2 papers
cs.CV2025
FootFormer: Estimating Stability from Visual Input
Keaton Kraiger, Jingjing Li, Skanda Bharadwaj +3
We propose FootFormer, a cross-modality approach for jointly predicting human motion dynamics directly from visual input. On multiple datasets, FootFormer achieves statistically si…
cs.CV2025
Recurrence-based Vanishing Point Detection
Skanda Bharadwaj, Robert Collins, Yanxi Liu
Classical approaches to Vanishing Point Detection (VPD) rely solely on the presence of explicit straight lines in images, while recent supervised deep learning approaches need labe…