AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

ProxyTTT: Proxy-driven Test-Time Training for Multi-modal Re-identification

Aihua Zheng, Zhaojun Liu, Xixi Wan, Chenglong Li, Jin Tang, Yan Yan

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modal object re-identification · 0 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 modality-common proxy (MCP) (ablation)ProxyTTT baseline · RGBNT201mAP (%): 75.4 -> 77.0Improved
add modality-specific proxy (MSP) (ablation)ProxyTTT · RGBNT201mAP (%): 77.0 -> 79.8Improved
add fine-grained reconstruction learning (FRL) (ablation)ProxyTTT · RGBNT201mAP (%): 79.8 -> 82.3Improved
add PESA test-time training (ablation)ProxyTTT · RGBNT201mAP (%): 82.3 -> 85.0Improved
add MPL to EDITOR (ablation)EDITOR · RGBNT201mAP (%): 66.5 -> 69.3Improved
add MPL to DeMo (ablation)DeMo · RGBNT201mAP (%): 77.4 -> 80.4Improved
use proxy-based pseudo-labels instead of classification head (ablation)PESA · RGBNT201mAP (%): 82.6 -> 83.9Improved
add entropy-based selection to proxy pseudo-labels (ablation)PESA · RGBNT201mAP (%): 83.9 -> 85.0Improved
add entropy selection to head pseudo-labels (ablation)PESA with Head · RGBNT201Rank-1 (%): mAP 82.6 -> 83.0; R-1 86.4 -> 85.4Mixed
test with missing RGB and TIR modalitiesProxyTTT vs DeMo · RGBNT201Rank-1 (%): M(RGB+TIR) R-1 24.9 (DeMo) -> 24.2Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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