# Ridiculously Fast Shot Boundary Detection with Fully Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1705.08214 · HTML: https://mlsanity.com/paper/1705.08214/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2017.

## Built on by (most cited first, 11 of 11)

- [Generic Event Boundary Detection: A Benchmark for Event Segmentation](https://mlsanity.com/paper/2101.10511/) (2021)
- [MovieCuts: A New Dataset and Benchmark for Cut Type Recognition](https://mlsanity.com/paper/2109.05569/) (2021)
- [AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection](https://mlsanity.com/paper/2304.06116/) (2023)
- [Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection](https://mlsanity.com/paper/2112.04771/) (2021)
- [Learning to Cut by Watching Movies](https://mlsanity.com/paper/2108.04294/) (2021)
- [Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency](https://mlsanity.com/paper/2204.03017/) (2022)
- [Rethinking the Architecture Design for Efficient Generic Event Boundary Detection](https://mlsanity.com/paper/2407.12622/) (2024)
- [PR-Net: Preference Reasoning for Personalized Video Highlight Detection](https://mlsanity.com/paper/2109.01799/) (2021)
- [Extraction of Positional Player Data from Broadcast Soccer Videos](https://mlsanity.com/paper/2110.11107/) (2021)
- [Fine-grained Dynamic Network for Generic Event Boundary Detection](https://mlsanity.com/paper/2407.04274/) (2024)
- [PERSIST: Persistent-State Discrimination for Shot Boundary Detection](https://mlsanity.com/paper/2608.29287/) (2026)

## Abstract (arXiv)

Shot boundary detection (SBD) is an important component of many video analysis tasks, such as action recognition, video indexing, summarization and editing. Previous work typically used a combination of low-level features like color histograms, in conjunction with simple models such as SVMs. Instead, we propose to learn shot detection end-to-end, from pixels to final shot boundaries. For training such a model, we rely on our insight that all shot boundaries are generated. Thus, we create a dataset with one million frames and automatically generated transitions such as cuts, dissolves and fades. In order to efficiently analyze hours of videos, we propose a Convolutional Neural Network (CNN) which is fully convolutional in time, thus allowing to use a large temporal context without the need to repeatedly processing frames. With this architecture our method obtains state-of-the-art results while running at an unprecedented speed of more than 120x real-time.