AI Paper Atlas

Research map / Video / Action recognition

DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization

Xiaojun Tang, Junsong Fan, Chuanchen Luo, Zhaoxiang Zhang, Man Zhang, Zongyuan Yang

ICCV 2023 · Video › Action recognition · approach: Weakly supervised temporal action localization · 24 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 DDG-Net (graph with discrimination-driven connections and feature consistency loss) to base WTAL model (ablation)base WTAL model · THUMOS14mAP Avg (%): 45.8 -> 47.3Improved
add graph average only to the baseline (ablation)base WTAL model · THUMOS14mAP Avg (%): 45.8 -> 46.4Improved
add graph convolution without feature consistency loss (ablation)base WTAL model with graph average · THUMOS14mAP Avg (%): 46.4 -> 36.1Hurt
add feature consistency loss to graph convolution (ablation)DDG-Net · THUMOS14mAP Avg (%): 36.1 -> 47.3Improved
use fused adjacency matrix across RGB and flow instead of separate adjacency matrices (ablation)DDG-Net · THUMOS14mAP Avg (%): 44.9 -> 47.3Improved
disconnect ambiguous snippets so they only receive information (ablation)DDG-Net · THUMOS14mAP Avg (%): 45.8 -> 47.3Improved
raise similarity threshold from 0.8 to 0.9 (ablation)DDG-Net · THUMOS14mAPHurt
choose action threshold 0.5 versus higher values (ablation)DDG-Net · THUMOS14mAPImproved
add DDG-Net on ActivityNet1.2base WTAL model · ActivityNet1.2mAPImproved
add DDG-Net to base modelbase WTAL model · THUMOS14parameters and FLOPs: 21.5 M -> 29.9 M params; 6.89 G -> 13.39 G FLOPsHurt

Later papers that compared with this method

2 later accepted papers report DDG-Net as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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