StateBridge: Phase- and Track-Grounded Reasoning for Synthetic-to-Real Traffic Video Captioning and VQA
arXiv:2610.31898v1 Announce Type: new Abstract: Traffic safety videos provide rich evidence for understanding interactions between pedestrians and vehicles, but synthetic-to-real evaluation makes this setting challenging because models must learn from simulated scenes and generalize to real-world t…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-26 04:00 · arXiv cs.CV
StateBridge: Phase- and Track-Grounded Reasoning for Synthetic-to-Real Traffic Video Captioning and VQA