Seminar
- Topic: Deformable Convolutional Networks
- Speaker: Longwei Fang
- Date: 3:30 P.M., Friday, May 11, 2018
- Place: The Fifth Meeting Room in Intelligent Building
- Abstract: Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we introduce two new [more...]
- Topic: Multi-atlas-aware Fully Convolutional Networks for Brain Labeling
- Speaker: Longwei Fang
- Date: 10:00 A.M., Thursday, Nov 2, 2017
- Place: The Fifth Meeting Room in Intelligent Building
- Abstract: Multi-atlas-based methods are commonly used for MR brain image labeling, which alleviates the burdening and time-consuming task of manual labeling in neuroimaging analysis studies. Traditionally, [more...]
- Topic: Combining Multiscale Diffusion Kernels for Learning the Structural and Functional Brain Connectivity
- Speaker: Wen Hongwei
- Date: 10:00 A.M., Friday, Mar 3, 2017
- Place: Intelligent building Meeting Room #6
- Abstract: One of the key strengths of the proposed approach is that it does not require hand-tuning of model parameters but actually learns them as part of the optimization process. The learned parameters may [more...]
- Topic: Modeling the outcome of structural disconnection on resting-state functional connectivity
- Speaker: Wen Hongwei
- Date: 10:30 A.M., Friday, Dec 16, 2016
- Place: Intelligent building Meeting Room #6
- Abstract: A growing body of experimental evidence suggests that functional connectivity at rest is shaped by the un-derlying anatomical structure. Furthermore, the organizational properties of resting-state [more...]
- Topic: 国家奖学金预答辩
- Speaker: Wen Hongwei
- Date: 3:00 P.M., Monday, Oct 10, 2016
- Place: Room 1022
- Abstract: 2016年研究生国家奖学金预答辩
- Topic: 3D ShapeNets: A Deep Representation for Volumetric Shapes
- Speaker: Huaiwei Cong
- Date: 10:00 A.M., Friday, Jul 29, 2016
- Place: Room 1022
- Abstract: This paper propose to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network.