AI Paper Atlas

Research map / Video / Action recognition

Context-Aware RCNN: A Baseline for Action Detection in Videos

Jianchao Wu, Zhanghui Kuang, Limin Wang, Wayne Zhang, Gangshan Wu

ECCV 2020 · Video › Action recognition · approach: Fully supervised temporal action detection · 82 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
replace RoI Pooling with crop-and-resize actor features (32x2) (ablation)actor-feature action detector · AVA val, actor features onlymAP: 22.1 -> 25.0Improved
replace RoI Pooling with crop-and-resize for extra small boxes (ablation)actor-feature action detector · AVA val, extra small boxesmAP: 12.9 -> 16.9Improved
replace RoI Pooling with crop-and-resize for extra large boxes (ablation)actor-feature action detector · AVA val, extra large boxesmAP: 22.2 -> 22.0No clear effect
replace RoI Pooling with crop-and-resize when one actor in frame (ablation)actor-feature action detector · AVA val, 1 actor per framemAP: 29.2 -> 35.2Improved
replace RoI Pooling with crop-and-resize when 9 to 37 actors in frame (ablation)actor-feature action detector · AVA val, 9-37 actors per framemAP: 17.2 -> 22.9Improved
increase actor input resolution from 112x112 to 224x224 (ablation)Context-Aware RCNN · AVA val, actor features onlymAP: 21.4 -> 25.0Improved
increase frames from 8x8 to 32x2 sampling with crop-and-resize (ablation)Crop+Resize · AVA val, actor features onlymAP: 23.1 -> 25.0Improved
expand actor box by max scale 1.5 versus 1.2 (ablation)Crop+Resize · AVA val, actor features onlymAP: 24.1 -> 25.0Improved
expand actor box to max scale 2.5 versus 1.5 (ablation)Crop+Resize · AVA val, actor features onlymAP: 25.0 -> 24.3Hurt
expand actor box with scale 1.5 in RoI Pooling pipeline (ablation)RoI Pooling · AVA val, actor features onlymAP: 22.1 -> 21.6Hurt
add scene feature by concatenation (ablation)Context-Aware RCNN · AVA val, 16x4mAP: 24.7 -> 25.7Improved
use transformer attention to scene features instead of concat (ablation)Context-Aware RCNN · AVA val, 16x4mAP: 25.7 -> 25.8No clear effect

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