AI Paper Atlas

Research map / Video / Action recognition

DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion

Sauradip Nag, Xiatian Zhu, Jiankang Deng, Yi-Zhe Song, Tao Xiang

ICCV 2023 · Video › Action recognition · approach: Fully supervised temporal action detection · 47 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
use cross-timestep selective conditioning instead of feature concatenation (ablation)DiffTAD · THUMOS14average mAP: 65.9 -> 68.0Improved
use selective conditioning instead of DiffusionDet proposal renewal (ablation)DiffTAD · THUMOS14average mAP: 65.1 -> 68.0Improved
combine DDIM denoising with selective conditioning (ablation)DiffTAD · THUMOS14average mAP (step 10): 64.9 -> 68.0Improved
increase sampling steps with no denoising and no selective conditioning (ablation)DiffTAD · THUMOS14average mAP: 62.7 -> 61.3 (step 1 to step 10)Hurt
use late fusion with decoupled RGB and flow denoising instead of early fusion (ablation)DiffTAD · THUMOS14average mAP: 66.0 -> 68.0Improved
set signal scaling to 0.5 rather than the object detection value of 2.0 (ablation)DiffTAD · THUMOS14average mAP: 64.2 -> 68.0Improved
increase number of proposals from 50 to 100 (ablation)DiffTAD · THUMOS14average mAP: 68.5 -> 68.4No clear effect
increase sampling steps from 1 to 5 with 50 proposals (ablation)DiffTAD · THUMOS14average mAP: 64.9 -> 68.5Improved
corrupt labels instead of proposals in the forward process (ablation)DiffTAD · THUMOS14average mAP: 68.0 -> 62.4Hurt
also corrupt labels in addition to proposals (ablation)DiffTAD · THUMOS14average mAP: 68.0 -> 67.3Hurt
add NMS post-processing (ablation)DiffTAD · THUMOS14AR@50: 63.6 -> 64.3No clear effect
add NMS post-processing (ablation)BMN · THUMOS14AR@50: 29.04 -> 32.73Improved

Later papers that compared with this method

1 later accepted paper reports DiffTAD 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