IEEE

Learning Where to Look: VLM-Assisted Efficient Inference for Sparse Aerial Objects Segmentation

Abstract: Existing high-performance semantic segmentation methods for remote sensing often struggle with the tradeoff between inference efficiency and high-resolution processing, especially in ...
GitHub

Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation

Abstract: Skeleton-based Temporal Action Segmentation (STAS) seeks to densely segment and classify diverse actions within long, untrimmed skeletal motion sequences. However, existing STAS ...
IEEE

Deep Learning-Driven Segmentation of Unseen Objects in Indoor Robotic Environments

Abstract: For robots operating in unstructured indoor environments, the ability to accurately perceive and interact with invisible objects is crucial because it is infeasible and impractical to assume ...
GitHub

Multi-platform point cloud analysis — registration, segmentation, surface reconstruction, and feature extraction for aerial, terrestrial, and UAV LiDAR.

Point cloud tooling in Python is fragmented. laspy reads files. Open3D visualizes them. PDAL pipelines transform them. But nothing treats acquisition platform as a first-class concept — and platform ...