# Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection

arXiv: https://arxiv.org/abs/2405.05130 · HTML: https://mlsanity.com/paper/2405.05130/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 8 May 2024.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Attention Bottlenecks for Multimodal Fusion](https://mlsanity.com/paper/2107.00135/) (2021)
- [Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision](https://mlsanity.com/paper/2007.04687/) (2020)
- [Multiview Transformers for Video Recognition](https://mlsanity.com/paper/2201.04288/) (2022)
- [Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval](https://mlsanity.com/paper/2112.04446/) (2021)
- [Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2212.04090/) (2022)
- [Improving Multi-Modal Learning with Uni-Modal Teachers](https://mlsanity.com/paper/2106.11059/) (2021)
- [Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection](https://mlsanity.com/paper/2303.13051/) (2023)
- [Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection](https://mlsanity.com/paper/2207.05500/) (2022)
- [Long-Short Temporal Co-Teaching for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2303.18044/) (2023)

## Built on by (most cited first, 3 of 3)

- [Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Method](https://mlsanity.com/paper/2501.07496/) (2025)
- [Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance](https://mlsanity.com/paper/2602.10549/) (2026)
- [AViS-Mamba: Adaptive Visual Steering of Audio State-Space Dynamics for Violence Detection](https://mlsanity.com/paper/2604.03329/) (2026)

## Abstract (arXiv)

Weakly supervised multimodal violence detection aims to learn a violence detection model by leveraging multiple modalities such as RGB, optical flow, and audio, while only video-level annotations are available. In the pursuit of effective multimodal violence detection (MVD), information redundancy, modality imbalance, and modality asynchrony are identified as three key challenges. In this work, we propose a new weakly supervised MVD method that explicitly addresses these challenges. Specifically, we introduce a multi-scale bottleneck transformer (MSBT) based fusion module that employs a reduced number of bottleneck tokens to gradually condense information and fuse each pair of modalities and utilizes a bottleneck token-based weighting scheme to highlight more important fused features. Furthermore, we propose a temporal consistency contrast loss to semantically align pairwise fused features. Experiments on the largest-scale XD-Violence dataset demonstrate that the proposed method achieves state-of-the-art performance. Code is available at https://github.com/shengyangsun/MSBT.