UCF-QNRF
PulseAugur coverage of UCF-QNRF — every cluster mentioning UCF-QNRF across labs, papers, and developer communities, ranked by signal.
-
New method enhances crowd analysis with guided mask learning
Researchers have developed a novel semi-supervised approach for crowd instance segmentation and counting, utilizing an Exclusion-Constrained Dual-Prompt SAM (EDP-SAM) to generate mask supervision from existing datasets.…
-
New method enhances crowd instance segmentation using SAM and reinforced point selection
Researchers have developed a new method called Dense Point-to-Mask Optimization (DPMO) to improve instance segmentation in dense crowd scenarios. DPMO integrates the Segment Anything Model (SAM) with a Nearest Neighbor …
-
CLIP-EBC model enhances CLIP for accurate crowd counting
Researchers have developed CLIP-EBC, a novel approach that enables the CLIP model to accurately estimate crowd density in images. This method addresses limitations in existing classification-based frameworks by using in…