{"id":"https://openalex.org/W4391306741","doi":"https://doi.org/10.1109/vcip59821.2023.10402641","title":"Low-complexity Transform Network Architecture for JPEG AI Image Codec","display_name":"Low-complexity Transform Network Architecture for JPEG AI Image Codec","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4391306741","doi":"https://doi.org/10.1109/vcip59821.2023.10402641"},"language":"en","primary_location":{"id":"doi:10.1109/vcip59821.2023.10402641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip59821.2023.10402641","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 Visual Communications and Image Processing (VCIP)","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/A5100670527","display_name":"Xiang Pan","orcid":"https://orcid.org/0000-0001-9108-944X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Pan","raw_affiliation_strings":["Tencent Media Lab,Shenzhen,China","Tencent Media Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Media Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Media Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352099","display_name":"Ding Ding","orcid":"https://orcid.org/0000-0002-0859-8065"},"institutions":[{"id":"https://openalex.org/I70745867","display_name":"KLA (United States)","ror":"https://ror.org/02rqhpa98","country_code":"US","type":"company","lineage":["https://openalex.org/I70745867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ding Ding","raw_affiliation_strings":["Tencent Media Lab,Palo Alto,CA,USA","Tencent Media Lab, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Media Lab,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I70745867"]},{"raw_affiliation_string":"Tencent Media Lab, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I70745867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427863","display_name":"Liqiang Wang","orcid":"https://orcid.org/0000-0002-1265-4656"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Wang","raw_affiliation_strings":["Tencent Media Lab,Shenzhen,China","Tencent Media Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Media Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Media Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102847146","display_name":"Xiaozhong Xu","orcid":"https://orcid.org/0000-0002-1309-5470"},"institutions":[{"id":"https://openalex.org/I70745867","display_name":"KLA (United States)","ror":"https://ror.org/02rqhpa98","country_code":"US","type":"company","lineage":["https://openalex.org/I70745867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaozhong Xu","raw_affiliation_strings":["Tencent Media Lab,Palo Alto,CA,USA","Tencent Media Lab, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Media Lab,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I70745867"]},{"raw_affiliation_string":"Tencent Media Lab, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I70745867"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100449791","display_name":"Shan Liu","orcid":"https://orcid.org/0000-0002-1442-1207"},"institutions":[{"id":"https://openalex.org/I70745867","display_name":"KLA (United States)","ror":"https://ror.org/02rqhpa98","country_code":"US","type":"company","lineage":["https://openalex.org/I70745867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shan Liu","raw_affiliation_strings":["Tencent Media Lab,Palo Alto,CA,USA","Tencent Media Lab, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Media Lab,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I70745867"]},{"raw_affiliation_string":"Tencent Media Lab, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I70745867"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11105","display_name":"Advanced Image Processing Techniques","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/T11105","display_name":"Advanced Image Processing Techniques","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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9998000264167786,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9998000264167786,"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/upsampling","display_name":"Upsampling","score":0.7763438820838928},{"id":"https://openalex.org/keywords/jpeg","display_name":"JPEG","score":0.7493994832038879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7480813264846802},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6897492408752441},{"id":"https://openalex.org/keywords/transform-coding","display_name":"Transform coding","score":0.5826642513275146},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.5423924922943115},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5293574929237366},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.5290027260780334},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.4916868805885315},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4808138608932495},{"id":"https://openalex.org/keywords/jpeg-2000","display_name":"JPEG 