AI Paper Atlas

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

Deep Cross-Modal Projection Learning for Image-Text Matching

Ying Zhang, Huchuan Lu

ECCV 2018 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 520 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 softmax classification loss to CMPM (ablation)CMPM · CUHK-PEDES image-to-textR@1: 44.02 -> 45.38Improved
add weight normalization to softmax classification (ablation)CMPM+softmax · CUHK-PEDES text-to-imageR@1: 45.38 -> 47.12Improved
add weight normalization to softmax classification (ablation)CMPM+softmax · CUHK-PEDES image-to-textR@1: 55.14 -> 56.51Improved
add cross-modal projection on top of weight-normalized softmax (full CMPC) (ablation)CMPM+softmax+normW · CUHK-PEDES text-to-imageR@1: 47.12 -> 49.37Improved
add CMPM matching loss to CMPC-only classification (ablation)CMPC · CUHK-PEDES text-to-imageR@1: 42.25 -> 49.37Improved
add weight normalization to CMPC alone (ablation)CMPC without CMPM · CUHK-PEDES text-to-imageR@1: 16.93 -> 42.25Improved
add CMPC loss to CMPM (ablation)CMPM · CUHK-PEDES text-to-imageR@1: 44.02 -> 49.37Improved
add CMPC loss to CMPM (ResNet-152) (ablation)CMPM · Flickr30K text-to-imageR@1: 35.7 -> 37.3Improved
add CMPC loss to CMPM (MobileNet) (ablation)CMPM · MSCOCO 1K image-to-textR@1: 51.4 -> 52.9Improved
replace MobileNet with ResNet-152 image encoderCMPM · Flickr30K image-to-textR@1: 37.1 -> 48.3Improved
replace KL(q||p) with CMPM (KL direction) at batch size 128 (ablation)matching loss · CUHK-PEDES text-to-imageR@1: 36.06 -> 42.43Improved
use CMPM instead of N-pair loss for image-to-text at batch size 64 (ablation)matching loss · CUHK-PEDES image-to-textR@1: 12.07 -> 51.98Improved

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