AI Paper Atlas

Research map / Video / Action recognition

Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks With Spatiotemporal Transformer Modules

Congqi Cao, Yifan Zhang, Yi Wu, Hanqing Lu, Jian Cheng

ICCV 2017 · Video › Action recognition · approach: Skeleton-based action recognition · 109 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 spatial affine transformer (STM) (ablation)C3D (RGB) · EgoGesture classification (RGB)accuracy: 0.864 -> 0.880Improved
use homography instead of affine transformation in spatial transformer (ablation)VGG16+LSTM+RSTM (RGB) · EgoGesture classification (RGB)accuracy: 0.812 -> 0.838Improved
use homography instead of affine transformation in spatial transformer (ablation)C3D+STM (RGB) · EgoGesture classification (RGB)accuracy: 0.880 -> 0.882Improved
extend spatial transformer to spatiotemporal transformer (STTM) (ablation)C3D+STM (H) (RGB) · EgoGesture classification (RGB)accuracy: 0.882 -> 0.887Improved
add LSTM over the whole gesture sequence (ablation)C3D (RGB) · EgoGesture classification (RGB)accuracy: 0.864 -> 0.889Improved
add STTM to C3D+LSTM (ablation)C3D+LSTM (RGB) · EgoGesture classification (RGB)accuracy: 0.889 -> 0.890Improved
add recurrent connections in the localization network (RSTTM) (ablation)C3D+LSTM+STTM (RGB) · EgoGesture classification (RGB)accuracy: 0.890 -> 0.893Improved
add STTM, then recurrence and LSTM, to C3D on walking scenesC3D (RGB) · EgoGesture walking scenes (4,6), RGBaccuracy: 0.828 -> 0.839 -> 0.868Improved
add STTM, then recurrence and LSTM, to C3D on stationary scenesC3D (RGB) · EgoGesture stationary scenes (1,2,3,5), RGBaccuracy: 0.866 -> 0.870 -> 0.882Improved
add STTM to C3D with RGB-D sliding-window detectionC3D-l16s8 · EgoGesture detection (RGB-D)Jaccard index: 0.698 -> 0.709Improved
add STTM to C3D with depth sliding-window detectionC3D-l16s8 · EgoGesture detection (depth)Jaccard index: 0.678 -> 0.681No clear effect
use smaller stride (8 instead of 16) for sliding windowC3D · EgoGesture detection (RGB-D)Jaccard index: 0.618 -> 0.698Improved

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