AI Paper Atlas

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

ACMM: Aligned Cross-Modal Memory for Few-Shot Image and Sentence Matching

Yan Huang, Liang Wang

ICCV 2019 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 71 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 shared memory after cross-modal alignment (ablation)ACMM align · Flickr30k (5000 test)mR: 76.5 -> 80.9Improved
add shared memory after cross-modal alignment (ablation)ACMM align · MSCOCO (5000 test)mR: 62.0 -> 70.6Improved
add relation modeling (visual GCN and bidirectional GRU) to align (ablation)ACMM align · Flickr30k (5000 test)mR: 68.7 -> 76.5Improved
add relation modeling (visual GCN and bidirectional GRU) to align (ablation)ACMM align · MSCOCO (5000 test)mR: 49.9 -> 62.0Improved
add cross-modal alignment before memory (ablation)ACMM memory · Flickr30k (5000 test)mR: 5.7 -> 80.9Improved
add cross-modal alignment before memory (ablation)ACMM memory · MSCOCO (5000 test)mR: 1.3 -> 70.6Improved
use shared memory instead of modality-specific memory (ablation)ACMM align + mem · Flickr30k (5000 test)mR: 73.9 -> 80.9Improved
use shared memory instead of modality-specific memory (ablation)ACMM align + mem · MSCOCO (5000 test)mR: 61.2 -> 70.6Improved
use shared memory without alignment instead of modality-specific (ablation)mem only · Flickr30k (5000 test)mR: 0.6 -> 5.7No clear effect
ensemble with lambda 0.5 and 0.8ACMM · Flickr30k (1000 test)mR: 80.9 -> 83.5Improved
ensemble with lambda 0.5 and 0.8ACMM · MSCOCO (5000 test)mR: 70.6 -> 73.6Improved
replace SCAN with ACMM on 1-shot test setSCAN · Flickr30k (5000 test), 1-shotmR: 67.1 -> 74.2Improved

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