# Large-scale, Fast and Accurate Shot Boundary Detection through Spatio-temporal Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1705.03281 · HTML: https://mlsanity.com/paper/1705.03281/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2017.

## Built on by (most cited first, 12 of 12)

- [AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection](https://mlsanity.com/paper/2304.06116/) (2023)
- [MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos](https://mlsanity.com/paper/2306.04216/) (2023)
- [Zero-shot Video Moment Retrieval With Off-the-Shelf Models](https://mlsanity.com/paper/2211.02178/) (2022)
- [MHMS: Multimodal Hierarchical Multimedia Summarization](https://mlsanity.com/paper/2204.03734/) (2022)
- [LiveSeg: Unsupervised Multimodal Temporal Segmentation of Long Livestream Videos](https://mlsanity.com/paper/2210.05840/) (2022)
- [OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer](https://mlsanity.com/paper/2604.24762/) (2026)
- [Segment Anything Across Shots: A Method and Benchmark](https://mlsanity.com/paper/2511.13715/) (2025)
- [V-Trans4Style: Visual Transition Recommendation for Video Production Style Adaptation](https://mlsanity.com/paper/2501.07983/) (2025)
- [Shot-Aware Frame Sampling for Video Understanding](https://mlsanity.com/paper/2603.17374/) (2026)
- [SliTraNet: Automatic Detection of Slide Transitions in Lecture Videos using Convolutional Neural Networks](https://mlsanity.com/paper/2202.03540/) (2022)
- [Faster than real-time detection of shot boundaries, sampling structure and dynamic keyframes in video](https://mlsanity.com/paper/2502.09202/) (2025)
- [PERSIST: Persistent-State Discrimination for Shot Boundary Detection](https://mlsanity.com/paper/2608.29287/) (2026)

## Abstract (arXiv)

Shot boundary detection (SBD) is an important pre-processing step for video manipulation. Here, each segment of frames is classified as either sharp, gradual or no transition. Current SBD techniques analyze hand-crafted features and attempt to optimize both detection accuracy and processing speed. However, the heavy computations of optical flow prevents this. To achieve this aim, we present an SBD technique based on spatio-temporal Convolutional Neural Networks (CNN). Since current datasets are not large enough to train an accurate SBD CNN, we present a new dataset containing more than 3.5 million frames of sharp and gradual transitions. The transitions are generated synthetically using image compositing models. Our dataset contain additional 70,000 frames of important hard-negative no transitions. We perform the largest evaluation to date for one SBD algorithm, on real and synthetic data, containing more than 4.85 million frames. In comparison to the state of the art, we outperform dissolve gradual detection, generate competitive performance for sharp detections and produce significant improvement in wipes. In addition, we are up to 11 times faster than the state of the art.