AI Paper Atlas

Research map / Video / Action recognition

Synthetic Humans for Action Recognition from Unseen Viewpoints

Gül Varol, Ivan Laptev, Cordelia Schmid, Andrew Zisserman

IJCV 2021 · Video › Action recognition · approach: Disentangled action recognition · 99 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 synthetic videos to real trainingResNeXt-101 3D RGB · NTU CVS unseen 90 deg viewaccuracy (%): 53.6 -> 69.0Improved
add synthetic videos to real training (UESTC Cross View I RGB)ResNeXt-101 3D RGB · UESTC Cross View Iaccuracy (%): 49.4 -> 66.4Improved
add synthetic videos to real training (RGB+Flow)ResNeXt-101 3D · UESTC Cross View IIaccuracy (%): 81.7 -> 87.4Improved
add synthetic videos to real trainingResNeXt-101 3D RGB+Flow · NTU CSaccuracy (%): 90.0 -> 90.7Improved
add optical flow stream (late fusion) (ablation)Synth+Real RGB · NTU CVS 90 degaccuracy (%): 69.0 -> 71.1Improved
use VIBE instead of HMMR motion estimates for rendering (ablation)Synthetic data · NTU CVS 90 deg, RGB synthetic onlyaccuracy (%): 42.7 -> 45.3Improved
add more views to synthetic training (all 8 vs 0 deg only) (ablation)Synthetic-only training · NTU CVS 90 degaccuracy (%): 17.9 -> 38.8Improved
add video-level additive noise on joint rotations (ablation)Synthetic training, 10 seq/action · NTU CVS 0 degaccuracy (%): 33.1 -> 37.9Improved
add frame-level additive noise on joint rotations (ablation)Synthetic training · NTU CVS 0 degaccuracy (%): 33.1 -> 25.0Hurt
add pose interpolation augmentation (ablation)Synthetic training · NTU CVS 0 degaccuracy (%): 33.1 -> 35.7Mixed
add multi-person videos with xy translation (ablation)Synthetic training · NTU CVS 0 degaccuracy (%): 18.3 -> 28.5Improved
randomize camera height and distance (ablation)Synthetic training · NTU CVS 0 degaccuracy (%): 28.5 -> 31.3Improved

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