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.5740988850593567},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5145460963249207},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5078189969062805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.452465295791626},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4300113022327423},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4256148040294647},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4238455295562744},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4206567704677582},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41846179962158203},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3332463502883911},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2023.3278650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2023.3278650","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1510835000","https://openalex.org/W1948843088","https://openalex.org/W1975802433","https://openalex.org/W1977965306","https://openalex.org/W1979722281","https://openalex.org/W2007163867","https://openalex.org/W2007571554","https://openalex.org/W2007593251","https://openalex.org/W2012257307","https://openalex.org/W2015831141","https://openalex.org/W2029714322","https://openalex.org/W2033552122","https://openalex.org/W2046863527","https://openalex.org/W2052882981","https://openalex.org/W2053631137","https://openalex.org/W2056254268","https://openalex.org/W2062118960","https://openalex.org/W2063608179","https://openalex.org/W2064675550","https://openalex.org/W2074231493","https://openalex.org/W2075644101","https://openalex.org/W2088574598","https://openalex.org/W2103666701","https://openalex.org/W2108598243","https://openalex.org/W2112570919","https://openalex.org/W2128272608","https://openalex.org/W2133946027","https://openalex.org/W2135957164","https://openalex.org/W2161502316","https://openalex.org/W2161523118","https://openalex.org/W2163929346","https://openalex.org/W2169528473","https://openalex.org/W2194775991","https://openalex.org/W2237503480","https://openalex.org/W2276718096","https://openalex.org/W2490662969","https://openalex.org/W2527003359","https://openalex.org/W2531748226","https://openalex.org/W2633406475","https://openalex.org/W2730649282","https://openalex.org/W2745461083","https://openalex.org/W2751388719","https://openalex.org/W2766426317","https://openalex.org/W2768825672","https://openalex.org/W2774319743","https://openalex.org/W2799224386","https://openalex.org/W2810231665","https://openalex.org/W2891817692","https://openalex.org/W2898911636","https://openalex.org/W2912614787","https://openalex.org/W2927333699","https://openalex.org/W2963921921","https://openalex.org/W2971402829","https://openalex.org/W2982306215","https://openalex.org/W2983589261","https://openalex.org/W2993760950","https://openalex.org/W3009026502","https://openalex.org/W3034964972","https://openalex.org/W3128601380","https://openalex.org/W3176796859","https://openalex.org/W4210800005","https://openalex.org/W4292793998","https://openalex.org/W4312416562","https://openalex.org/W6682778277","https://openalex.org/W6684042573","https://openalex.org/W6753975331"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W33281282","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Visual":[0],"scanpaths":[1,24,40,49,68,143,168],"of":[2,37,88,105,155,169,190,197,208],"multiple":[3,38,65,140,183,216],"humans":[4],"on":[5,25,41,69,127,178],"an":[6,42,70,114,128],"image":[7,43,129],"represent":[8],"the":[9,15,35,82,86,103,153,170,188,191,195,198,206],"process":[10,101],"by":[11,148],"which":[12,186],"they":[13],"capture":[14],"information":[16],"in":[17,81],"it.":[18],"State-of-the-art":[19],"models":[20,175],"to":[21,84,121,138],"predict":[22,122,139],"visual":[23,32,39,48,67,116,125,142,222],"images":[26],"learn":[27],"directly":[28],"from":[29],"recorded":[30],"human":[31,47],"scanpaths.":[33,223],"However,":[34],"generation":[36],"having":[44],"diversity":[45],"like":[46],"has":[50],"not":[51],"been":[52],"explicitly":[53],"considered.":[54],"In":[55],"this":[56],"article,":[57],"we":[58,112],"propose":[59,113],"a":[60,94,123,150,156],"deep":[61],"network":[62,120,134],"for":[63,110,164],"predicting":[64],"diverse":[66,141,221],"image.":[71],"Image-specific":[72],"hidden":[73],"Markov":[74],"model-based":[75],"generative":[76,98,210],"data":[77,99,211],"augmentation":[78,100,212],"is":[79,130,135,161],"performed":[80],"beginning":[83],"increase":[85],"number":[87],"image-visual":[89],"scanpath":[90,117,126,217],"training":[91],"pairs.":[92],"Considering":[93],"similarity":[95],"between":[96],"our":[97,209,215],"and":[102,214],"use":[104],"long":[106],"short-term":[107],"memory":[108],"(LSTM)":[109],"prediction,":[111],"LSTM-based":[115],"predictor.":[118],"A":[119,158],"single":[124],"designed":[131],"first.":[132],"The":[133],"then":[136],"modified":[137],"representing":[144],"different":[145],"viewer":[146,172],"varieties":[147],"using":[149,182],"parameter":[151],"indicating":[152,205],"uniqueness":[154],"viewer.":[157],"random":[159],"vector":[160],"also":[162,203],"employed":[163],"subtle":[165],"variations":[166],"within":[167],"same":[171],"variety.":[173],"Our":[174],"are":[176,202],"evaluated":[177],"three":[179],"standard":[180],"datasets":[181],"performance":[184],"measures,":[185],"demonstrate":[187],"superiority":[189],"proposed":[192],"approach":[193],"over":[194],"state":[196],"art.":[199],"Empirical":[200],"studies":[201],"given":[204],"significance":[207],"method":[213],"prediction":[218],"strategy":[219],"producing":[220]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}