AI Paper Atlas

Research map / Video / Action recognition

Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization

Humam Alwassel, Fabian Caba Heilbron, Bernard Ghanem

ECCV 2018 · 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
add learned Action Search as precursor to Res3D + S-CNNRes3D + S-CNN · THUMOS14 test, tIoU 0.5mAP: 22.5 -> 30.8Improved
add learned Action Search as precursor to Res3D + S-CNNRes3D + S-CNN · THUMOS14 testobserved frames S: 100 -> 17.3Improved
train search by imitating human searches instead of reinforcement policyFrame Glimpses · THUMOS14 test, tIoU 0.5mAP: 17.1 -> 30.8Improved
use ResNet backbone instead of C3D (ablation)Action Search · THUMOS14 test, tIoU 0.5mAP: 23.9 -> 30.8Improved
use ResNet backbone instead of C3D (ablation)Action Search · THUMOS14 testobserved frames S: 45.1 -> 17.3Improved
add Action Search with C3D to the C3D-based detector (ablation)Res3D + S-CNN baseline · THUMOS14 test, tIoU 0.5mAP: +4.9% mAP, 54.9% less frames observedImproved
train on 25% of human searches (ablation)Action Search · THUMOS14 test, tIoU 0.5mAP: 22.5 -> 22.4No clear effect
train on 25% of human searches (ablation)Action Search · THUMOS14 testobserved frames S: 100 -> 63.5Improved
train on 50% instead of 25% of human searches (ablation)Action Search · THUMOS14 test, tIoU 0.5mAP: 22.4 -> 26.1Improved
train on 100% instead of 50% of human searches (ablation)Action Search · THUMOS14 test, tIoU 0.5mAP: 26.1 -> 30.8Improved
train on 100% instead of 50% of human searches (ablation)Action Search · THUMOS14 testobserved frames S: 34.4 -> 17.3Improved
add Action Search with temporal context vs direction-only baselineDirection Baseline · AVA test (coverage <=5%)observations to spot action: 16.6% fewer observationsImproved

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