# Semantic-Guided Unsupervised Video Summarization

arXiv: https://arxiv.org/abs/2601.14773 · HTML: https://mlsanity.com/paper/2601.14773/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 30 references that are in the map.
- First posted on arXiv 21 Jan 2026.

## Builds on (most cited first, 5 of 5)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [Video Summarization through Reinforcement Learning with a 3D Spatio-Temporal U-Net](https://mlsanity.com/paper/2106.10528/) (2021)
- [Unsupervised Object-Level Video Summarization with Online Motion Auto-Encoder](https://mlsanity.com/paper/1801.00543/) (2018)
- [Unsupervised Modality-Transferable Video Highlight Detection with Representation Activation Sequence Learning](https://mlsanity.com/paper/2403.09401/) (2024)

## Abstract (arXiv)

Video summarization is a crucial technique for social understanding, enabling efficient browsing of massive multimedia content and extraction of key information from social platforms. Most existing unsupervised summarization methods rely on Generative Adversarial Networks (GANs) to enhance keyframe selection and generate coherent, video summaries through adversarial training. However, such approaches primarily exploit unimodal features, overlooking the guiding role of semantic information in keyframe selection, and often suffer from unstable training. To address these limitations, we propose a novel Semantic-Guided Unsupervised Video Summarization method. Specifically, we design a novel frame-level semantic alignment attention mechanism and integrate it into a keyframe selector, which guides the Transformer-based generator within the adversarial framework to better reconstruct videos. In addition, we adopt an incremental training strategy to progressively update the model components, effectively mitigating the instability of GAN training. Experimental results demonstrate that our approach achieves superior performance on multiple benchmark datasets.