AI Paper Atlas

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

Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts

Bingqing Zhang, Zhuo Cao, Heming Du, Yang Li, Xue Li, Jiajun Liu, Sen Wang

ICLR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 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 HAT-VTR (hubness suppression + multi-granular TCR) to CLIP4ClipCLIP4Clip · MSRVTT-1kA v2t, severity 5R@1 avg: 17.0 -> 26.2Improved
add HAT-VTR to XpoolXpool · MSRVTT-1kA v2t, severity 5R@1 avg: 20.0 -> 30.3Improved
add HAT-VTR to CLIP4ClipCLIP4Clip · ActivityNet v2t, highest severityR@1 avg: 12.41 -> 22.28Improved
apply existing TTA methods (Tent, READ, SAR, EATA) to CLIP4ClipCLIP4Clip · ActivityNet v2t, highest severityR@1 avg: 12.41 -> 10.23 (Tent), 11.07 (EATA)Hurt
apply existing TTA methods (Tent, READ, SAR) to CLIP4ClipCLIP4Clip · MSRVTT-1kA v2t, severity 5R@1 avg: 17.0 -> 16.8 (Tent), 17.0 (READ), 17.2 (SAR)No clear effect
add TCR to CLIP4ClipCLIP4Clip · MSRVTT->ActivityNet cross-dataset v2tR@1: 32.64 -> 19.28Hurt
add HAT-VTR to CLIPCLIP · zero-shot adaptation, MSRVTT v2tR@1: 26.50 -> 35.40Improved
add HSM at posterior reranking (ablation)HAT-VTR · HSM ablation, v2tR@1: 23.3 -> 25.5Improved
add HSM at target selection (ablation)HAT-VTR · HSM ablation, v2tR@1: 23.3 -> 23.6Improved
add HSM at both target selection and reranking (ablation)HAT-VTR · HSM ablationavg R@1: 28.0 -> 30.1Improved
add noise-robust entropy term L_NA (ablation)HAT-VTR adaptation loss · adaptation-loss ablation, v2tR@1: 22.6 -> 24.1Improved
add multi-granular uniformity losses L_inter and L_intra (ablation)HAT-VTR adaptation loss · adaptation-loss ablation, v2tR@1: 22.6 -> 24.3Improved

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