{"id":"https://openalex.org/W7127430121","doi":"https://doi.org/10.1109/rivf68649.2025.11365125","title":"WAVENET-MV: Wavelet-Based Neural Image Compression for Machine Vision Tasks","display_name":"WAVENET-MV: Wavelet-Based Neural Image Compression for Machine Vision Tasks","publication_year":2025,"publication_date":"2025-12-18","ids":{"openalex":"https://openalex.org/W7127430121","doi":"https://doi.org/10.1109/rivf68649.2025.11365125"},"language":null,"primary_location":{"id":"doi:10.1109/rivf68649.2025.11365125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf68649.2025.11365125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 RIVF International Conference on Computing and Communication Technologies (RIVF)","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/A5103283489","display_name":"Nguy\u1ec5n Hi\u1ebfu Minh","orcid":"https://orcid.org/0009-0009-4815-9639"},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]},{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Ngoc Minh Do","raw_affiliation_strings":["VNU–University of Engineering and Technology,Hanoi,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNU–University of Engineering and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011827276","display_name":"Duong Dinh Trieu","orcid":null},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]},{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Duong Dinh Trieu","raw_affiliation_strings":["VNU–University of Engineering and Technology,Hanoi,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNU–University of Engineering and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022703513","display_name":"Xiem HoangVan","orcid":"https://orcid.org/0000-0002-7524-6529"},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]},{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Xiem Hoang Van","raw_affiliation_strings":["VNU–University of Engineering and Technology,Hanoi,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNU–University of Engineering and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62594693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"956","last_page":"961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9437999725341797,"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":0.9437999725341797,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.017000000923871994,"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":0.005400000140070915,"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/image-compression","display_name":"Image compression","score":0.590499997138977},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5033000111579895},{"id":"https://openalex.org/keywords/jpeg","display_name":"JPEG","score":0.4763000011444092},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.47440001368522644},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.4697999954223633},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.429500013589859},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41429999470710754},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.399399995803833},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38359999656677246}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7398999929428101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304999828338623},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6866000294685364},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.590499997138977},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C198751489","wikidata":"https://www.wikidata.org/wiki/Q2195","display_name":"JPEG","level":3,"score":0.4763000011444092},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.399399995803833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C69216139","wikidata":"https://www.wikidata.org/wiki/Q931783","display_name":"JPEG 2000","level":5,"score":0.29100000858306885},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf68649.2025.11365125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf68649.2025.11365125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5532409583","display_name":null,"funder_award_id":"CN25.18","funder_id":"https://openalex.org/F4320337882","funder_display_name":"Tr\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc C\u00f4ng ngh\u1ec7, \u0110\u1ea1i h\u1ecdc Qu\u1ed1c Gia H\u00e0 N\u1ed9i"}],"funders":[{"id":"https://openalex.org/F4320337882","display_name":"Tr\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc C\u00f4ng ngh\u1ec7, \u0110\u1ea1i h\u1ecdc Qu\u1ed1c Gia H\u00e0 N\u1ed9i","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2140196014","https://openalex.org/W2170023599","https://openalex.org/W2963494934","https://openalex.org/W3034469748","https://openalex.org/W3160673571","https://openalex.org/W3175317007","https://openalex.org/W3213789764","https://openalex.org/W4251101141","https://openalex.org/W4386066710"],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"image":[1,35],"codecs,":[2],"such":[3],"as":[4],"JPEG,":[5],"are":[6],"principally":[7],"engineered":[8],"to":[9,61,124],"optimize":[10],"perceptual":[11],"quality":[12],"for":[13,25,40,52,65,76],"human":[14],"viewers,":[15],"which":[16],"often":[17],"results":[18],"in":[19,96],"the":[20,83],"omission":[21],"of":[22,115,121],"information":[23],"essential":[24],"machine":[26],"vision":[27,42],"tasks.":[28],"This":[29],"research":[30],"introduces":[31],"WAVENET-MV,":[32],"a":[33,48,68,72,102,113],"neural":[34],"compression":[36],"framework":[37],"explicitly":[38],"designed":[39],"computer":[41],"applications.":[43],"The":[44],"proposed":[45],"architecture":[46],"integrates":[47],"learnable":[49],"wavelet-based":[50],"transform":[51],"multi-scale":[53],"frequency":[54],"decomposition,":[55],"an":[56,119],"attention-guided":[57],"feature":[58],"mixing":[59],"module":[60],"enhance":[62,145],"features":[63],"vital":[64],"tasks,":[66],"and":[67,118],"variable-rate":[69],"compressor":[70],"with":[71],"learned":[73],"entropy":[74],"model":[75],"efficient":[77],"bit-rate":[78],"management.":[79],"Evaluations":[80],"conducted":[81],"on":[82],"COCO":[84],"2017":[85],"dataset,":[86],"targeting":[87],"object":[88],"detection,":[89],"demonstrate":[90],"that":[91],"WAVENET-MV":[92],"consistently":[93],"outperforms":[94],"JPEG":[95],"detection":[97],"accuracy":[98,147],"while":[99],"operating":[100],"within":[101,138],"similar":[103],"bitrate":[104],"range.":[105],"For":[106],"instance,":[107],"at":[108,148],"1.34":[109],"bpp,":[110],"it":[111],"achieves":[112],"PSNR":[114,128],"27.4":[116],"dB":[117,127],"mAP":[120],"79.2%,":[122],"compared":[123],"JPEG's":[125],"33.0":[126],"and$66.6":[129],"\\%":[130],"\\text{mAP}$at":[131],"1.01":[132],"bpp.":[133],"These":[134],"findings":[135],"underscore":[136],"that,":[137],"machine-centric":[139],"workflows,":[140],"maintaining":[141],"task-relevant":[142],"structures":[143],"can":[144],"downstream":[146],"comparable":[149],"bitrates,":[150],"even":[151],"when":[152],"pixelwise":[153],"fidelity":[154],"(e.g.,":[155],"PSNR)":[156],"is":[157],"lower.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-04T00:00:00"}