Y
Yao Lu
Researcher at Australian National University
Publications - 21
Citations - 898
Yao Lu is an academic researcher from Australian National University. The author has contributed to research in topics: Artificial neural network & Optical flow. The author has an hindex of 8, co-authored 21 publications receiving 566 citations. Previous affiliations of Yao Lu include Zhongnan University of Economics and Law & Chinese Academy of Sciences.
Papers
More filters
Proceedings ArticleDOI
Oblivious Neural Network Predictions via MiniONN Transformations
TL;DR: MiniONN is presented, the first approach for transforming an existing neural network to an oblivious neural network supporting privacy-preserving predictions with reasonable efficiency and it is shown that MiniONN outperforms existing work in terms of response latency and message sizes.
Posted Content
Learning to Estimate Hidden Motions with Global Motion Aggregation
TL;DR: In this paper, a transformer-based approach is proposed to find long-range dependencies between pixels in the first image and perform global aggregation on the corresponding motion features, achieving state-of-the-art results on the challenging Sintel dataset.
Proceedings ArticleDOI
Learning Optical Flow from a Few Matches
TL;DR: In this article, the k closest matches in one feature map for each feature vector in the other feature map are computed and stored in a sparse data structure, which can reduce computational cost and memory use significantly.
Proceedings ArticleDOI
Devon: Deformable Volume Network for Learning Optical Flow
TL;DR: A new neural network module, Deformable Cost Volume, is proposed which can estimate multi-scale optical flow in a single high resolution and achieves comparable results to the state-of-the-art methods in public benchmarks.
Journal ArticleDOI
Traveling bumps and their collisions in a two-dimensional neural field
TL;DR: It is shown through numerical experiments that localized traveling excitation patterns (traveling bumps) exist in a two-dimensional neural field with excitation and inhibition mechanisms and might shed light on how neurons in the brain are functionally organized.