AI Paper Atlas

Research map / Video / Action recognition

Cross-Modal Learning with 3D Deformable Attention for Action Recognition

Sangwon Kim, Dasom Ahn, Byoung Chul Ko

ICCV 2023 · Video › Action recognition · approach: Disentangled action recognition · 56 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 3D deformable attention (ablation)3D deformable transformer · PennActiontop-1 accuracy (%): 94.8 -> 99.7Improved
add joint stride attention (ablation)3D deformable transformer · PennActiontop-1 accuracy (%): 98.2 -> 99.7Improved
add temporal stride attention (ablation)3D deformable transformer · PennActiontop-1 accuracy (%): 98.5 -> 99.7Improved
use cross-modal tokens instead of a single shared token (ablation)3D deformable transformer · PennActiontop-1 accuracy (%): 97.0 -> 99.7Improved
use cross-modal tokens instead of averaging RGB and pose tokens (ablation)3D deformable transformer · PennActiontop-1 accuracy (%): 92.2 -> 99.7Improved
set temporal stride to about half the window size (ablation)temporal stride attention · PennActiontop-1 accuracyImproved
use 12 input frames instead of fewer (ablation)3D deformable transformer · PennActiontop-1 accuracyImproved
train without pre-training versus pre-trained PoseC3D3D deformable transformer · FineGYMmean accuracy (%): 95.6 -> 90.3Hurt

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