{"id":"https://openalex.org/W4408352727","doi":"https://doi.org/10.1109/icassp49660.2025.10890353","title":"iReWindColor: Vision Transformer with Residual Embedding and Window Encoder for Point-Interactive Image Colorization","display_name":"iReWindColor: Vision Transformer with Residual Embedding and Window Encoder for Point-Interactive Image Colorization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352727","doi":"https://doi.org/10.1109/icassp49660.2025.10890353"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5113405527","display_name":"H. OGURA","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideyuki Ogura","raw_affiliation_strings":["Keio University,Faculty of Science and Engineering,Yokohama,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,Faculty of Science and Engineering,Yokohama,Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090181402","display_name":"Masaaki Ikehara","orcid":"https://orcid.org/0000-0003-3461-1507"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaaki Ikehara","raw_affiliation_strings":["Keio University,Faculty of Science and Engineering,Yokohama,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Keio University,Faculty of Science and Engineering,Yokohama,Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I203951103"],"apc_list":null,"apc_paid":null,"fwci":4.2409,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93400567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.9887999892234802,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9887999892234802,"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":0.9884999990463257,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.983299970626831,"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/encoder","display_name":"Encoder","score":0.6635720729827881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6596657633781433},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6548425555229187},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6102048754692078},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6084659099578857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5954003930091858},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.5947576761245728},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5780928134918213},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1423393189907074},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13429155945777893},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12039393186569214},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07418578863143921}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6635720729827881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6596657633781433},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6548425555229187},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6102048754692078},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6084659099578857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5954003930091858},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.5947576761245728},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5780928134918213},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1423393189907074},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13429155945777893},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12039393186569214},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07418578863143921},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7382650399","display_name":"Degradation removal of images by nonlocal deep learning using signal processing techniques","funder_award_id":"23K03842","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2006497447","https://openalex.org/W2117539524","https://openalex.org/W2308529009","https://openalex.org/W2533598788","https://openalex.org/W2612063021","https://openalex.org/W2946103236","https://openalex.org/W4246399762","https://openalex.org/W4249736682","https://openalex.org/W4319300802","https://openalex.org/W4385245566","https://openalex.org/W6600609147","https://openalex.org/W6726497184","https://openalex.org/W6757817989","https://openalex.org/W6780226713","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2390901981","https://openalex.org/W2109115373","https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W4390516098","https://openalex.org/W2788972299","https://openalex.org/W2521347458","https://openalex.org/W2498789492","https://openalex.org/W2037549926"],"abstract_inverted_index":{"Point-interactive":[0],"image":[1,9,33,39,98,167,182],"colorization":[2,71,112,129,183],"is":[3,99,105],"intended":[4],"to":[5,14,34,81,127,162],"colorize":[6],"a":[7,36],"grayscale":[8],"by":[10,23,72,88,101],"allowing":[11],"the":[12,24,32,56,59,82,90,93,96,106,118,136,139,164],"user":[13,25,42,146,191],"specify":[15],"colors":[16,21],"at":[17],"specific":[18],"locations.":[19],"The":[20],"provided":[22],"(user":[26],"hints)":[27],"are":[28],"propagated":[29],"appropriately":[30],"throughout":[31],"obtain":[35],"reasonably":[37],"colorized":[38],"with":[40,113,193],"minimal":[41],"effort.":[43],"However,":[44],"existing":[45,178],"approaches":[46],"result":[47],"in":[48,84],"excessive":[49],"color":[50,53,186],"propagation":[51],"and":[52,157,170,184],"bleeding":[54],"beyond":[55],"boundaries":[57],"of":[58,154],"region.":[60],"To":[61],"address":[62],"this":[63],"problem,":[64],"we":[65,123,148],"propose":[66,124,149],"iReWindColor.":[67],"iReWindColor":[68],"achieves":[69],"fine":[70,111],"using":[73],"smaller":[74],"patches":[75,115],"for":[76,95,143,180],"Vision":[77],"Transformer-based":[78],"processing.":[79,108],"Due":[80],"increase":[83],"computational":[85,119],"cost":[86],"caused":[87],"reducing":[89],"patch":[91],"size,":[92],"processing":[94],"entire":[97,140],"replaced":[100],"Window":[102],"Encoder,":[103],"which":[104],"window-based":[107],"This":[109],"allows":[110],"small":[114],"without":[116],"increasing":[117],"cost.":[120,196],"In":[121],"addition,":[122],"Residual":[125,133],"Embaedding":[126],"reduce":[128],"divergence":[130],"between":[131,166],"windows.":[132],"Embedding":[134],"makes":[135],"network":[137],"consider":[138],"image.":[141],"Furthermore,":[142],"better":[144],"utilizing":[145],"hints,":[147],"Encode":[150],"Block":[151],"that":[152,174,188],"consists":[153],"both":[155],"Self-Attention":[156],"CNNs.":[158],"Adopting":[159],"it":[160],"helps":[161],"capture":[163],"interrelationships":[165],"patches.":[168],"Quantitative":[169],"qualitative":[171],"results":[172],"show":[173],"our":[175],"approach":[176],"outperforms":[177],"methods":[179],"point-interactive":[181],"produces":[185],"images":[187],"accurately":[189],"reflect":[190],"intent":[192],"less":[194],"computation":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}