{"id":"https://openalex.org/W4386598521","doi":"https://doi.org/10.1109/icip49359.2023.10222853","title":"Transformer-Based Variable-Rate Image Compression with Region-of-Interest Control","display_name":"Transformer-Based Variable-Rate Image Compression with Region-of-Interest Control","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386598521","doi":"https://doi.org/10.1109/icip49359.2023.10222853"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-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/A5039818785","display_name":"Chia-Hao Kao","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Hao Kao","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan","National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113096052","display_name":"Ying-Chieh Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ying-Chieh Weng","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan","National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018152658","display_name":"Yi\u2010Hsin Chen","orcid":"https://orcid.org/0000-0002-6102-7544"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsin Chen","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan","National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038549076","display_name":"Wei-Chen Chiu","orcid":"https://orcid.org/0000-0001-7715-8306"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Chen Chiu","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan","National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071531458","display_name":"Wen-Hsiao Peng","orcid":"https://orcid.org/0000-0002-4421-8031"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Hsiao Peng","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Taiwan","National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":1.5555,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85428091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2960","last_page":"2964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9997000098228455,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9997000098228455,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9997000098228455,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.7484323978424072},{"id":"https://openalex.org/keywords/region-of-interest","display_name":"Region of interest","score":0.6239993572235107},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5863197445869446},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.5771008729934692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5507156848907471},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5235009789466858},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.467821329832077},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.43470150232315063},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4342455267906189},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.42056334018707275},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.31054162979125977},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.2707616686820984},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2635936737060547},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14490818977355957},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10597628355026245},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09238183498382568}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484323978424072},{"id":"https://openalex.org/C19609008","wikidata":"https://www.wikidata.org/wiki/Q2138203","display_name":"Region of interest","level":2,"score":0.6239993572235107},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5863197445869446},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.5771008729934692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5507156848907471},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5235009789466858},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.467821329832077},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.43470150232315063},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4342455267906189},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.42056334018707275},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31054162979125977},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2707616686820984},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2635936737060547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14490818977355957},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10597628355026245},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09238183498382568},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222853","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2963814095","https://openalex.org/W3003267478","https://openalex.org/W3004685385","https://openalex.org/W3138516171","https://openalex.org/W3179468628","https://openalex.org/W3185341429","https://openalex.org/W3212865599","https://openalex.org/W4230291482","https://openalex.org/W4312651322","https://openalex.org/W4317555293","https://openalex.org/W6773431304"],"related_works":["https://openalex.org/W2521595930","https://openalex.org/W4243608781","https://openalex.org/W3165542721","https://openalex.org/W4313046148","https://openalex.org/W1939109514","https://openalex.org/W4378191574","https://openalex.org/W2129829718","https://openalex.org/W1843792225","https://openalex.org/W2751842002","https://openalex.org/W2161981399"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,17,58],"transformer-based":[4,38],"learned":[5],"image":[6],"compression":[7,15],"system.":[8],"It":[9],"is":[10],"capable":[11],"of":[12,40,63,87],"achieving":[13],"variable-rate":[14,77],"with":[16],"single":[18],"model":[19],"while":[20],"supporting":[21],"the":[22,37,51,64,68,85,96],"region-of-interest":[23],"(ROI)":[24],"functionality.":[25],"Inspired":[26],"by":[27],"prompt":[28,32,43],"tuning,":[29],"we":[30],"introduce":[31],"generation":[33,44],"networks":[34,45],"to":[35,50,75],"condition":[36],"autoencoder":[39],"compression.":[41],"Our":[42],"generate":[46],"content-adaptive":[47],"tokens":[48],"according":[49],"input":[52],"image,":[53],"an":[54,72],"ROI":[55,65,79],"mask,":[56],"and":[57,67,78,91],"rate":[59,69],"parameter.":[60],"The":[61],"separation":[62],"mask":[66],"parameter":[70],"allows":[71],"intuitive":[73],"way":[74],"achieve":[76],"coding":[80],"simultaneously.":[81],"Extensive":[82],"experiments":[83],"validate":[84],"effectiveness":[86],"our":[88],"proposed":[89],"method":[90],"confirm":[92],"its":[93],"superiority":[94],"over":[95],"other":[97],"competing":[98],"methods.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}