MSEF fine-tunes VisualGLM-6B with GPT-4-generated soft labels to assess streetscape walkability, safety, and vibrancy, reporting F1 0.84 and 89.3% perception agreement.
Measuring residents’ perceptions of city streets to inform better street planning through deep learning and space syntax[J]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Interpretable Multimodal Framework for Human-Centered Street Assessment: Integrating Visual-Language Models for Perceptual Urban Diagnostics
MSEF fine-tunes VisualGLM-6B with GPT-4-generated soft labels to assess streetscape walkability, safety, and vibrancy, reporting F1 0.84 and 89.3% perception agreement.