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)

1 Jul 2021arXiv:2107.00239archive 2025-07-28

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.

PaperPDFCode

Code

DexiangHong/Cascade-PC officialmentioned in paperpytorch 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

Boundary DetectionEvent SegmentationGeneric Event Boundary Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
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