RiskCueBench: Benchmarking Anticipatory Reasoning from Early Risk Cues in Video-Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908778378559488 |
|---|---|
| author | Luo, Sha Prabhu, Yogesh Ossowski, Timothy Chen, Kaiping Hu, Junjie |
| author_facet | Luo, Sha Prabhu, Yogesh Ossowski, Timothy Chen, Kaiping Hu, Junjie |
| contents | With the rapid growth of video centered social media, the ability to anticipate risky events from visual data is a promising direction for ensuring public safety and preventing real world accidents. Prior work has extensively studied supervised video risk assessment across domains such as driving, protests, and natural disasters. However, many existing datasets provide models with access to the full video sequence, including the accident itself, which substantially reduces the difficulty of the task. To better reflect real world conditions, we introduce a new video understanding benchmark RiskCueBench in which videos are carefully annotated to identify a risk signal clip, defined as the earliest moment that indicates a potential safety concern. Experimental results reveal a significant gap in current systems ability to interpret evolving situations and anticipate future risky events from early visual signals, highlighting important challenges for deploying video risk prediction models in practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03369 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RiskCueBench: Benchmarking Anticipatory Reasoning from Early Risk Cues in Video-Language Models Luo, Sha Prabhu, Yogesh Ossowski, Timothy Chen, Kaiping Hu, Junjie Computer Vision and Pattern Recognition Computation and Language With the rapid growth of video centered social media, the ability to anticipate risky events from visual data is a promising direction for ensuring public safety and preventing real world accidents. Prior work has extensively studied supervised video risk assessment across domains such as driving, protests, and natural disasters. However, many existing datasets provide models with access to the full video sequence, including the accident itself, which substantially reduces the difficulty of the task. To better reflect real world conditions, we introduce a new video understanding benchmark RiskCueBench in which videos are carefully annotated to identify a risk signal clip, defined as the earliest moment that indicates a potential safety concern. Experimental results reveal a significant gap in current systems ability to interpret evolving situations and anticipate future risky events from early visual signals, highlighting important challenges for deploying video risk prediction models in practice. |
| title | RiskCueBench: Benchmarking Anticipatory Reasoning from Early Risk Cues in Video-Language Models |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2601.03369 |