# Audiovisual Highlight Detection in Videos

arXiv: https://arxiv.org/abs/2102.05811 · HTML: https://mlsanity.com/paper/2102.05811/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 11 Feb 2021.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Audio-Visual Scene Analysis with Self-Supervised Multisensory Features](https://mlsanity.com/paper/1804.03641/) (2018)
- [Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace](https://mlsanity.com/paper/1910.04855/) (2019)
- [Video Summarization with Long Short-term Memory](https://mlsanity.com/paper/1605.08110/) (2016)
- [Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward](https://mlsanity.com/paper/1801.00054/) (2017)
- [Summarizing Videos with Attention](https://mlsanity.com/paper/1812.01969/) (2018)
- [Unsupervised Extraction of Video Highlights Via Robust Recurrent Auto-encoders](https://mlsanity.com/paper/1510.01442/) (2015)
- [PHD-GIFs: Personalized Highlight Detection for Automatic GIF Creation](https://mlsanity.com/paper/1804.06604/) (2018)
- [Comprehensive Video Understanding: Video summarization with content-based video recommender design](https://mlsanity.com/paper/1910.13888/) (2019)
- [Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings](https://mlsanity.com/paper/1910.10869/) (2019)

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

- [TSMD: Temporal-Stream Modality Dropout for Robust Video Highlight Detection](https://mlsanity.com/paper/2609.39051/) (2026)

## Abstract (arXiv)

In this paper, we test the hypothesis that interesting events in unstructured videos are inherently audiovisual. We combine deep image representations for object recognition and scene understanding with representations from an audiovisual affect recognition model. To this set, we include content agnostic audio-visual synchrony representations and mel-frequency cepstral coefficients to capture other intrinsic properties of audio. These features are used in a modular supervised model. We present results from two experiments: efficacy study of single features on the task, and an ablation study where we leave one feature out at a time. For the video summarization task, our results indicate that the visual features carry most information, and including audiovisual features improves over visual-only information. To better study the task of highlight detection, we run a pilot experiment with highlights annotations for a small subset of video clips and fine-tune our best model on it. Results indicate that we can transfer knowledge from the video summarization task to a model trained specifically for the task of highlight detection.