AI Paper Atlas

Research map / Video / Video segmentation and tracking

Egocentric Activity Prediction via Event Modulated Attention

Yang Shen, Bingbing Ni, Zefan Li, Ning Zhuang

ECCV 2018 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 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 asynchronous event-sequence LSTM branch instead of time-series only (ablation)Time series LSTM · GTEA Gazeprediction accuracy: 0.581 -> 0.612Improved
add asynchronous event-sequence LSTM branch instead of time-series only (ablation)Time series LSTM · GTEA Gaze+prediction accuracy: 0.614 -> 0.659Improved
fuse synchronous and asynchronous features (ablation)Event sequence LSTM · GTEA Gazeprediction accuracy: 0.612 -> 0.632Improved
fuse synchronous and asynchronous features (ablation)Event sequence LSTM · GTEA Gaze+prediction accuracy: 0.659 -> 0.674Improved
add event modulated attention (ablation)Fusion LSTMs · GTEA Gazeprediction accuracy: 0.632 -> 0.648Improved
add event modulated attention (ablation)Fusion LSTMs · GTEA Gaze+prediction accuracy: 0.674 -> 0.687Improved
use Rubicon Boundaries re-annotated labelsTime series LSTM recognition · GTEA Gaze+recognition accuracy: 0.671 -> 0.686Improved
use gaze-based LSTM instead of joint training CNNsAttention based LSTMs motion prediction · GTEA Gaze+motion prediction accuracy: 0.576 -> 0.842Improved
add event modulated attention under Gaussian noise (ablation)Fusion LSTMs · GTEA Gazeaccuracy drop under noise: drops 14.5% -> 13.1%Improved
use our gaze-event two-stream LSTM instead of Ego ConvNet 2D+3Dprediction · GTEA Gazeprediction accuracy: 0.514 -> 0.632Improved

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