AI Paper Atlas

Research map / Video / Action recognition

D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations

Sanath Narayan, Hisham Cholakkal, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, Ling Shao

ICCV 2021 · Video › Action recognition · approach: Weakly supervised temporal action localization · 70 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 focal loss instead of cross-entropy (ablation)D2-Net baseline · THUMOS14 testmAP@IoU0.5: 23.0 -> 26.7Improved
add discriminative loss L_Dis instead of focal loss (ablation)D2-Net · THUMOS14 testmAP@IoU0.5: 26.7 -> 32.2Improved
add denoising loss L_D to L_Dis (ablation)D2-Net · THUMOS14 testmAP@IoU0.5: 32.2 -> 36.0Improved
add denoising loss L_D to L_Dis (ablation)D2-Net · THUMOS14 testF1@IoU0.5: 30.7 -> 36.7Improved
add grouping and clustering weights to the focal penalty (ablation)L_Dis · THUMOS14 testmAP@IoU0.5: 29.2 -> 32.2Improved
use MI-based pDMI loss instead of L1 for denoising (ablation)D2-Net · THUMOS14 testmAP@IoU0.5: 32.9 -> 36.0Improved
use MI-based pDMI loss instead of BCE for denoising (ablation)D2-Net · THUMOS14 testmAP@IoU0.5: 33.5 -> 36.0Improved
add snippet-level denoising to L_Dis (ablation)D2-Net · THUMOS14 testmAP@IoU0.5: 32.2 -> 34.3Improved
add video-level denoising to L_Dis (ablation)D2-Net · THUMOS14 testmAP@IoU0.5: 32.2 -> 33.2Improved
add both snippet-level and video-level denoising (ablation)D2-Net · THUMOS14 testmAP@IoU0.5: 34.3 -> 36.0Improved
add intra-class grouping weight gamma=0.01 instead of 0 (ablation)D2-Net · THUMOS14 testmAP@IoU0.5: 34.2 -> 36.0Improved
raise intra-class grouping weight gamma from 0.01 to 1.0 (ablation)D2-Net · THUMOS14 testmAP@IoU0.5: 36.0 -> 33.7Hurt

Later papers that compared with this method

2 later accepted papers report D2-Net as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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