AI Paper Atlas

Research map / Video / Action recognition

3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization

Sanath Narayan, Hisham Cholakkal, Fahad Shahbaz Khan, Ling Shao

ICCV 2019 · Video › Action recognition · approach: Weakly supervised temporal action localization · 181 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 multi-label center loss (ablation)CLS baseline · THUMOS14 localizationmAP@IoU0.5: 19.1 -> 24.6Improved
add counting loss (ablation)CLS + CL · THUMOS14 localizationmAP@IoU0.5: 24.6 -> 26.6Improved
add center loss (ablation)CLS baseline · ActivityNet 1.2 localizationmean mAP: 18.2 -> 21.1Improved
add counting loss (ablation)CLS + CL · ActivityNet 1.2 localizationmean mAP: 21.1 -> 21.7Improved
add classification loss in both streams (ablation)3C-Net · THUMOS14 localizationmAP@IoU0.5: 2.5% mAP drop when removedImproved
add center loss in both RGB and flow streams (vs flow only) (ablation)3C-Net · THUMOS14 localizationmAP@IoU0.5: 2.1% mAP drop when flow onlyImproved
add center loss in both streams (vs RGB only) (ablation)3C-Net · THUMOS14 localizationmAP@IoU0.5: 1.9% mAP drop when RGB onlyImproved
add negative category counting loss (ablation)3C-Net · THUMOS14 localizationmAP@IoU0.5: 1.5% mAP drop when removedImproved
use relative error rather than absolute error in counting loss (ablation)3C-Net · THUMOS14 localizationmAP@IoU0.5: 1.2% mAP drop with absolute errorImproved
3C-Net vs W-TALCW-TALC · THUMOS14 localizationmAP@IoU0.5: 22.0 -> 26.6Improved
3C-Net vs W-TALCW-TALC · ActivityNet 1.2 localizationmean mAP: 18.0 -> 21.7Improved
3C-Net vs W-TALCW-TALC · ActivityNet 1.2 classificationmAP: 93.2 vs 92.4No clear effect

Later papers that compared with this method

1 later accepted paper reports 3C-Net as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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