{"id":"https://openalex.org/W7161182368","doi":"https://doi.org/10.1109/dcc66757.2026.00027","title":"MG-VLQA: Multi-Granularity Quality Assessment for Image Compression via Visual Language Models","display_name":"MG-VLQA: Multi-Granularity Quality Assessment for Image Compression via Visual Language Models","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7161182368","doi":"https://doi.org/10.1109/dcc66757.2026.00027"},"language":null,"primary_location":{"id":"doi:10.1109/dcc66757.2026.00027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc66757.2026.00027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Data Compression Conference (DCC)","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/A5065859286","display_name":"Hui Li","orcid":"https://orcid.org/0000-0001-9198-3951"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanfei Li","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129641139","display_name":"Anle Ke","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anle Ke","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102931927","display_name":"Jiawen Gu","orcid":"https://orcid.org/0000-0002-9433-4698"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawen Gu","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136118607","display_name":"Chao Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Zhou","raw_affiliation_strings":["Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051849668","display_name":"T -Y Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Chen","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136104821","display_name":"Zhan Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Ma","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5065859286"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94957716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.6814000010490417,"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":0.6814000010490417,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.23029999434947968,"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":0.016100000590085983,"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/quality-assessment","display_name":"Quality assessment","score":0.51910001039505},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.43529999256134033},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.4129999876022339},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.3970000147819519},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3880000114440918},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3785000145435333},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.365200012922287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6419000029563904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5978000164031982},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5508999824523926},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.51910001039505},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.43529999256134033},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.4129999876022339},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dcc66757.2026.00027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dcc66757.2026.00027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Data Compression Conference (DCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"significant":[1],"advances":[2],"in":[3],"image":[4,59],"compression,":[5],"existing":[6],"evaluation":[7],"metrics":[8,36],"remain":[9],"poorly":[10],"aligned":[11],"with":[12,68,141],"human":[13,142],"visual":[14],"perception-particularly":[15],"under":[16],"extremely":[17],"low":[18],"bitrates,":[19],"where":[20],"reconstructed":[21],"images":[22],"often":[23],"suffer":[24],"from":[25],"abstract":[26],"distortions":[27],"or":[28],"semantic":[29,66,111],"degradation":[30],"that":[31,52,135],"are":[32],"difficult":[33],"for":[34],"conventional":[35],"to":[37,57],"capture.":[38],"To":[39],"address":[40],"this":[41],"limitation,":[42],"we":[43],"propose":[44],"MG-VLQA,":[45],"a":[46,75,116],"novel":[47],"multi-granularity":[48],"quality":[49],"assessment":[50,123],"framework":[51],"leverages":[53],"VisionLanguage":[54],"Models":[55],"(VLMs)":[56],"evaluate":[58],"reconstruction":[60],"fidelity":[61,91],"through":[62],"the":[63,69],"lens":[64],"of":[65,77,124],"consistency":[67],"original":[70],"caption.":[71],"Our":[72],"method":[73],"formulates":[74],"suite":[76],"captionderived":[78],"questions":[79],"spanning":[80],"three":[81],"complementary":[82],"dimensions:":[83],"(1)":[84],"entity":[85],"presence":[86],"(semantic":[87],"completeness),":[88],"(2)":[89],"detail":[90],"(local":[92],"appearance":[93],"accuracy),":[94],"and":[95,110,120,132,144],"(3)":[96],"inter-entity":[97],"interactions":[98],"(relational":[99],"coherence).":[100],"By":[101],"simulating":[102],"human-like":[103],"perceptual":[104],"judgment":[105,143],"via":[106],"VLMbased":[107],"question":[108],"answering":[109],"similarity":[112],"scoring,":[113],"MG-VLQA":[114],"provides":[115],"more":[117],"interpretable,":[118],"fine-grained,":[119],"perceptually":[121],"relevant":[122],"compression":[125],"quality.":[126],"Extensive":[127],"experiments":[128],"across":[129],"multiple":[130],"datasets":[131],"codecs":[133],"demonstrate":[134],"our":[136],"metric":[137],"achieves":[138],"higher":[139],"correlation":[140],"offers":[145],"superior":[146],"discriminative":[147],"power.":[148]},"counts_by_year":[],"updated_date":"2026-05-16T06:04:12.930555","created_date":"2026-05-15T00:00:00"}