3 papers
cs.CV2023
Grouping Boundary Proposals for Fast Interactive Image Segmentation
Li Liu, Da Chen, Minglei Shu +1
Geodesic models are known as an efficient tool for solving various image segmentation problems. Most of existing approaches only exploit local pointwise image features to track geo…
cs.CG2023
Computing Geodesic Paths Encoding a Curvature Prior
Da Chen, Jean-Marie Mirebeau, Minglei Shu +1
In this paper, we introduce an efficient method for computing curves minimizing a variant of the Euler-Mumford elastica energy, with fixed endpoints and tangents at these endpoints…
cs.LG2022
Energy and Spectrum Efficient Federated Learning via High-Precision Over-the-Air Computation
Liang Li, Chenpei Huang, Dian Shi +4
Federated learning (FL) enables mobile devices to collaboratively learn a shared prediction model while keeping data locally. However, there are two major research challenges to pr…