AI Paper Atlas

Research map / Video / Action recognition

Temporal Dynamic Graph LSTM for Action-Driven Video Object Detection

Yuan Yuan, Xiaodan Liang, Xiaolong Wang, Dit-Yan Yeung, Abhinav Gupta

ICCV 2017 · Video › Action recognition · approach: Fully supervised temporal action detection · 92 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 dynamic temporal graph between region proposals (ablation)TD-Graph LSTM · Charades (action-driven weak supervision)classification mAP: 17.13 -> 19.52Improved
add dynamic temporal graph between region proposals (ablation)TD-Graph LSTM · Charades (action-driven weak supervision)detection mAP: 1.55 -> 1.98Improved
add LSTM units over the temporal graph (ablation)TD-Graph LSTM · Charades (action-driven weak supervision)classification mAP: 15.89 -> 19.52Improved
add LSTM units over the temporal graph (ablation)TD-Graph LSTM · Charades (action-driven weak supervision)detection mAP: 1.16 -> 1.98Improved
use dynamic graph instead of static graph with adaptive edge weights (ablation)TD-Graph LSTM · Charades (action-driven weak supervision)classification mAP: 17.97 -> 19.52Improved
use dynamic graph instead of static graph with adaptive edge weights (ablation)TD-Graph LSTM · Charades (action-driven weak supervision)detection mAP: 1.89 -> 1.98Improved
use dynamic graph instead of mean graph (uniform edge weights) (ablation)TD-Graph LSTM · Charades (action-driven weak supervision)classification mAP: 16.92 -> 19.52Improved
use dynamic graph instead of mean graph (uniform edge weights) (ablation)TD-Graph LSTM · Charades (action-driven weak supervision)detection mAP: 1.41 -> 1.98Improved
use a fully-connected mean graph instead of no graph (ablation)TD-Graph LSTM · Charades (action-driven weak supervision)detection mAP: 1.55 -> 1.41Hurt
use TD-Graph LSTM instead of ContextLocNetweakly-supervised detector · Charades (action-driven weak supervision)classification mAP: 16.47 -> 19.52Improved
use TD-Graph LSTM instead of WSDDNweakly-supervised detector · Charades (action-driven weak supervision)classification mAP: 15.67 -> 19.52Improved
use TD-Graph LSTM instead of ContextLocNet on small objectsweakly-supervised detector · Charades (action-driven weak supervision), pillow classclassification AP: 3.51 -> 17.64Improved

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