The paper claims 87.7% AP on DAD by aligning VGG-16 video features with Long-CLIP embeddings of California DMV accident reports and GPT-generated safe-driving reports.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Domain-Enhanced Dual-Branch Model for Efficient and Interpretable Accident Anticipation
The paper claims 87.7% AP on DAD by aligning VGG-16 video features with Long-CLIP embeddings of California DMV accident reports and GPT-generated safe-driving reports.