{"id":"https://openalex.org/W7123425433","doi":"https://doi.org/10.1109/mmsp64401.2025.11324356","title":"Latent Space Stability vs. Perceptual Sensitivity: A Study of Visual Encoders under Distortion","display_name":"Latent Space Stability vs. Perceptual Sensitivity: A Study of Visual Encoders under Distortion","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7123425433","doi":"https://doi.org/10.1109/mmsp64401.2025.11324356"},"language":null,"primary_location":{"id":"doi:10.1109/mmsp64401.2025.11324356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","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/A5036140037","display_name":"Abderrezzaq Sendjasni","orcid":"https://orcid.org/0000-0002-6533-5675"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Abderrezzaq Sendjasni","raw_affiliation_strings":["Univ. Poitiers, XLIM, UMR,CNRS,France,7252"],"affiliations":[{"raw_affiliation_string":"Univ. Poitiers, XLIM, UMR,CNRS,France,7252","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122961887","display_name":"Mohamed-Chaker Larabi","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohamed-Chaker Larabi","raw_affiliation_strings":["Univ. Poitiers, XLIM, UMR,CNRS,France,7252"],"affiliations":[{"raw_affiliation_string":"Univ. Poitiers, XLIM, UMR,CNRS,France,7252","institution_ids":["https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036140037"],"corresponding_institution_ids":["https://openalex.org/I1294671590"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68912776,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"334","last_page":"339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9702000021934509,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9702000021934509,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.012900000438094139,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.002099999925121665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6061999797821045},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5368000268936157},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5178999900817871},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.508899986743927},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4943999946117401},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.4560999870300293},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4325000047683716},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4244999885559082},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.40939998626708984},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.3625999987125397}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6604999899864197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6297000050544739},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6061999797821045},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5368000268936157},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5178999900817871},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4837999939918518},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4560999870300293},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4325000047683716},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.3625999987125397},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C22033958","wikidata":"https://www.wikidata.org/wiki/Q7167036","display_name":"Perceptual learning","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27720001339912415},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C207363949","wikidata":"https://www.wikidata.org/wiki/Q462915","display_name":"Visual space","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp64401.2025.11324356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp64401.2025.11324356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5183045268058777,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2046119925","https://openalex.org/W2055745001","https://openalex.org/W2085518012","https://openalex.org/W2133665775","https://openalex.org/W2141983208","https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2286686646","https://openalex.org/W2563786098","https://openalex.org/W2737134362","https://openalex.org/W2754213847","https://openalex.org/W2798581339","https://openalex.org/W2963975576","https://openalex.org/W3035719652","https://openalex.org/W3159481202","https://openalex.org/W3194293177","https://openalex.org/W4214745154","https://openalex.org/W4312443924","https://openalex.org/W4382462760","https://openalex.org/W4408355256"],"related_works":[],"abstract_inverted_index":{"Robust":[0],"and":[1,13,37,50,62,72,82,101],"distortion-aware":[2],"visual":[3,15,30],"representations":[4],"are":[5],"paramount":[6],"for":[7,114],"perceptual":[8,102],"image":[9],"quality":[10,103],"assessment":[11],"(IQA)":[12],"downstream":[14],"understanding":[16],"under":[17,39],"real-world":[18],"degradations.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23],"conduct":[24],"a":[25,86],"comprehensive":[26],"analysis":[27],"of":[28,111],"state-of-the-art":[29],"encoders,":[31],"including":[32],"CLIP,":[33],"DINO,":[34],"ConvNeXt,":[35],"EfficientNet,":[36],"ResNet,":[38],"common":[40],"distortions":[41,91],"such":[42],"as":[43],"Gaussian":[44,51],"blur,":[45,47],"motion":[46],"compression":[48],"artifacts,":[49],"noise.":[52],"We":[53],"employ":[54],"latent":[55,94],"feature":[56],"divergence,":[57],"ANOVA-based":[58],"effect":[59],"size":[60],"analysis,":[61],"dimension-wise":[63],"mean":[64],"absolute":[65],"differences":[66],"(MAD)":[67],"to":[68,89],"assess":[69],"model":[70],"robustness":[71],"sensitivity.":[73],"Our":[74],"results":[75],"reveal":[76],"how":[77],"architectural":[78],"choices,":[79],"training":[80],"objectives,":[81],"data":[83],"diversity":[84],"shape":[85],"model\u2019s":[87],"ability":[88],"encode":[90],"within":[92],"its":[93],"space.":[95],"These":[96],"findings":[97],"bridge":[98],"representation":[99],"learning":[100],"modeling,":[104],"offering":[105],"new":[106],"insights":[107],"into":[108],"the":[109],"development":[110],"distortion-resilient":[112],"encoders":[113],"IQA.":[115]},"counts_by_year":[],"updated_date":"2026-01-14T23:44:37.837170","created_date":"2026-01-14T00:00:00"}