AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Active Contrastive Learning of Audio-Visual Video Representations

Shuang Ma, Zhaoyang Zeng, Daniel McDuff, Yale Song

ICLR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 46 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
replace random negative sampling with active samplingXMoCo · UCF101top-1 accuracy: 74.1 -> 77.2 (+3.1)Improved
replace random negative sampling with active samplingXMoCo · HMDB51top-1 accuracy: 38.7 -> 40.6 (+1.9)Improved
replace random negative sampling with active samplingXMoCo · ESC50top-1 accuracy: 73.0 -> 79.2 (+6.2)Improved
add the additional FC layers for cross-modal gradient flow (ablation)CM-ACC · UCF101top-1 accuracy: 75.8 -> 77.2Improved
add the additional FC layers for cross-modal gradient flow (ablation)CM-ACC · HMDB51top-1 accuracy: 39.1 -> 40.6Improved
add the additional FC layers for cross-modal gradient flow (ablation)CM-ACC · ESC50top-1 accuracy: 77.3 -> 79.2Improved
use gradient embeddings rather than feature embeddings for active sampling (ablation)CM-ACC · UCF101top-1 accuracy: 74.5 -> 77.2 (+2.7)Improved
use gradient embeddings rather than feature embeddings for active sampling (ablation)CM-ACC · HMDB51top-1 accuracy: 38.2 -> 40.6 (+2.4)Improved
use gradient embeddings rather than feature embeddings for active sampling (ablation)CM-ACC · ESC50top-1 accuracy: 75.1 -> 79.2 (+4.1)Improved
replace random sampling with OHEMcontrastive pretraining · UCF101, M=32top-1 accuracy: 61.9 -> 50.2 (-11.7)Hurt
replace random sampling with OHEMcontrastive pretraining · HMDB51, M=32top-1 accuracy: 33.1 -> 26.8 (-6.3)Hurt
replace random sampling with active samplingcontrastive pretraining · UCF101, M=32top-1 accuracy: 61.9 -> 78.0 (+16.1)Improved

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