AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

ReMatch: Boosting Representation through Matching for Multimodal Retrieval

Qianying Liu, Xiao Liang, Zhiqiang Zhang, Yibo Chen, Xu Tang, Zhongfei Qing, Fengfan Zhou, Yao Hu, Paul Henderson

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 6 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
tune training setup (LoRA, LR, cosine schedule, temperature) (ablation)VLM2Vec baseline · MMEB overallHit@1: 59.7 -> 65.5Improved
add target instructions (ablation)tuned baseline · MMEB overallHit@1: 65.5 -> 67.3Improved
add one explicit hard negative (ablation)tuned baseline · MMEB overallHit@1: 67.3 -> 67.9Improved
add multi-view query-document matching (MVQDM) (ablation)Exp3 baseline · MMEB overallHit@1: 67.9 -> 68.4Improved
add chat-style template to embedding extraction (MVQDM++) (ablation)Exp3 baseline · MMEB overallHit@1: 67.9 -> 68.8Improved
add multi embedding fusion with learnable tokens (ablation)Exp3 baseline · MMEB overallHit@1: 67.9 -> 68.7Improved
combine MVQDM++ and MEF (ablation)Exp3 baseline · MMEB overallHit@1: 67.9 -> 69.2Improved
use all raw/feature views instead of Feat <-> Feat only (ablation)MVQDM · MMEB overallHit@1: 68.1 -> 68.4Improved
raise matching loss weight from 0.1 to 0.4 (ablation)MVQDM · MMEB overallHit@1: 68.4 -> 68.0Hurt
average 32 learnable tokens without orthogonal regularization (ablation)Exp3 baseline · MMEB overallHit@1: 67.9 -> 68.2No clear effect
add orthogonal regularization at 64 tokens (ablation)Avg fusion · MMEB overallHit@1: 68.5 -> 68.8Improved
add orthogonal regularization at 4 tokens (ablation)Avg fusion · MMEB overallHit@1: 68.6 -> 68.3Hurt

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