# Your Interest, Your Summaries: Query-Focused Long Video Summarization

arXiv: https://arxiv.org/abs/2410.14087 · HTML: https://mlsanity.com/paper/2410.14087/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Video Summarization Using Fully Convolutional Sequence Networks](https://mlsanity.com/paper/1805.10538/) (2018)
- [Query-Focused Video Summarization: Dataset, Evaluation, and A Memory Network Based Approach](https://mlsanity.com/paper/1707.04960/) (2017)
- [Query-Focused Extractive Video Summarization](https://mlsanity.com/paper/1607.05177/) (2016)
- [Predicting Important Objects for Egocentric Video Summarization](https://mlsanity.com/paper/1505.04803/) (2015)
- [Query-Conditioned Three-Player Adversarial Network for Video Summarization](https://mlsanity.com/paper/1807.06677/) (2018)

## Built on by (most cited first, 1 of 1)

- [Spiking Variational Graph Representation Inference for Video Summarization](https://mlsanity.com/paper/2508.15389/) (2025)

## Abstract (arXiv)

Generating a concise and informative video summary from a long video is important, yet subjective due to varying scene importance. Users' ability to specify scene importance through text queries enhances the relevance of such summaries. This paper introduces an approach for query-focused video summarization, aiming to align video summaries closely with user queries. To this end, we propose the Fully Convolutional Sequence Network with Attention (FCSNA-QFVS), a novel approach designed for this task. Leveraging temporal convolutional and attention mechanisms, our model effectively extracts and highlights relevant content based on user-specified queries. Experimental validation on a benchmark dataset for query-focused video summarization demonstrates the effectiveness of our approach.