Enhancing Vision-Language Models with Scene Graphs for Traffic Accident Understanding

Documenti analoghi

• EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis
  di: Fang, Jianwu, et al.
  Pubblicazione: (2025)
• SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation
  di: Zhang, Jiwen, et al.
  Pubblicazione: (2026)
• Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding
  di: Li, Haoyuan, et al.
  Pubblicazione: (2025)
• Explainable Scene Understanding with Qualitative Representations and Graph Neural Networks
  di: Belmecheri, Nassim, et al.
  Pubblicazione: (2025)
• Application of Vision-Language Model to Pedestrians Behavior and Scene Understanding in Autonomous Driving
  di: Gao, Haoxiang, et al.
  Pubblicazione: (2025)