atlas

Research map / Video / Action recognition

Weakly Supervised Action Localization by Sparse Temporal Pooling Network

CVPR 2018 · Video › Action recognition · approach: Weakly supervised temporal action localization · 429 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 sparse attention-weighted temporal pooling and an ℓ1 sparsity loss (ablation)STPN action classification and localization · THUMOS14APHelped
Add attention-weighted pooling (ablation)STPN · THUMOS14APHelped
Add an ℓ1 sparsity loss on attention weights (ablation)STPN · THUMOS14APHelped
Use optical flow rather than RGB features (ablation)STPN modality input · THUMOS14APHelped
Combine RGB and optical-flow features (ablation)STPN modality input · THUMOS14APHelped
Replace I3D features with UntrimmedNet featuresSTPN · THUMOS14AP@IoU 0.1: 52.0 -> 45.3Hurt

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