Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
DynEoMT: Learning Object Dynamicity from Online Segmentation Queries
Calvin Galagain, Martyna Poreba, François Goulette
Video segmentation models recognize and track objects over time, but they do not indicate whether each segmented region moves independently of the observing camera. This dynamicity…
cs.CV2026
Token-Space Mask Prediction for Efficient Vision Transformer Segmentation
Calvin Galagain, Martyna Poreba, François Goulette
Query-based Vision Transformer segmentation models typically reconstruct dense spatial feature maps to predict masks, inheriting design patterns from convolutional architectures. W…