Papers › Generic Event Boundary Detection Challenge at CVPR 2021 Technical Report: Cascaded...
Generic Event Boundary Detection Challenge at CVPR 2021 Technical Report: Cascaded Temporal Attention Network (CASTANET)
Dexiang Hong, CongCong Li, Longyin Wen, Xinyao Wang, Libo Zhang
This report presents the approach used in the submission of Generic Event Boundary Detection (GEBD) Challenge at CVPR21. In this work, we design a Cascaded Temporal Attention Network (CASTANET) for GEBD, which is formed by three parts, the backbone network, the temporal attention module, and the classification module. Specifically, the Channel-Separated Convolutional Network (CSN) is used as the backbone network to extract features, and the temporal attention module is designed to enforce the network to focus on the discriminative features. After that, the cascaded architecture is used in the classification module to generate more accurate boundaries. In addition, the ensemble strategy is used to further improve the performance of the proposed method. The proposed method achieves 83.30% F1 score on Kinetics-GEBD test set, which improves 20.5% F1 score compared to the baseline method. Code is available at https://github.com/DexiangHong/Cascade-PC.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Boundary Detection | Kinetics-400 | CASTANET+ Ensemble | Pairwise F1 | 0.814 | #1 of 1 | Archive leaderboard | report |
| Boundary Detection | Kinetics-400 | CASTANET+ Ensemble | Precision | 82.8 | #1 of 1 | Archive leaderboard | report |
| Boundary Detection | Kinetics-400 | CASTANET+ Ensemble | Recall | 83.8 | #1 of 1 | Archive leaderboard | report |
| Event Segmentation | Kinetics-400 | CASTANET+ Ensemble | F1 | 83.3 | #1 of 1 | 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