# Improving Sequential Determinantal Point Processes for Supervised Video Summarization

arXiv: https://arxiv.org/abs/1807.10957 · HTML: https://mlsanity.com/paper/1807.10957/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jul 2018.

## Built on by (most cited first, 9 of 9)

- [Transcript to Video: Efficient Clip Sequencing from Texts](https://mlsanity.com/paper/2107.11851/) (2021)
- [DeepQAMVS: Query-Aware Hierarchical Pointer Networks for Multi-Video Summarization](https://mlsanity.com/paper/2105.06441/) (2021)
- [How Good is a Video Summary? A New Benchmarking Dataset and Evaluation Framework Towards Realistic Video Summarization](https://mlsanity.com/paper/2101.10514/) (2021)
- [Conditional Modeling Based Automatic Video Summarization](https://mlsanity.com/paper/2311.12159/) (2023)
- [Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes](https://mlsanity.com/paper/2207.00486/) (2022)
- [Causal Video Summarizer for Video Exploration](https://mlsanity.com/paper/2307.01947/) (2023)
- [Vector Retrieval with Similarity and Diversity: How Hard Is It?](https://mlsanity.com/paper/2407.04573/) (2024)
- [Scalable Sampling for Nonsymmetric Determinantal Point Processes](https://mlsanity.com/paper/2201.08417/) (2022)
- [Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing](https://mlsanity.com/paper/2603.22466/) (2026)

## Abstract (arXiv)

It is now much easier than ever before to produce videos. While the ubiquitous video data is a great source for information discovery and extraction, the computational challenges are unparalleled. Automatically summarizing the videos has become a substantial need for browsing, searching, and indexing visual content. This paper is in the vein of supervised video summarization using sequential determinantal point process (SeqDPP), which models diversity by a probabilistic distribution. We improve this model in two folds. In terms of learning, we propose a large-margin algorithm to address the exposure bias problem in SeqDPP. In terms of modeling, we design a new probabilistic distribution such that, when it is integrated into SeqDPP, the resulting model accepts user input about the expected length of the summary. Moreover, we also significantly extend a popular video summarization dataset by 1) more egocentric videos, 2) dense user annotations, and 3) a refined evaluation scheme. We conduct extensive experiments on this dataset (about 60 hours of videos in total) and compare our approach to several competitive baselines.