AI Paper Atlas

Research map / Video / Action recognition

AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos

Zheng Shou, Hang Gao, Lei Zhang, Kazuyuki Miyazawa, Shih-Fu Chang

ECCV 2018 · Video › Action recognition · approach: Weakly supervised temporal action localization · 291 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 the outer-inner contrast to the loss rather than inner activation only (ablation)AutoLoc · ActivityNet v1.2 valmAP@IoU 0.5: 4.6 -> 27.3Improved
add the outer-inner contrast to the loss rather than inner activation only (ablation)AutoLoc · ActivityNet v1.2 valaverage mAP: 1.6 -> 16.0Improved
train the boundary predictor on training videos instead of direct optimization on each test video (ablation)AutoLoc · ActivityNet v1.2 valmAP@IoU 0.5: 21.8 -> 27.3Improved
train the boundary predictor on training videos instead of direct optimization on each test video (ablation)AutoLoc · ActivityNet v1.2 valaverage mAP: 12.6 -> 16.0Improved
use a learned boundary predictor instead of OIC Selection over all enumerated segments (ablation)AutoLoc · ActivityNet v1.2 valmAP@IoU 0.5: 15.8 -> 27.3Improved
use OIC-loss-based segment selection instead of CAS thresholding (ablation)UntrimmedNet CAS · ActivityNet v1.2 valmAP@IoU 0.5: 7.4 -> 15.8Improved
replace CAS thresholding with direct boundary prediction trained with OIC lossUntrimmedNet · THUMOS'14 testmAP@IoU 0.5: 13.7 -> 21.2Improved
replace CAS thresholding with direct boundary prediction trained with OIC lossUntrimmedNet · ActivityNet v1.2 valmAP@IoU 0.5: 7.4 -> 27.3Improved
weak-supervised AutoLoc versus full-supervised S-CNNAutoLoc · THUMOS'14 testmAP@IoU 0.5: 19.0 -> 21.2Improved

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