{"id":"https://openalex.org/W4403917938","doi":"https://doi.org/10.1109/tcsvt.2024.3488181","title":"High Efficiency Image Compression for Large Visual-Language Models","display_name":"High Efficiency Image Compression for Large Visual-Language Models","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403917938","doi":"https://doi.org/10.1109/tcsvt.2024.3488181"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3488181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3488181","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5087392324","display_name":"Binzhe Li","orcid":"https://orcid.org/0000-0002-1535-0121"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Binzhe Li","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Pokfulam, Hong Kong","Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-1535-0121","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102713644","display_name":"Shurun Wang","orcid":"https://orcid.org/0000-0002-0758-9175"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Shurun Wang","raw_affiliation_strings":["Alibaba Group, Beijing, China","Department of Computer Science, City University of Hong Kong, Pokfulam, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385178","display_name":"Shiqi Wang","orcid":"https://orcid.org/0000-0002-3583-959X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Shiqi Wang","raw_affiliation_strings":["Alibaba Group, Beijing, China","Department of Computer Science, City University of Hong Kong, Pokfulam, Hong Kong","Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3583-959X","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Pokfulam, Hong Kong","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101602641","display_name":"Yan Ye","orcid":"https://orcid.org/0000-0002-7278-0822"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Ye","raw_affiliation_strings":["Alibaba Group U.S., Sunnyvale, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7278-0822","affiliations":[{"raw_affiliation_string":"Alibaba Group U.S., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6131,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68858847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"35","issue":"3","first_page":"2870","last_page":"2880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.996399998664856,"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":0.996399998664856,"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/T11439","display_name":"Video Analysis and Summarization","score":0.977400004863739,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.974399983882904,"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":0.6810287833213806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6688500642776489},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5758013725280762},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.558894157409668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5501948595046997},{"id":"https://openalex.org/keywords/texture-compression","display_name":"Texture compression","score":0.468772828578949},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.46773654222488403},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4211844503879547},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4185033440589905},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3358965218067169}],"concepts":[{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.6810287833213806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688500642776489},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5758013725280762},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.558894157409668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501948595046997},{"id":"https://openalex.org/C54243161","wikidata":"https://www.wikidata.org/wiki/Q39333","display_name":"Texture compression","level":5,"score":0.468772828578949},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.46773654222488403},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4211844503879547},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4185033440589905},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3358965218067169},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3488181","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3488181","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1168500608","display_name":"Compression, Transmission and National Standardization for Ultra-high-definition VR Videos","funder_award_id":"GHP/044/21SZ","funder_id":"https://openalex.org/F4320326427","funder_display_name":"Innovation and Technology Fund"}],"funders":[{"id":"https://openalex.org/F4320326427","display_name":"Innovation and