mlsanityData to 7 Oct 2026

ViDAS: Vision-based Danger Assessment and Scoring

arXiv 2410.00477 ↗First posted 1 Oct 2024cs.CVcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 43 references that are in the map. First posted on arXiv 1 Oct 2024.

Builds on

17 of 43 references.

References · 17

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  3. 2017Localizing Moments in Video with Natural Languagecited by 660
  4. 2017TALL: Temporal Activity Localization via Language Querycited by 581
  5. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  6. 2019The VIA Annotation Software for Images, Audio and Videocited by 166
  7. 2017CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videoscited by 112
  8. 2019Street Scene: A new dataset and evaluation protocol for video anomaly detectioncited by 89
  9. 2019Background Suppression Network for Weakly-supervised Temporal Action Localizationcited by 73
  10. 2022Zero-Shot Temporal Action Detection via Vision-Language Promptingcited by 65
  11. 2023Meta-in-context learning in large language modelscited by 59
  12. 2023Non-Vacuous Generalization Bounds for Large Language Modelscited by 53
5 more
  1. 2023A Practical Survey on Zero-shot Prompt Design for In-context Learningcited by 49
  2. 2021Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biasescited by 21
  3. 2021Temporal Action Proposal Generation with Background Constraintcited by 16
  4. 2019Learning Sparse 2D Temporal Adjacent Networks for Temporal Action Localizationcited by 4
  5. 2022Student Dangerous Behavior Detection in Schoolcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024VARS: Vision-based Assessment of Risk in Security Systemscited by 0