AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Bridging Modalities via Progressive Re-alignment for Multimodal Test-Time Adaptation

Jiacheng Li, Songhe Feng

AAAI 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 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
use L_PMGFA instead of KL-divergence for feature alignment (ablation)BriMPR · Kinetics50-C (multimodal shift)average accuracy (%): 31.5 -> 40.5Improved
use L_PMGFA instead of squared moment matching (ablation)BriMPR · Kinetics50-C (multimodal shift)average accuracy (%): 34.5 -> 40.5Improved
use non-squared instead of squared moment matching (ablation)moment matching alignment · Kinetics50-C (multimodal shift)average accuracy (%): 34.5 -> 37.4Improved
add inter-modal instance-wise contrastive learning L_IICL (ablation)BriMPR · Kinetics50-C (multimodal shift)average accuracy (%): 40.5 -> 40.7Improved
add cross-modal masked embedding recombination L_CMER (ablation)BriMPR · Kinetics50-C (multimodal shift)average accuracy (%): 40.7 -> 40.9Improved
add L_CMER (ablation)BriMPR · VGGSound-C (audio corruption)average accuracy (%): 35.3 -> 36.5Improved
use correct CMER weights instead of swapped lambda^a and lambda^v (ablation)BriMPR · VGGSound-C (audio corruption)average accuracy (%): 32.1 -> 36.5Improved
use correct CMER weights instead of swapped lambda^a and lambda^v (ablation)BriMPR · Kinetics50-C (audio corruption)average accuracy (%): 70.0 -> 72.0Improved
apply BriMPR when dominant modality (video) is corruptedCAV-MAE · Kinetics50-C (video corruption)average accuracy (%): 60.5 -> 65.9Improved
apply BriMPR when dominant modality (audio) is corruptedCAV-MAE · VGGSound-C (audio corruption)average accuracy (%): 25.0 -> 36.5Improved
apply BriMPR on real-world shiftTransformer · MOSI to SIMSaccuracy (%): 46.0 -> 58.2Improved
apply unimodal TTA Tent to audio corruptionCAV-MAE · VGGSound-C (audio corruption)average accuracy (%): 25.0 -> 4.6Hurt

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