activity
20232026
most citedImage Coding for Machines via Feature-Preserving Rate-Distortion Optimization

1 citations · 2 across the 9 of their papers we have counts for

collaborators

12 papers

eess.IV2026

Rate-distortion optimization for full-reference image quality metrics via stochastic Hessian estimates

Samuel Fernández-Menduiña, Eduardo Pavez, Antonio Ortega

Block-based video codecs select coding parameters based on the input by optimizing a rate-distortion trade-off. The conventional distortion choice, the sum of squared errors (SSE),…

cs.LG2026

Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms

Samuel Fernández-Menduiña, Amir Ziashahabi, Eduardo Pavez +2

Long-context LLM decoding reads the key-value (KV) cache at every step. Loading it takes longer than computing attention over it, so throughput is bandwidth-bound. Hence, reducing…

eess.IV2026

FaSST: Fast Sparsifying Secondary Transform

Darukeesan Pakiyarajah, Samuel Fernández-Menduiña, Eduardo Pavez +2

Data-dependent secondary transforms, which aim to decorrelate coefficients of a separable primary transform, can improve residual coding efficiency; however, their deployment is of…

eess.IV2026

Rate-Distortion Optimization for Ensembles of Non-Reference Metrics

Xin Xiong, Samuel Fernández-Menduiña, Eduardo Pavez +3

Non-reference metrics (NRMs) can assess the visual quality of images and videos without a reference, making them well-suited for the evaluation of user-generated content. Nonethele…

cs.LG2026

L2G-Net: Local to Global Spectral Graph Neural Networks via Cauchy Factorizations

Samuel Fernández-Menduiña, Eduardo Pavez, Antonio Ortega

Despite their theoretical advantages, spectral methods based on the graph Fourier transform (GFT) are seldom used in graph neural networks (GNNs) due to the cost of computing the e…

eess.IV2026

Wrapper-Aware Rate-Distortion Optimization in Feature Coding for Machines

Samuel Fernández-Menduiña, Hyomin Choi, Fabien Racapé +2

Feature coding for machines (FCM) is a lossy compression paradigm for split-inference. The transmitter encodes the outputs of the first part of a neural network before sending them…