AI Paper Atlas

Research map / Video / Action recognition

Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition

Shreyank N Gowda, Marcus Rohrbach, Frank Keller, Laura Sevilla-Lara

ECCV 2022 · Video › Action recognition · approach: Disentangled action recognition · 40 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 the pairs Selector (ablation)L2A · UCF101 (20% labeled)accuracy: 55.8 -> 58.9Improved
add Video Compositing (ablation)L2A · UCF101 (20% labeled)accuracy: 54.5 -> 58.9Improved
add Semantic Matching (ablation)L2A · UCF101 (20% labeled)accuracy: 55.2 -> 58.9Improved
add all three components over the baseline (ablation)L2A · UCF101 (20% labeled)accuracy: 45.5 -> 58.9Improved
inpaint holes of removed objects in the background (ablation)L2A · UCF101 (20% labeled)accuracy: 57.6 -> 58.9Improved
use segmentation instead of bounding boxes (ablation)L2A · UCF101 (20% labeled)accuracy: 56.8 -> 58.9Improved
remove objects as well as humans from the foreground (ablation)L2A · UCF101 (20% labeled)accuracy: 55.7 -> 58.9Improved
mix semantically similar classes instead of the same class (ablation)L2A · UCF101 (20% labeled)accuracy: 41.4 -> 58.9Improved
re-train the classifier instead of joint training with the Selector (ablation)L2A · UCF101 (20% labeled)accuracy: 57.4 -> 60.3Improved
pre-train the Selector on Kinetics-400 and fix it (ablation)L2A · UCF101 (20% labeled)accuracy: 60.3 -> 64.8Improved
use the learned Selector instead of SMART-based selection (ablation)L2A · UCF101 (20% labeled)accuracy: 58.9 -> 60.3Improved
use semantic class matching instead of random matching in few-shot (ablation)C3D-PN + L2A · HMDB51 few-shot (TruZe split, 5-shot)accuracy: 47.7 -> 50.8Improved

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