{"id":"https://openalex.org/W4308233687","doi":"https://doi.org/10.1109/icip46576.2022.9897987","title":"Learning Frequency-Specific Quantization Scaling in VVC for Standard-Compliant Task-Driven Image Coding","display_name":"Learning Frequency-Specific Quantization Scaling in VVC for Standard-Compliant Task-Driven Image Coding","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308233687","doi":"https://doi.org/10.1109/icip46576.2022.9897987"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897987","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2301.08533","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032747735","display_name":"Kristian Fischer","orcid":"https://orcid.org/0000-0002-0024-3171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kristian Fischer","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Multimedia Communications and Signal Processing,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Multimedia Communications and Signal Processing,Erlangen,Germany,91058","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053003385","display_name":"Fabian Brand","orcid":"https://orcid.org/0000-0002-2022-1033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabian Brand","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Multimedia Communications and Signal Processing,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Multimedia Communications and Signal Processing,Erlangen,Germany,91058","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048500216","display_name":"Christian Herglotz","orcid":"https://orcid.org/0000-0001-8975-0171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Herglotz","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Multimedia Communications and Signal Processing,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Multimedia Communications and Signal Processing,Erlangen,Germany,91058","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062850220","display_name":"Andr\u00e9 Kaup","orcid":"https://orcid.org/0000-0002-0929-5074"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andre Kaup","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Multimedia Communications and Signal Processing,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU),Multimedia Communications and Signal Processing,Erlangen,Germany,91058","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2757,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61226285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"476","last_page":"480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","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"}},"topics":[{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.998199999332428,"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":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.8110063076019287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7719929218292236},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6972525119781494},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6926474571228027},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5550438165664673},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45727211236953735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41732552647590637},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3388785421848297},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12462359666824341}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.8110063076019287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719929218292236},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6972525119781494},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6926474571228027},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5550438165664673},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45727211236953735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41732552647590637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3388785421848297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12462359666824341},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip46576.2022.9897987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897987","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2301.08533","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.08533","pdf_url":"https://arxiv.org/pdf/2301.08533","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2301.08533","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2301.08533","pdf_url":"https://arxiv.org/pdf/2301.08533","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G5032493830","display_name":"Videocodierung f\u00fcr die maschinelle Kommunikation basierend auf tiefem Lernen","funder_award_id":"426084215","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308233687.pdf","grobid_xml":"https://content.openalex.org/works/W4308233687.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W174971197","https://openalex.org/W1591404671","https://openalex.org/W2042598971","https://openalex.org/W2071581321","https://openalex.org/W2071847247","https://openalex.org/W2101700394","https://openalex.org/W2146395539","https://openalex.org/W2196397312","https://openalex.org/W2340897893","https://openalex.org/W2505609860","https://openalex.org/W2552465432","https://openalex.org/W2890304135","https://openalex.org/W2901056197","https://openalex.org/W2962676454","https://openalex.org/W2963150697","https://openalex.org/W2963661664","https://openalex.org/W3089957179","https://openalex.org/W3113550930","https://openalex.org/W3152708635","https://openalex.org/W3162412530","https://openalex.org/W3202918664","https://openalex.org/W6675207249"],"related_works":["https://openalex.org/W2107680156","https://openalex.org/W2163719598","https://openalex.org/W3161919736","https://openalex.org/W2387018512","https://openalex.org/W4301184752","https://openalex.org/W2751422192","https://openalex.org/W1509797384","https://openalex.org/W1201576901","https://openalex.org/W2479386627","https://openalex.org/W2288771647"],"abstract_inverted_index":{"Today,":[0],"visual":[1,48,137],"data":[2],"is":[3,41],"often":[4],"analyzed":[5],"by":[6],"a":[7,42,81],"neural":[8,71,92],"network":[9],"without":[10],"any":[11],"human":[12,47,136],"being":[13],"involved,":[14],"which":[15],"demands":[16],"for":[17,45,70,90,134],"specialized":[18],"codecs.":[19],"For":[20],"standard-compliant":[21],"codec":[22],"adaptations":[23],"towards":[24],"certain":[25],"information":[26,74,99],"sinks,":[27],"HEVC":[28],"or":[29],"VVC":[30,67,121],"provide":[31],"the":[32,46,104,108,135],"possibility":[33],"of":[34,117],"frequency-specific":[35],"quantization":[36],"with":[37,95,107,122],"scaling":[38,51,63,88,110,131,141],"lists.":[39],"This":[40],"well-known":[43],"method":[44,84],"system,":[49],"where":[50],"lists":[52,64,89,111,132,142],"are":[53],"derived":[54],"from":[55],"psycho-visual":[56],"models.":[57],"In":[58],"this":[59,77],"work,":[60],"we":[61,79],"employ":[62],"when":[65],"performing":[66],"intra":[68],"coding":[69,103],"networks":[72],"as":[73,98],"sink.":[75],"To":[76],"end,":[78],"propose":[80],"novel":[82],"data-driven":[83],"to":[85],"obtain":[86],"optimal":[87],"arbitrary":[91],"networks.":[93],"Experiments":[94],"Mask":[96],"R-CNN":[97],"sink":[100],"reveal":[101],"that":[102],"Cityscapes":[105],"dataset":[106],"proposed":[109],"result":[112],"in":[113],"peak":[114],"bitrate":[115],"savings":[116],"8.9":[118],"%":[119],"over":[120],"constant":[123],"quantization.":[124],"By":[125],"that,":[126],"our":[127],"approach":[128],"also":[129],"outperforms":[130],"optimized":[133],"system.":[138],"The":[139],"generated":[140],"can":[143],"be":[144],"found":[145],"under":[146],"https://github.com/FAU-LMS/VCM_scaling_lists.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2022-11-09T00:00:00"}