AI Paper Atlas

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

Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning

Min Cao, Xinyu Zhou, Ding Jiang, Bo Du, Mang Ye, Min Zhang

TPAMI 2025 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 5 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 bi-lingual MLM and cross-lingual D-MIM (Bi-IRR) (ablation)Bi-IRRA · CUHK-PEDES(M) EnglishR@1 (%): 76.97 -> 78.82Improved
add bi-lingual MLM (ablation)Bi-IRRA · CUHK-PEDES(M) EnglishR@1 (%): 77.81 -> 78.82Improved
add cross-lingual D-MIM (ablation)Bi-IRRA · CUHK-PEDES(M) EnglishR@1 (%): 77.49 -> 78.82Improved
replace SDM with Md-GA global alignment (ablation)Bi-IRRA · CUHK-PEDES(M) EnglishR@1 (%): 66.89 -> 78.82Improved
add ID loss (ablation)Bi-IRRA · CUHK-PEDES(M) EnglishR@1 (%): 78.82 -> 78.28No clear effect
use LDAT pipeline instead of direct LLM translation (ablation)Bi-IRRA · CUHK-PEDES(M) EnglishR@1 (%): 78.09 -> 78.82Improved
use MLLM instead of LLM for direct translation (ablation)Bi-IRRA · CUHK-PEDES(M) EnglishR@1 (%): 78.09 -> 78.61Improved
use MLLM instead of LLM in rewriting phase of LDAT (ablation)LDAT · CUHK-PEDES(M) EnglishR@1 (%): 78.22 -> 78.82Improved
use blockwise masking instead of random masking in D-MIM (ablation)Bi-IRRA · CUHK-PEDES(M) EnglishR@1 (%): 78.17 -> 78.82Improved
use blockwise masking instead of gridwise masking (ablation)Bi-IRRA · CUHK-PEDES(M) EnglishR@1 (%): 77.89 -> 78.82Improved
use feature distillation with source-text teacher and target-text student, instead of swapped roles (ablation)Bi-IRRA · CUHK-PEDES(M) EnglishR@1 (%): 78.59 -> 78.82Improved
mask the image paired with target text in A-ITM (ablation)Bi-IRRA · CUHK-PEDES(M) EnglishR@1 (%): 77.92 -> 78.82Improved

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