AI Paper Atlas

Research map / Video / Action recognition

Progressive Boundary Refinement Network for Temporal Action Detection

Qinying Liu, Zilei Wang

AAAI 2020 · Video › Action recognition · approach: Fully supervised temporal action detection · 144 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 refined pyramidal detection on top of coarse pyramidal detection (ablation)PBRNet · THUMOS'14 RGBmAP@0.5: 36.8 -> 39.7Improved
add fine-grained detection module (ablation)PBRNet · THUMOS'14 RGBmAP@0.5: 39.7 -> 42.2Improved
add frame-level classification branches (ablation)PBRNet · THUMOS'14 FlowmAP@0.5: 40.3 -> 42.4Improved
use increasing IoU thresholds across modules (progressive matching) (ablation)PBRNet · THUMOS'14 RGBmAP@0.5: 41.3 -> 42.2Improved
add preliminary anchor discarding before hard example mining (ablation)PBRNet · THUMOS'14 FlowmAP@0.5: 41.7 -> 42.4Improved
one-stage cascaded refinement detector vs two-stage TAL-Nettemporal action detection · THUMOS'14mAP@0.5: 42.8 -> 51.3Improved

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