# When and How to Cut Classical Concerts? A Multimodal Automated Video Editing Approach

arXiv: https://arxiv.org/abs/2510.05661 · HTML: https://mlsanity.com/paper/2510.05661/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [SpecAugment on Large Scale Datasets](https://mlsanity.com/paper/1912.05533/) (2019)
- [Deep Learning-based Image and Video Inpainting: A Survey](https://mlsanity.com/paper/2401.03395/) (2024)
- [Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows](https://mlsanity.com/paper/2210.08737/) (2022)
- [Pseudo Dataset Generation for Out-of-Domain Multi-Camera View Recommendation](https://mlsanity.com/paper/2410.13585/) (2024)
- [Videogenic: Identifying Highlight Moments in Videos with Professional Photographs as a Prior](https://mlsanity.com/paper/2211.12493/) (2022)
- [Minutes to Seconds: Speeded-up DDPM-based Image Inpainting with Coarse-to-Fine Sampling](https://mlsanity.com/paper/2407.05875/) (2024)
- [Better Spanish Emotion Recognition In-the-wild: Bringing Attention to Deep Spectrum Voice Analysis](https://mlsanity.com/paper/2409.05148/) (2024)
- [Aesthetic Matters in Music Perception for Image Stylization: A Emotion-driven Music-to-Visual Manipulation](https://mlsanity.com/paper/2501.01700/) (2025)

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

- [A Dual-Transformer for Multi-Camera View Recommendation](https://mlsanity.com/paper/2608.25601/) (2026)

## Abstract (arXiv)

Automated video editing remains an underexplored task in the computer vision and multimedia domains, especially when contrasted with the growing interest in video generation and scene understanding. In this work, we address the specific challenge of editing multicamera recordings of classical music concerts by decomposing the problem into two key sub-tasks: when to cut and how to cut. Building on recent literature, we propose a novel multimodal architecture for the temporal segmentation task (when to cut), which integrates log-mel spectrograms from the audio signals, plus an optional image embedding, and scalar temporal features through a lightweight convolutional-transformer pipeline. For the spatial selection task (how to cut), we improve the literature by updating from old backbones, e.g. ResNet, with a CLIP-based encoder and constraining distractor selection to segments from the same concert. Our dataset was constructed following a pseudo-labeling approach, in which raw video data was automatically clustered into coherent shot segments. We show that our models outperformed previous baselines in detecting cut points and provide competitive visual shot selection, advancing the state of the art in multimodal automated video editing.