AI Paper Atlas

Research map / Video / Action recognition

Joint Prediction of Activity Labels and Starting Times in Untrimmed Videos

Tahmida Mahmud, Mahmudul Hasan, Amit K. Roy-Chowdhury

ICCV 2017 · Video › Action recognition · approach: Disentangled action recognition · 78 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 scene context (object features) (ablation)Proposed network · MPII-Cookingtop-1 accuracy (%): 33.1 -> 80.1Improved
add scene context (object features) (ablation)Proposed network · VIRAT Groundtop-1 accuracy (%): 61.0 -> 71.8Improved
add inter-activity time context branch (ablation)Proposed network · MPII-Cookingtop-1 accuracy (%): 75.1 -> 80.1Improved
add inter-activity time context branch (ablation)Proposed network · VIRAT Groundtop-1 accuracy (%): 69.2 -> 71.8Improved
add sequential activity and scene context to time prediction (ablation)Proposed network · MPII-CookingRMSE (sec): 1.4872 -> 1.2454Improved
use LSTM sequence length 3 instead of 2 (ablation)Proposed network · MPII-Cookingtop-1 accuracy (%): 78.8 -> 80.1Improved
use sequence length 3 instead of 9 (ablation)Proposed network · MPII-Cookingtop-1 accuracy (%): 77.2 -> 80.1Improved
use sequence length 3 instead of 5 (ablation)Proposed network · MPII-Cookingtop-1 accuracy (%): 79.2 -> 80.1Improved
use C3D features instead of MBH (ablation)Proposed network · MPII-Cookingtop-1 accuracy (%): 80.1 -> 79.9No clear effect
use proposed prediction network instead of CNN + LSTM recognitionCNN + LSTM · MPII-Cookingtop-1/precision: 34.8 -> 70.7Improved
use proposed network instead of graphical modelGraphical Model · VIRAT Groundtop-1 accuracy (%): 68.5 -> 71.8Improved
use proposed network instead of statistical LGCP model for timeStatistical Model · MPII-CookingRMSE (sec): 3.9431 -> 1.2454Improved

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