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

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

22 Aug 2019ICCV 2019 10arXiv:1908.08216archive 2025-07-28

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

Temporal action localization is a challenging computer vision problem with numerous real-world applications. Most existing methods require laborious frame-level supervision to train action localization models. In this work, we propose a framework, called 3C-Net, which only requires video-level supervision (weak supervision) in the form of action category labels and the corresponding count. We introduce a novel formulation to learn discriminative action features with enhanced localization capabilities. Our joint formulation has three terms: a classification term to ensure the separability of learned action features, an adapted multi-label center loss term to enhance the action feature discriminability and a counting loss term to delineate adjacent action sequences, leading to improved localization. Comprehensive experiments are performed on two challenging benchmarks: THUMOS14 and ActivityNet 1.2. Our approach sets a new state-of-the-art for weakly-supervised temporal action localization on both datasets. On the THUMOS14 dataset, the proposed method achieves an absolute gain of 4.6% in terms of mean average precision (mAP), compared to the state-of-the-art. Source code is available at https://github.com/naraysa/3c-net.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

naraysa/3c-net officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action ClassificationAction LocalizationTemporal Action LocalizationWeakly Supervised Action LocalizationWeakly-supervised Temporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Classification ActivityNet-1.2 3C-Net mAP 92.4 #2 of 3 Archive leaderboard report
Action Classification THUMOS'14 3C-Net mAP 86.9 #1 of 1 Archive leaderboard report
Action Classification THUMOS’14 3C-Net mAP 86.9 #1 of 3 Archive leaderboard report
Weakly Supervised Action Localization ActivityNet-1.2 3C-Net Mean mAP 21.7 #13 of 19 Archive leaderboard report
Weakly Supervised Action Localization ActivityNet-1.2 3C-Net mAP@0.5 37.2 #13 of 19 Archive leaderboard report
Weakly Supervised Action Localization THUMOS 2014 3C-Net mAP@0.5 26.6 #24 of 30 Archive leaderboard report
Weakly Supervised Action Localization THUMOS’14 3C-Net mAP@0.5 26.6 #13 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections