IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

We show that high performance optical flow estimation can be achieved without using dense cost volumes.

[paper]

arXiv, 2020.

We theoretically solve the vanishing/exploding gradients problem in neural networks. Key idea: constrain signal norm in both directions via a new class of activation functions and orthogonal weight matrices.

[paper]

IEEE Winter Conference on Applications of Computer Vision (WACV), 2020.

We pointed out the problem of image warping in estimating optical flow and proposed the deformable cost volume to solve the problem.

[paper]

Pattern Recognition Letters, 2019.

International Joint Conference on Neural Networks (IJCNN), 2019.

We proposed a new neural network module, Contrast Association Units, to model the relations between two sets of input variables.

[paper]

ICML workshop on Modern Trends in Nonconvex Optimization for Machine Learning, 2018.

We proposed a new matrix approximation method which allows efficient matrix inversion. We then applied the method to second order optimization algorithms for training neural networks.

[paper]

ACM Conference on Computer and Communications Security (CCS), 2017.

We proposed a new method for privacy-preserving predictions with trained
neural networks.

[paper]

Pattern Recognition, 2016.

We designed a fast graph matching algorithm with time complexity
*O*(*n^3*) per iteration, where *n* is the size of a graph. We
proved its convergence rate. It takes within 10 seconds to match two graphs of
1000 nodes on a PC.

[paper]

International Joint Conference on Artificial Intelligence (IJCAI), 2016.

We found visual attributes of object classes can be unsuperisedly learned by applying Independent Component Analysis on the softmax outputs of a trained ConvNet. We showed such attributes can be useful for object recognition by performing zero-shot learning experiments on the ImageNet dataset of over 20,000 object classes.

[paper]

Graph-Based Representations in Pattern Recognition (GbR), 2013.

We designed a fast Maximum Common Subgraph (MCS) algorithm for Planar Triangulation Graphs. Its time complexity is *O*(*mnk*), where *n* is the size of one graph, *m* is the size of the other graph and *k* is the size of their MCS.

[paper]

Neural Computation, 2011.

We found a unique traveling bump solution, which was unknown to exist before, in a set of two-dimensional neural network equations.

[paper]