2000","score":0.4600223898887634},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45321837067604065},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4364311099052429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43586140871047974},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.42582884430885315},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3916781544685364},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.39132484793663025},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37301427125930786},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.263679563999176},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.23168212175369263},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2228548526763916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11373427510261536}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7763438820838928},{"id":"https://openalex.org/C198751489","wikidata":"https://www.wikidata.org/wiki/Q2195","display_name":"JPEG","level":3,"score":0.7493994832038879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480813264846802},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6897492408752441},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.5826642513275146},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5423924922943115},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5293574929237366},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.5290027260780334},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.4916868805885315},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4808138608932495},{"id":"https://openalex.org/C69216139","wikidata":"https://www.wikidata.org/wiki/Q931783","display_name":"JPEG 2000","level":5,"score":0.4600223898887634},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45321837067604065},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4364311099052429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43586140871047974},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.42582884430885315},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3916781544685364},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.39132484793663025},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37301427125930786},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.263679563999176},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.23168212175369263},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2228548526763916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11373427510261536},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip59821.2023.10402641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip59821.2023.10402641","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 Visual Communications and Image Processing (VCIP)","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":20,"referenced_works":["https://openalex.org/W1580389772","https://openalex.org/W2046119925","https://openalex.org/W2114582993","https://openalex.org/W2141983208","https://openalex.org/W2476548250","https://openalex.org/W2571611310","https://openalex.org/W2981288052","https://openalex.org/W3034469748","https://openalex.org/W3091266734","https://openalex.org/W3157956104","https://openalex.org/W3175457126","https://openalex.org/W4221148507","https://openalex.org/W4225672218","https://openalex.org/W4312806968","https://openalex.org/W4316660616","https://openalex.org/W4320559388","https://openalex.org/W4376464601","https://openalex.org/W6738991188","https://openalex.org/W6767848769","https://openalex.org/W6849793491"],"related_works":["https://openalex.org/W2441603424","https://openalex.org/W4200377430","https://openalex.org/W2147471256","https://openalex.org/W2542654834","https://openalex.org/W4243959093","https://openalex.org/W2151920332","https://openalex.org/W1994319845","https://openalex.org/W2159814397","https://openalex.org/W2147992969","https://openalex.org/W2100013736"],"abstract_inverted_index":{"Learning-based":[0],"image":[1,16],"coding":[2],"schemes,":[3],"exemplified":[4],"by":[5,11,29,98,101],"JPEG":[6,131],"AI,":[7],"have":[8,126],"shown":[9],"potential":[10],"greatly":[12],"exceeding":[13],"the":[14,35,91,108,130],"conventional":[15],"compression":[17],"standards":[18],"in":[19,123],"rate-distortion":[20],"(RD)":[21],"performance.":[22],"However,":[23],"their":[24,48],"widespread":[25],"applications":[26],"are":[27,50],"hindered":[28],"high":[30],"decoding":[31],"complexity,":[32,46],"particularly":[33],"from":[34],"upsampling":[36,76],"and":[37,78],"attention":[38,72],"modules.":[39],"Existing":[40],"works":[41],"sought":[42],"to":[43,83,105,119],"reduce":[44],"this":[45,59,85,124],"but":[47],"solutions":[49],"not":[51],"fully":[52],"effective,":[53],"leaving":[54],"considerable":[55],"complexity":[56,96],"unaddressed.":[57],"In":[58],"paper,":[60],"we":[61],"present":[62],"a":[63,74,79],"simplified":[64,92],"transform":[65],"network":[66],"architecture":[67],"that":[68,90],"employs":[69],"an":[70],"optimized":[71],"module,":[73,77],"streamlined":[75],"pared-down":[80],"activation":[81],"function":[82],"tackle":[84],"issue.":[86],"Simulation":[87],"results":[88],"show":[89],"decoder":[93],"sees":[94],"its":[95],"(measured":[97],"kMACs/pixel)":[99],"reduced":[100],"80%":[102],"(from":[103,117],"833":[104],"172),":[106],"while":[107],"gain":[109],"over":[110],"Versatile":[111],"Video":[112],"Coding":[113],"(VVC)":[114],"increases":[115],"slightly":[116],"27.3%":[118],"27.5%).":[120],"Partial":[121],"methods":[122],"paper":[125],"been":[127],"integrated":[128],"into":[129],"AI":[132],"Verification":[133],"Model":[134],"(VM)":[135],"software.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}