# ViDAS: Vision-based Danger Assessment and Scoring

arXiv: https://arxiv.org/abs/2410.00477 · HTML: https://mlsanity.com/paper/2410.00477/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 43 references that are in the map.
- First posted on arXiv 1 Oct 2024.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [The VIA Annotation Software for Images, Audio and Video](https://mlsanity.com/paper/1904.10699/) (2019)
- [CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos](https://mlsanity.com/paper/1703.01515/) (2017)
- [Street Scene: A new dataset and evaluation protocol for video anomaly detection](https://mlsanity.com/paper/1902.05872/) (2019)
- [Background Suppression Network for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/1911.09963/) (2019)
- [Zero-Shot Temporal Action Detection via Vision-Language Prompting](https://mlsanity.com/paper/2207.08184/) (2022)
- [Meta-in-context learning in large language models](https://mlsanity.com/paper/2305.12907/) (2023)
- [Non-Vacuous Generalization Bounds for Large Language Models](https://mlsanity.com/paper/2312.17173/) (2023)
- [A Practical Survey on Zero-shot Prompt Design for In-context Learning](https://mlsanity.com/paper/2309.13205/) (2023)
- [Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases](https://mlsanity.com/paper/2112.07868/) (2021)
- [Temporal Action Proposal Generation with Background Constraint](https://mlsanity.com/paper/2112.07984/) (2021)
- [Learning Sparse 2D Temporal Adjacent Networks for Temporal Action Localization](https://mlsanity.com/paper/1912.03612/) (2019)
- [Student Dangerous Behavior Detection in School](https://mlsanity.com/paper/2202.09550/) (2022)

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

- [VARS: Vision-based Assessment of Risk in Security Systems](https://mlsanity.com/paper/2410.19642/) (2024)

## Abstract (arXiv)

We present a novel dataset aimed at advancing danger analysis and assessment by addressing the challenge of quantifying danger in video content and identifying how human-like a Large Language Model (LLM) evaluator is for the same. This is achieved by compiling a collection of 100 YouTube videos featuring various events. Each video is annotated by human participants who provided danger ratings on a scale from 0 (no danger to humans) to 10 (life-threatening), with precise timestamps indicating moments of heightened danger. Additionally, we leverage LLMs to independently assess the danger levels in these videos using video summaries. We introduce Mean Squared Error (MSE) scores for multimodal meta-evaluation of the alignment between human and LLM danger assessments. Our dataset not only contributes a new resource for danger assessment in video content but also demonstrates the potential of LLMs in achieving human-like evaluations.