CVPR 2021上的通用事件边界检测挑战技术报告：级联时间注意力网络（CASTANET）
Generic Event Boundary Detection Challenge at CVPR 2021 Technical Report: Cascaded Temporal Attention Network (CASTANET)
摘要：
本报告介绍了在CVPR 21上提交通用事件边界检测（GEBD）挑战时使用的方法。在这项工作中，我们设计了一个级联的时间注意力网络（CASTANET）的GEBD，它由三个部分组成，骨干网络，时间注意力模块，和分类模块。具体而言，采用离散卷积网络（CSN）作为主干网络进行特征提取，并设计了时间注意模块，使网络集中于具有区分性的特征。在此基础上，在分类模块中使用级联结构，以生成更准确的边界。此外，集成策略被用来进一步提高所提出的方法的性能。该方法在Kinetics-GEBD测试集上获得了83.30%的F1分数，与基线方法相比提高了20.5%的F1分数。代码可在https://github.com/DexiangHong/Cascade-PC上获得。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
