Test-Time Adaptation via Cache Personalization for Facial Expression Recognition in Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sharafi, Masoumeh, Zeeshan, Muhammad Osama, Belharbi, Soufiane, Koerich, Alessandro Lameiras, Pedersoli, Marco, Granger, Eric
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914416374579200
author Sharafi, Masoumeh
Zeeshan, Muhammad Osama
Belharbi, Soufiane
Koerich, Alessandro Lameiras
Pedersoli, Marco
Granger, Eric
author_facet Sharafi, Masoumeh
Zeeshan, Muhammad Osama
Belharbi, Soufiane
Koerich, Alessandro Lameiras
Pedersoli, Marco
Granger, Eric
contents Facial expression recognition (FER) in videos requires model personalization to capture the considerable variations across subjects. Vision-language models (VLMs) offer strong transfer to downstream tasks through image-text alignment, but their performance can still degrade under inter-subject distribution shifts. Personalizing models using test-time adaptation (TTA) methods can mitigate this challenge. However, most state-of-the-art TTA methods rely on unsupervised parameter optimization, introducing computational overhead that is impractical in many real-world applications. This paper introduces TTA through Cache Personalization (TTA-CaP), a cache-based TTA method that enables cost-effective (gradient-free) personalization of VLMs for video FER. Prior cache-based TTA methods rely solely on dynamic memories that store test samples, which can accumulate errors and drift due to noisy pseudo-labels. TTA-CaP leverages three coordinated caches: a personalized source cache that stores source-domain prototypes, a positive target cache that accumulates reliable subject-specific samples, and a negative target cache that stores low-confidence cases as negative samples to reduce the impact of noisy pseudo-labels. Cache updates and replacement are controlled by a tri-gate mechanism based on temporal stability, confidence, and consistency with the personalized cache. Finally, TTA-CaP refines predictions through fusion of embeddings, yielding refined representations that support temporally stable video-level predictions. Our experiments on three challenging video FER datasets, BioVid, StressID, and BAH, indicate that TTA-CaP can outperform state-of-the-art TTA methods under subject-specific and environmental shifts, while maintaining low computational and memory overhead for real-world deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21309
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Test-Time Adaptation via Cache Personalization for Facial Expression Recognition in Videos
Sharafi, Masoumeh
Zeeshan, Muhammad Osama
Belharbi, Soufiane
Koerich, Alessandro Lameiras
Pedersoli, Marco
Granger, Eric
Computer Vision and Pattern Recognition
Facial expression recognition (FER) in videos requires model personalization to capture the considerable variations across subjects. Vision-language models (VLMs) offer strong transfer to downstream tasks through image-text alignment, but their performance can still degrade under inter-subject distribution shifts. Personalizing models using test-time adaptation (TTA) methods can mitigate this challenge. However, most state-of-the-art TTA methods rely on unsupervised parameter optimization, introducing computational overhead that is impractical in many real-world applications. This paper introduces TTA through Cache Personalization (TTA-CaP), a cache-based TTA method that enables cost-effective (gradient-free) personalization of VLMs for video FER. Prior cache-based TTA methods rely solely on dynamic memories that store test samples, which can accumulate errors and drift due to noisy pseudo-labels. TTA-CaP leverages three coordinated caches: a personalized source cache that stores source-domain prototypes, a positive target cache that accumulates reliable subject-specific samples, and a negative target cache that stores low-confidence cases as negative samples to reduce the impact of noisy pseudo-labels. Cache updates and replacement are controlled by a tri-gate mechanism based on temporal stability, confidence, and consistency with the personalized cache. Finally, TTA-CaP refines predictions through fusion of embeddings, yielding refined representations that support temporally stable video-level predictions. Our experiments on three challenging video FER datasets, BioVid, StressID, and BAH, indicate that TTA-CaP can outperform state-of-the-art TTA methods under subject-specific and environmental shifts, while maintaining low computational and memory overhead for real-world deployment.
title Test-Time Adaptation via Cache Personalization for Facial Expression Recognition in Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.21309