# EdgeVidSum: Real-Time Personalized Video Summarization at the Edge

arXiv: https://arxiv.org/abs/2506.03171 · HTML: https://mlsanity.com/paper/2506.03171/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 31 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 10 of 10)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [SpeedNet: Learning the Speediness in Videos](https://mlsanity.com/paper/2004.06130/) (2020)
- [Rotate to Attend: Convolutional Triplet Attention Module](https://mlsanity.com/paper/2010.03045/) (2020)
- [Query-Focused Video Summarization: Dataset, Evaluation, and A Memory Network Based Approach](https://mlsanity.com/paper/1707.04960/) (2017)
- [To Click or Not To Click: Automatic Selection of Beautiful Thumbnails from Videos](https://mlsanity.com/paper/1609.01388/) (2016)
- [FFNet: Video Fast-Forwarding via Reinforcement Learning](https://mlsanity.com/paper/1805.02792/) (2018)
- [LTC-SUM: Lightweight Client-driven Personalized Video Summarization Framework Using 2D CNN](https://mlsanity.com/paper/2201.09049/) (2022)
- [Personalizing Fast-Forward Videos Based on Visual and Textual Features from Social Network](https://mlsanity.com/paper/1912.12655/) (2019)
- [A Sparse Sampling-based framework for Semantic Fast-Forward of First-Person Videos](https://mlsanity.com/paper/2009.11063/) (2020)

## Abstract (arXiv)

EdgeVidSum is a lightweight method that generates personalized, fast-forward summaries of long-form videos directly on edge devices. The proposed approach enables real-time video summarization while safeguarding user privacy through local data processing using innovative thumbnail-based techniques and efficient neural architectures. Unlike conventional methods that process entire videos frame by frame, the proposed method uses thumbnail containers to significantly reduce computational complexity without sacrificing semantic relevance. The framework employs a hierarchical analysis approach, where a lightweight 2D CNN model identifies user-preferred content from thumbnails and generates timestamps to create fast-forward summaries. Our interactive demo highlights the system's ability to create tailored video summaries for long-form videos, such as movies, sports events, and TV shows, based on individual user preferences. The entire computation occurs seamlessly on resource-constrained devices like Jetson Nano, demonstrating how EdgeVidSum addresses the critical challenges of computational efficiency, personalization, and privacy in modern video consumption environments.