Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025★ 1 cited
GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts
Fan Yuan, Yuchen Yan, Yifan Jiang +9
Mathematical reasoning is a key capability for vision-language models (VLMs), yet current benchmarks mainly evaluate text-based or explicitly symbolic visual inputs. It remains unc…
cs.CV2025
MA-CBP: A Criminal Behavior Prediction Framework Based on Multi-Agent Asynchronous Collaboration
Cheng Liu, Daou Zhang, Tingxu Liu +7
With the acceleration of urbanization, criminal behavior in public scenes poses an increasingly serious threat to social security. Traditional anomaly detection methods based on fe…
cs.CV2025
Hoi2Threat: An Interpretable Threat Detection Method for Human Violence Scenarios Guided by Human-Object Interaction
Yuhan Wang, Cheng Liu, Daou Zhang +6
In light of the mounting imperative for public security, the necessity for automated threat detection in high-risk scenarios is becoming increasingly pressing. However, existing me…