AI Paper Atlas

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

Identity-Aware Textual-Visual Matching With Latent Co-Attention

Shuang Li, Tong Xiao, Hongsheng Li, Wei Yang, Xiaogang Wang

ICCV 2017 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 290 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 CMCE loss instead of triplet loss (ablation)Stage-1 · CUHK-PEDES text-to-image retrievaltop-1 accuracy: 14.76 -> 21.55Improved
use CMCE loss instead of triplet loss (ablation)Stage-1 · CUB image-to-texttop-1 accuracy: 52.5 -> 61.5Improved
use CMCE loss instead of triplet loss (ablation)Stage-1 · CUB text-to-imageAP@50: 52.4 -> 55.5Improved
use CMCE loss instead of triplet loss (ablation)Stage-1 · Flower image-to-texttop-1 accuracy: 64.3 -> 68.4Improved
use CMCE loss instead of triplet loss (ablation)Stage-1 · Flower text-to-imageAP@50: 64.9 -> 68.0Improved
use identity-level annotations (ablation)Stage-2 · CUHK-PEDES text-to-image retrievaltop-1 accuracy: 23.47 -> 25.94Improved
use identity-level annotations (ablation)Stage-2 · CUHK-PEDES text-to-image retrievaltop-10 accuracy: 54.77 -> 60.48Improved
add latent semantic attention (ablation)Stage-2 · CUHK-PEDES text-to-image retrievaltop-1 accuracy: 23.58 -> 25.94Improved
add latent semantic attention (ablation)Stage-2 · CUHK-PEDES text-to-image retrievaltop-10 accuracy: 58.68 -> 60.48Improved
add spatial attention (ablation)Stage-2 w/o SMA · CUHK-PEDES text-to-image retrievaltop-1 accuracy: 22.11 -> 23.58Improved
add spatial attention (ablation)Stage-2 w/o SMA · CUHK-PEDES text-to-image retrievaltop-10 accuracy: 58.05 -> 58.68Improved
add stage-1 initialization and easy-negative screening (ablation)Stage-2 w/o SMA+SPA · CUHK-PEDES text-to-image retrievaltop-1 accuracy: 17.19 -> 22.11Improved

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