AI Paper Atlas

Research map / Video / Video-language understanding

CLIP-AUTT: Test-Time Personalization with Action Unit Prompting for Fine-Grained Video Emotion Recognition

Muhammad Osama Zeeshan, Masoumeh Sharafi, Benoît Savary, Alessandro Lameiras Koerich, Marco Pedersoli, Eric Granger

ECCV 2026 · Video › Video-language understanding · approach: Video-language pretraining · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add minimum-entropy temporal window selection (ablation)CLIP-AU · BioVidWAR (%): 78.0 -> 78.7Improved
add minimum-entropy temporal window selection (ablation)CLIP-AU · BioVidF1 (%): 74.8 -> 75.2Improved
add AU prompt tuning at test time (ablation)CLIP-AU · BioVidWAR (%): 78.0 -> 80.0Improved
add AU prompt tuning at test time (ablation)CLIP-AU · BioVidF1 (%): 74.8 -> 76.4Improved
add both window selection and AU prompt tuning (ablation)CLIP-AU · BioVidWAR (%): 78.0 -> 81.5Improved
add both window selection and AU prompt tuning (ablation)CLIP-AU · BioVidF1 (%): 74.8 -> 78.0Improved
add test-time personalization (CLIP-AUTT) on top of CLIP-AUCLIP-AU · StressIDF1 (%): 58.5 -> 77.9Improved
add test-time personalization (CLIP-AUTT) on top of CLIP-AUCLIP-AU · BAHWAR (%): 68.3 -> 69.8Improved
use AU prompts instead of AU-free fine-tuning (CLIP-AU vs full CLIP FT)CLIP-ViT-B/32 · BioVidWAR (%): 69.7 -> 78.0Improved
use AU prompts instead of AU-free fine-tuning (CLIP-AU vs EmoCLIP)CLIP-AU · StressIDWAR (%): 67.0 vs 66.5Mixed
replace AU prompts with 46 generic class prompts (ablation)CLIP-AUTT · StressIDWAR (%): nearly a 15% dropHurt
vary temporal window length from 4 to 72 frames (ablation)CLIP-AUTT · BioVidWAR (%)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy