{"id":"https://openalex.org/W4391307027","doi":"https://doi.org/10.1109/vcip59821.2023.10402607","title":"Towards Efficient Learned Image Coding for Machines via Saliency-Driven Rate Allocation","display_name":"Towards Efficient Learned Image Coding for Machines via Saliency-Driven Rate Allocation","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4391307027","doi":"https://doi.org/10.1109/vcip59821.2023.10402607"},"language":"en","primary_location":{"id":"doi:10.1109/vcip59821.2023.10402607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip59821.2023.10402607","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":"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/A5101885067","display_name":"Zixiang Zhang","orcid":"https://orcid.org/0009-0003-8024-3458"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zixiang Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan,China","Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739349","display_name":"Li Yu","orcid":"https://orcid.org/0000-0002-5060-2558"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Yu","raw_affiliation_strings":["Huazhong University of Science and Technology,Wuhan,China","Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100955017","display_name":"Qiang Zhang","orcid":"https://orcid.org/0009-0005-3530-2695"},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Zhang","raw_affiliation_strings":["ZTE Corporation,Nanjing,China","ZTE Corporation, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"ZTE Corporation,Nanjing,China","institution_ids":["https://openalex.org/I4210098582"]},{"raw_affiliation_string":"ZTE Corporation, Nanjing, China","institution_ids":["https://openalex.org/I4210098582"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050504314","display_name":"Mei Junjun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjun Mei","raw_affiliation_strings":["ZTE Corporation,Nanjing,China","ZTE Corporation, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"ZTE Corporation,Nanjing,China","institution_ids":["https://openalex.org/I4210098582"]},{"raw_affiliation_string":"ZTE Corporation, Nanjing, China","institution_ids":["https://openalex.org/I4210098582"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100713382","display_name":"Tao Guan","orcid":"https://orcid.org/0000-0002-7568-0560"},"institutions":[{"id":"https://openalex.org/I4210098582","display_name":"ZTE (China)","ror":"https://ror.org/00rjhhq63","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210098582"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Guan","raw_affiliation_strings":["ZTE Corporation,Nanjing,China","ZTE Corporation, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"ZTE Corporation,Nanjing,China","institution_ids":["https://openalex.org/I4210098582"]},{"raw_affiliation_string":"ZTE Corporation, Nanjing, China","institution_ids":["https://openalex.org/I4210098582"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101885067"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55774558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9991999864578247,"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":0.8304778933525085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6585320234298706},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5504905581474304},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5017006397247314},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.5003437995910645},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4171747863292694},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15949440002441406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8304778933525085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6585320234298706},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5504905581474304},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5017006397247314},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.5003437995910645},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4171747863292694},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15949440002441406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/vcip59821.2023.10402607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip59821.2023.10402607","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2030265202","https://openalex.org/W2101700394","https://openalex.org/W2140196014","https://openalex.org/W2146395539","https://openalex.org/W2949361041","https://openalex.org/W2964098744","https://openalex.org/W3034469748","https://openalex.org/W3164402689","https://openalex.org/W3169876831","https://openalex.org/W3202918664","https://openalex.org/W4289821645","https://openalex.org/W4312365925","https://openalex.org/W4312597589","https://openalex.org/W4386071691","https://openalex.org/W6675207249","https://openalex.org/W6754634825"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398","https://openalex.org/W2775347418"],"abstract_inverted_index":{"Recently,":[0],"efficient":[1],"image":[2,33,75,101,185],"coding":[3,14,166],"for":[4,84,194],"machines":[5],"method":[6,163],"is":[7,91,112,134,150],"widely":[8],"required":[9,103],"under":[10,21],"machine":[11,58,85,108,197],"vision":[12,59,109],"task-oriented":[13],"scenarios.":[15],"To":[16],"achieve":[17,120,153],"higher":[18],"task":[19,42,176],"accuracy":[20],"a":[22,73,79,107,129],"certain":[23],"bitrate":[24],"constraint,":[25],"existing":[26],"solutions":[27],"take":[28],"advantage":[29],"of":[30],"cutting-edge":[31],"learned":[32,74],"compression":[34,39,76],"methods":[35],"and":[36,40,54,61,196],"cascade":[37],"the":[38,48,116,124,138,142,147,161,174,179,183],"specific":[41],"model":[43,77],"straightly":[44],"to":[45,56,93,114,119,136,152],"carry":[46],"out":[47],"joint":[49],"optimization,":[50],"which":[51,98],"lacks":[52],"adaptability":[53],"flexibility":[55],"handling":[57],"saliency":[60,110],"non-saliency":[62],"regions,":[63],"thus":[64],"obtaining":[65],"inferior":[66],"performance.":[67],"In":[68,127],"this":[69],"paper,":[70],"we":[71],"propose":[72],"with":[78],"saliency-driven":[80],"rate":[81,121],"allocation":[82,122],"strategy":[83],"vision.":[86],"Specifically,":[87],"an":[88,154],"auxiliary":[89],"network":[90,177],"introduced":[92],"provide":[94],"reference":[95],"latent":[96,125],"first":[97],"contains":[99],"full":[100],"reconstruction":[102],"information.":[104],"And":[105],"then,":[106],"detector":[111],"applied":[113],"generate":[115],"adjustment":[117],"factor":[118],"in":[123],"domain.":[126],"addition,":[128],"spatial":[130,144],"dynamic":[131],"convolution":[132],"module":[133],"designed":[135],"facilitate":[137],"compressor":[139],"adaptively":[140],"processing":[141],"different":[143],"areas.":[145],"Finally,":[146],"multi-distortion":[148],"constraint":[149],"utilized":[151],"end-to-end":[155],"optimization.":[156],"Experimental":[157],"results":[158],"show":[159],"that":[160],"proposed":[162],"achieves":[164],"-77.48%":[165],"gains":[167],"over":[168],"VVC":[169],"using":[170],"Mask":[171],"R-CNN":[172],"as":[173],"back-end":[175],"on":[178],"Cityscapes":[180],"dataset.":[181],"Moreover,":[182],"reconstructed":[184],"maintains":[186],"considerable":[187],"visual":[188],"fidelity,":[189],"making":[190],"it":[191],"possible":[192],"both":[193],"human":[195],"consumption.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}