Generic Event Boundary Detection Challenge at CVPR 2021 Technical Report: Cascaded Temporal Attention Network (CASTANET)

TL;DR

This paper introduces CASTANET, a cascaded temporal attention network designed for generic event boundary detection, achieving significant performance improvements in the CVPR 2021 challenge.

Contribution

The paper proposes a novel cascaded architecture with temporal attention and ensemble strategies for improved event boundary detection.

Findings

Achieved 83.30% F1 score on Kinetics-GEBD test set.

Improved 20.5% F1 score over baseline methods.

Demonstrated effectiveness of cascaded attention and ensemble techniques.

Abstract

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.