MétaCan
Menu
Back to cohort
Record W2108373964 · doi:10.1142/s0219467809003551

PECSI: A PRACTICAL PERCEPTUALLY-ENHANCED COMPRESSION FRAMEWORK FOR STILL IMAGES

2009· article· en· W2108373964 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueInternational Journal of Image and Graphics · 2009
Typearticle
Languageen
FieldComputer Science
TopicImage and Video Quality Assessment
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsUpsamplingImage compressionComputer scienceArtificial intelligenceComputer visionQuantization (signal processing)Image qualityCompression (physics)Data compressionPerceptionData compression ratioTexture compressionEncoding (memory)Image (mathematics)Image processing

Abstract

fetched live from OpenAlex

This paper presents PECSI, a perceptually-enhanced image compression framework designed to provide high compression rates for still images while preserving visual quality. PECSI utilizes important human perceptual characteristics during image encoding stages (e.g. downsampling and quantization) and image decoding stages (e.g. upsampling and deblocking) to find a better balance between image compression and the perceptual quality of an image. The proposed framework is computationally efficient and easy to integrate into existing block-based still image compression standards. Experimental results show that the PECSI framework provides improved perceptual quality at the same compression rate as existing still image compression methods. Alternatively, the framework can be used to achieve higher compression ratios while maintaining the same level of perceptual quality.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: Theoretical or conceptual
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.567
Threshold uncertainty score0.425

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.033
GPT teacher head0.394
Teacher spread0.361 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it