cd /news/artificial-intelligence/test-time-adaptation-with-online-per… · home topics artificial-intelligence article
[ARTICLE · art-89856] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Test-Time Adaptation with Online Personalized Energy-Based Cache for Fine-Grained Video Expression Recognition

Researchers introduced EB-CaP, a test-time adaptation method for video facial expression recognition that personalizes class prototypes per target video using an energy-based model and CLIP embeddings, outperforming state-of-the-art TTA methods on BioVid, StressID, and BAH benchmarks while maintaining low computational and memory overhead.

read1 min views1 publishedAug 10, 2026

arXiv:2608.06467v1 Announce Type: new Abstract: Facial expression recognition (FER) in videos is challenging because models must identify subtle, temporally evolving affective states that vary across individuals. Although vision-language models provide transferable visual-semantic representations, models trained on subject-independent data often degrade under subject-specific distribution shifts at inference time. Existing test-time adaptation (TTA) methods commonly update model parameters during inference, increasing computational cost and latency. Cache-based methods avoid parameter updates, but they usually require enough target samples to form reliable class prototypes, which is difficult early in adaptation and for rarely observed classes. We introduce Energy-Based Cache Personalization (EB-CaP), a subject-based online TTA method for video FER that generates class-specific prototypes personalized to each target video. EB-CaP uses a lightweight energy-based model to sample prototypes from the current unlabeled video and populate a personalized cache online, without accumulating large amounts of target data or storing diverse source prototypes. Its energy function relies only on pretrained CLIP: similarities between the target video embedding and class text embeddings guide prototype sampling. In parallel, positive and negative caches store reliable and uncertain target embeddings. An adaptive entropy gate controls cache updates according to the evolving confidence distribution, while a diversity gate limits redundant samples. Final predictions combine cache-derived scores with the current CLIP scores. Experiments on BioVid, StressID, and BAH show that EB-CaP outperforms state-of-the-art TTA methods while maintaining low computational and memory overhead. Code is available at https://github.com/MasoumehSharafi/EB-CaP.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @eb-cap 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/test-time-adaptation…] indexed:0 read:1min 2026-08-10 ·