{"id":"https://openalex.org/W4372260482","doi":"https://doi.org/10.1109/icassp49357.2023.10094674","title":"ROI-Based Deep Image Compression with Swin Transformers","display_name":"ROI-Based Deep Image Compression with Swin Transformers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260482","doi":"https://doi.org/10.1109/icassp49357.2023.10094674"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100649277","display_name":"Binglin Li","orcid":"https://orcid.org/0000-0003-2798-1710"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Binglin Li","raw_affiliation_strings":["Simon Fraser University,School of Engineering Science,Canada","School of Engineering Science, Simon Fraser University, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University,School of Engineering Science,Canada","institution_ids":["https://openalex.org/I18014758"]},{"raw_affiliation_string":"School of Engineering Science, Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108166775","display_name":"Jie Liang","orcid":"https://orcid.org/0000-0003-3003-4343"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jie Liang","raw_affiliation_strings":["Simon Fraser University,School of Engineering Science,Canada","School of Engineering Science, Simon Fraser University, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University,School of Engineering Science,Canada","institution_ids":["https://openalex.org/I18014758"]},{"raw_affiliation_string":"School of Engineering Science, Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045288861","display_name":"Haisheng Fu","orcid":"https://orcid.org/0000-0001-8709-5927"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haisheng Fu","raw_affiliation_strings":["Xian Jiaotong University,School of Microelectronics,China","School of Microelectronics, Xian Jiaotong University, China"],"affiliations":[{"raw_affiliation_string":"Xian Jiaotong University,School of Microelectronics,China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Microelectronics, Xian Jiaotong University, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046233912","display_name":"Jingning Han","orcid":"https://orcid.org/0000-0001-7168-2254"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingning Han","raw_affiliation_strings":["Google LLC,Mountain View,CA,USA","Google LLC, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,Mountain View,CA,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100649277"],"corresponding_institution_ids":["https://openalex.org/I18014758"],"apc_list":null,"apc_paid":null,"fwci":2.1702,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89489101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"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/T10627","display_name":"Advanced Image and Video Retrieval 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/T10627","display_name":"Advanced Image and Video Retrieval 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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9990000128746033,"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":0.9983999729156494,"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/region-of-interest","display_name":"Region of interest","score":0.8157946467399597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7960410118103027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7730674743652344},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6841344237327576},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5545387864112854},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.48223552107810974},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.41133391857147217},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3340231776237488},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.29443010687828064},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.274689257144928},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.26218992471694946}],"concepts":[{"id":"https://openalex.org/C19609008","wikidata":"https://www.wikidata.org/wiki/Q2138203","display_name":"Region of interest","level":2,"score":0.8157946467399597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960410118103027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7730674743652344},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6841344237327576},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5545387864112854},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.48223552107810974},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.41133391857147217},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3340231776237488},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29443010687828064},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.274689257144928},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26218992471694946}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2070924407","https://openalex.org/W2103105267","https://openalex.org/W2162903716","https://openalex.org/W2178928294","https://openalex.org/W2949361041","https://openalex.org/W2963447011","https://openalex.org/W2982483316","https://openalex.org/W2997454254","https://openalex.org/W3014641072","https://openalex.org/W3034383034","https://openalex.org/W3036682213","https://openalex.org/W3097448661","https://openalex.org/W3120432545","https://openalex.org/W3138516171","https://openalex.org/W3173274771","https://openalex.org/W3212865599","https://openalex.org/W4230291482","https://openalex.org/W4280603646","https://openalex.org/W4285180923","https://openalex.org/W4287605633","https://openalex.org/W6620707391","https://openalex.org/W6639102338","https://openalex.org/W6735463952","https://openalex.org/W6754634825","https://openalex.org/W6769827072","https://openalex.org/W6780365925","https://openalex.org/W6804350942"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2803255133","https://openalex.org/W2326552140"],"abstract_inverted_index":{"Encoding":[0],"the":[1,10,43,56,65,71,75,81,126],"Region":[2],"Of":[3],"Interest":[4],"(ROI)":[5],"with":[6,35,113],"better":[7],"quality":[8],"than":[9,98],"background":[11],"has":[12,117],"many":[13],"applications":[14],"including":[15],"video":[16,19],"conferencing":[17],"systems,":[18],"surveillance":[20],"and":[21,77,101,121],"object-oriented":[22],"vision":[23],"tasks.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28,68],"propose":[29],"a":[30],"ROI-based":[31],"image":[32],"compression":[33],"framework":[34],"Swin":[36],"transformers":[37],"as":[38],"main":[39],"building":[40],"blocks":[41],"for":[42,86,105],"autoencoder":[44],"network.":[45],"The":[46],"binary":[47],"ROI":[48,66,76,96],"mask":[49],"is":[50],"integrated":[51],"into":[52],"different":[53,87],"layers":[54],"of":[55,74],"network":[57],"to":[58],"provide":[59],"spatial":[60],"information":[61],"guidance.":[62],"Based":[63],"on":[64,110,125],"mask,":[67],"can":[69],"control":[70],"relative":[72],"importance":[73],"non-ROI":[78],"by":[79],"modifying":[80],"corresponding":[82],"Lagrange":[83],"multiplier":[84],"\u03bb":[85],"regions.":[88],"Experimental":[89],"results":[90],"show":[91],"our":[92],"model":[93],"achieves":[94],"higher":[95],"PSNR":[97,104],"other":[99],"methods":[100],"modest":[102],"average":[103],"human":[106],"evaluation.":[107],"When":[108],"tested":[109],"models":[111],"pre-trained":[112],"original":[114],"images,":[115],"it":[116],"superior":[118],"object":[119],"detection":[120],"instance":[122],"segmentation":[123],"performance":[124],"COCO":[127],"validation":[128],"dataset.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}