NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
PulseAugur coverage of NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization — every cluster mentioning NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization across labs, papers, and developer communities, ranked by signal.
-
DCA-MoE framework enhances crowd counting with adaptive fusion and routing
Researchers have introduced DCA-MoE, a novel framework designed to improve crowd counting accuracy by making feature fusion and expert routing content-dependent. This approach utilizes Spatially Adaptive Layer Fusion (S…
-
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…
-
Action Hints paper uses LLMs for skeleton-based video anomaly detection
Researchers have developed a new framework for zero-shot video anomaly detection (ZS-VAD) that leverages semantic typicality and context uniqueness from skeleton data. This approach aims to improve generalization to new…