Technology Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W1956340063","https://openalex.org/W2118217749","https://openalex.org/W2140196014","https://openalex.org/W2140199336","https://openalex.org/W2146395539","https://openalex.org/W2178928294","https://openalex.org/W2185175083","https://openalex.org/W2186356322","https://openalex.org/W2194775991","https://openalex.org/W2251512949","https://openalex.org/W2293642747","https://openalex.org/W2489434015","https://openalex.org/W2552465432","https://openalex.org/W2752782242","https://openalex.org/W2783569857","https://openalex.org/W2785562966","https://openalex.org/W2964191079","https://openalex.org/W2969260367","https://openalex.org/W2981749440","https://openalex.org/W2997591391","https://openalex.org/W3000470288","https://openalex.org/W3012708638","https://openalex.org/W3015540635","https://openalex.org/W3018065762","https://openalex.org/W3034469748","https://openalex.org/W3090672847","https://openalex.org/W3090720321","https://openalex.org/W3097448661","https://openalex.org/W3106763294","https://openalex.org/W3135530072","https://openalex.org/W3140060010","https://openalex.org/W3160345508","https://openalex.org/W3160555381","https://openalex.org/W3160673571","https://openalex.org/W3171673455","https://openalex.org/W3173272744","https://openalex.org/W3183629544","https://openalex.org/W3202918664","https://openalex.org/W3217080256","https://openalex.org/W4205495609","https://openalex.org/W4289821645","https://openalex.org/W4292415545","https://openalex.org/W4312365925","https://openalex.org/W4312446817","https://openalex.org/W4312938066","https://openalex.org/W4312959373","https://openalex.org/W4313156423","https://openalex.org/W4313291310","https://openalex.org/W4372346379","https://openalex.org/W4385627414","https://openalex.org/W4386065808","https://openalex.org/W4386598313","https://openalex.org/W4386825164","https://openalex.org/W4387245321","https://openalex.org/W4390488855","https://openalex.org/W4390874575","https://openalex.org/W4391092988","https://openalex.org/W4392809953","https://openalex.org/W4401452460","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6694251005","https://openalex.org/W6726497184","https://openalex.org/W6735463952","https://openalex.org/W6754634825","https://openalex.org/W6761628794","https://openalex.org/W6763509872","https://openalex.org/W6773545853","https://openalex.org/W6791776128","https://openalex.org/W6796761347","https://openalex.org/W6800139874","https://openalex.org/W6839015040","https://openalex.org/W6849177959","https://openalex.org/W6852934099","https://openalex.org/W6859906311"],"related_works":["https://openalex.org/W2129829718","https://openalex.org/W2595043295","https://openalex.org/W2751842002","https://openalex.org/W3165542721","https://openalex.org/W4313046148","https://openalex.org/W4243608781","https://openalex.org/W142455045","https://openalex.org/W2096442341","https://openalex.org/W2387043686","https://openalex.org/W3180760233"],"abstract_inverted_index":{"In":[0,31,61],"recent":[1],"years,":[2],"large":[3,124],"visual":[4,25],"language":[5],"models":[6],"(LVLMs)":[7],"have":[8,164],"shown":[9],"impressive":[10],"performance":[11,57,149],"and":[12,49,94,100,105,134,168],"promising":[13,55],"generalization":[14,129,169],"capability":[15,96,130,170],"in":[16,27],"multi-modal":[17,162],"tasks,":[18,77],"thus":[19],"replacing":[20],"humans":[21],"as":[22],"receivers":[23],"of":[24,45,64,122,171],"information":[26],"various":[28,132],"application":[29],"scenarios.":[30],"this":[32],"paper,":[33],"we":[34,78],"pioneer":[35],"to":[36,53,151],"propose":[37,79],"a":[38,46,71,80],"variable":[39,107],"bitrate":[40,108],"image":[41,110],"compression":[42],"scheme":[43],"consisting":[44],"pre-editing":[47,68,103],"module":[48,104],"an":[50,66],"end-to-end":[51,109],"codec":[52,111],"achieve":[54,145],"rate-accuracy":[56,148],"for":[58,85,131],"different":[59],"LVLMs.":[60],"particular,":[62],"instead":[63],"optimizing":[65],"adaptive":[67],"network":[69],"towards":[70],"particular":[72],"task":[73],"or":[74],"several":[75],"representative":[76],"new":[81],"optimization":[82],"strategy":[83],"tailored":[84],"LVLMs,":[86],"which":[87,126],"is":[88],"designed":[89],"based":[90,118],"on":[91,119],"the":[92,106,116,123,140,152,166,172],"representation":[93],"discrimination":[95],"with":[97,161],"token-level":[98],"distortion":[99],"rank.":[101],"The":[102],"are":[112],"jointly":[113],"trained":[114],"by":[115],"losses":[117],"semantic":[120],"tokens":[121],"model,":[125],"introduce":[127],"enhanced":[128],"data":[133],"tasks.":[135],"Experimental":[136],"results":[137],"demonstrate":[138],"that":[139],"proposed":[141,173],"framework":[142],"could":[143],"efficiently":[144],"much":[146],"better":[147],"compared":[150],"state-of-the-art":[153],"coding":[154],"standard,":[155],"Versatile":[156],"Video":[157],"Coding.":[158],"Meanwhile,":[159],"experiments":[160],"tasks":[163],"revealed":[165],"robustness":[167],"framework.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}