{"id":"https://openalex.org/W4402982478","doi":"https://doi.org/10.1109/icme57554.2024.10688065","title":"Theoretical Bound-Guided Hierarchical Vae For Neural Image Codecs","display_name":"Theoretical Bound-Guided Hierarchical Vae For Neural Image Codecs","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402982478","doi":"https://doi.org/10.1109/icme57554.2024.10688065"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100444205","display_name":"Yichi Zhang","orcid":"https://orcid.org/0009-0005-1156-5538"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yichi Zhang","raw_affiliation_strings":["Purdue University,Elmore Family School of Electrical and Computer Engineering,West Lafayette,Indiana,U.S.A"],"affiliations":[{"raw_affiliation_string":"Purdue University,Elmore Family School of Electrical and Computer Engineering,West Lafayette,Indiana,U.S.A","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029146300","display_name":"Zhihao Duan","orcid":"https://orcid.org/0000-0002-7948-4356"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihao Duan","raw_affiliation_strings":["Purdue University,Elmore Family School of Electrical and Computer Engineering,West Lafayette,Indiana,U.S.A"],"affiliations":[{"raw_affiliation_string":"Purdue University,Elmore Family School of Electrical and Computer Engineering,West Lafayette,Indiana,U.S.A","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101750851","display_name":"Yuning Huang","orcid":"https://orcid.org/0000-0002-6500-9335"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuning Huang","raw_affiliation_strings":["Purdue University,Elmore Family School of Electrical and Computer Engineering,West Lafayette,Indiana,U.S.A"],"affiliations":[{"raw_affiliation_string":"Purdue University,Elmore Family School of Electrical and Computer Engineering,West Lafayette,Indiana,U.S.A","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001380619","display_name":"Fengqing Zhu","orcid":"https://orcid.org/0000-0002-3863-3220"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengqing Zhu","raw_affiliation_strings":["Purdue University,Elmore Family School of Electrical and Computer Engineering,West Lafayette,Indiana,U.S.A"],"affiliations":[{"raw_affiliation_string":"Purdue University,Elmore Family School of Electrical and Computer Engineering,West Lafayette,Indiana,U.S.A","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100444205"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":1.0148,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80200532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7306315898895264},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6617698073387146},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5869804620742798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5323109030723572},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4435752332210541},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41567718982696533},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07190185785293579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7306315898895264},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6617698073387146},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5869804620742798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5323109030723572},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4435752332210541},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41567718982696533},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07190185785293579}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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":16,"referenced_works":["https://openalex.org/W2952122856","https://openalex.org/W2997572967","https://openalex.org/W3034368386","https://openalex.org/W3034469748","https://openalex.org/W3091372207","https://openalex.org/W3151130473","https://openalex.org/W3202918664","https://openalex.org/W4223425316","https://openalex.org/W4312443924","https://openalex.org/W4312806968","https://openalex.org/W4386075611","https://openalex.org/W4386598507","https://openalex.org/W4387449305","https://openalex.org/W4390918564","https://openalex.org/W4393153454","https://openalex.org/W4401878737"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"reveal":[2],"a":[3,51,96],"significant":[4],"theoretical":[5,21,33,52,64],"link":[6],"between":[7],"variational":[8],"autoencoders":[9],"(VAEs)":[10],"and":[11,81,109],"rate-distortion":[12,27],"theory,":[13],"notably":[14],"in":[15],"utilizing":[16],"VAEs":[17,80],"to":[18,66],"estimate":[19],"the":[20,25,37,63,68,76],"upper":[22],"bound":[23,65],"of":[24,29,39],"information":[26],"function":[28],"images.":[30],"Such":[31],"estimated":[32],"bounds":[34],"substantially":[35],"exceed":[36],"performance":[38,108],"existing":[40,102],"neural":[41,91],"image":[42],"codecs":[43],"(NICs).":[44],"To":[45],"narrow":[46],"this":[47],"gap,":[48],"we":[49,94],"propose":[50],"bound-guided":[53],"hierarchical":[54],"VAE":[55],"(BG-VAE)":[56],"for":[57],"NIC.":[58],"The":[59,112],"proposed":[60],"BG-VAE":[61,77],"leverages":[62],"guide":[67],"NIC":[69,99],"model":[70],"towards":[71],"enhanced":[72],"performance.":[73],"We":[74],"implement":[75],"using":[78],"Hierarchical":[79],"demonstrate":[82],"its":[83],"effectiveness":[84],"through":[85],"extensive":[86],"experiments.":[87],"Along":[88],"with":[89],"advanced":[90],"network":[92],"blocks,":[93],"provide":[95],"versatile,":[97],"variable-rate":[98],"that":[100],"outperforms":[101],"methods":[103],"when":[104],"considering":[105],"both":[106],"ratedistortion":[107],"computational":[110],"complexity.":[111],"code":[113],"is":[114],"available":[115],"at":[116],"$\\color{magenta}{\\text{BG":[117],"-":[118],"VAE}}$.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
