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

arXiv: https://arxiv.org/abs/2107.00239 · HTML: https://mlsanity.com/paper/2107.00239/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 8 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Video Classification with Channel-Separated Convolutional Networks](https://mlsanity.com/paper/1904.02811/) (2019)
- [Audiovisual SlowFast Networks for Video Recognition](https://mlsanity.com/paper/2001.08740/) (2020)
- [Large-scale weakly-supervised pre-training for video action recognition](https://mlsanity.com/paper/1905.00561/) (2019)
- [Generic Event Boundary Detection: A Benchmark for Event Segmentation](https://mlsanity.com/paper/2101.10511/) (2021)

## Built on by (most cited first, 13 of 13)

- [Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection](https://mlsanity.com/paper/2112.04771/) (2021)
- [End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection](https://mlsanity.com/paper/2203.15336/) (2022)
- [Structured Context Transformer for Generic Event Boundary Detection](https://mlsanity.com/paper/2206.02985/) (2022)
- [Rethinking the Architecture Design for Efficient Generic Event Boundary Detection](https://mlsanity.com/paper/2407.12622/) (2024)
- [What's in the Flow? Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detection](https://mlsanity.com/paper/2404.18935/) (2024)
- [Fine-grained Dynamic Network for Generic Event Boundary Detection](https://mlsanity.com/paper/2407.04274/) (2024)
- [Masked Autoencoders for Generic Event Boundary Detection CVPR'2022 Kinetics-GEBD Challenge](https://mlsanity.com/paper/2206.08610/) (2022)
- [Motion Aware Self-Supervision for Generic Event Boundary Detection](https://mlsanity.com/paper/2210.05574/) (2022)
- [AutoMatch: A Large-scale Audio Beat Matching Benchmark for Boosting Deep Learning Assistant Video Editing](https://mlsanity.com/paper/2303.01884/) (2023)
- [Local Compressed Video Stream Learning for Generic Event Boundary Detection](https://mlsanity.com/paper/2309.15431/) (2023)
- [EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation](https://mlsanity.com/paper/2607.10165/) (2026)
- [MAE-GEBD:Winning the CVPR'2023 LOVEU-GEBD Challenge](https://mlsanity.com/paper/2306.15704/) (2023)
- [Structured Context Learning for Generic Event Boundary Detection](https://mlsanity.com/paper/2512.00475/) (2025)

## Abstract (arXiv)

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.