Research
StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks
|
|
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
|
|
Improving GANs Using Optimal Transport We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution |
|
Improved Human Pose Estimation through Adversarial Data Augmentation Deep models are usually trained in a two-phase paradigm, where data collection and network training are separated. This may not be efficient since data collection is blind to network training. |
- Page Site: ./research/other-research-projects
Generative Adversarial Networks(GAN)
|
|
Query Specific Fusion for Large-Scale Image Retrieval Recent image retrieval algorithms based on local features indexed by a vocabulary tree and holistic features indexed by compact hashing codes both demonstrate excellent scalability. However, their retrieval precision may vary dramatically among queries. This motivates us to investigate how to fuse the ordered retrieval sets given by multiple retrieval methods, to further enhance the retrieval precision. |
|
Image Annotation using Group Sparsity Automatically assigning relevant text keywords to images is an important problem. We introduce a regularization based feature selection algorithm to leverage both the sparsity and clustering properties of features, and incorporate it into the image annotation task. |
|
Transformation Invariant Sparse Representation We propose a framework for obtaining transformation-invariant image sparse representation. W can simultaneously recover the sparse representation of a target image and the image plane transformation between the target and the model images. |
|
This project address the problem of registering a sequence of images in a moving dynamic texture video. |
|
This projects address the issue of motion saliency detection in video sequences. |
- Page Site: research/medical-image-analysis
Deformable Segmentation using Sparse Shape Representation We propose Sparse Shape Composition model (SSC) to deal with these three challenges in a unified framework. |
|
We propose composite splitting algorithms which are applied to the compressed MR image reconstruction. |
|
Left Ventricle Motion Analysis The in-wall motion and the strain field of the left ventricle myocardium are reconstructed from tagged MRI. |
|
4D High-resolution Cardiac Reconstruction 4D cardiac reconstruction using high resolution CT images captures complex anatomical features, such as the papillary muscles and the ventricular trabeculae. |
|
4D Cardiac Reconstruction and Blood Flow Simulation 4D cardiac reconstructions are created using high resolution CT images captures complex anatomical features. A simulation of the blood flow is performed and visualizations are generated to find problems. |
|
We propose a robust deformable segmentation method, Metamorphs, which integrates the region information with the gradient information. We use this algorithm to solve diverse applications such rodent brain segmentation in MRI and cardiac segmentation in CT. |
|
The deformable contours and moving trajectories of cancer cells are tracked in computerized Video Time-lapse Microcopy. |
|
We introduce a tag separation method for better cardiac boundary segmentation and tag tracking. |
|
Bioluminescence Image Anaysis and Diagnosis 4D cardiac reconstruction using high resolution CT images captures complex anatomical features, such as the papillary muscles and the ventricular trabeculae. |
- Page Site: ./research/computer-graphics
4D Cardiac Reconstruction and Blood Flow Simulation 4D cardiac reconstructions are created using high resolution CT images captures complex anatomical features. A simulation of the blood flow is performed and visualizations are generated to find problems. |
|
We extend the As-Rigid-As-Possible Surface Modeling by considering skeleton information. It is able to roughly preserve the volume magnitude during deformation. |
|
We consider the minimization of a smooth convex function regularized by the mixture of prior models. In this paper, we present two algorithms to effectively solve it, and apply the proposed algorithms to compressed MR image reconstruction and low-rank tensor completion. |
- Page Site: ./research/behavior-and-gesture-analysis
Accurate face tracking and 3D head pose prediction (shown in top left as a 3D vector of pitch, yaw and tilt) while the face is making various facial expressions as well as out of plane rotations. The 79 tracked landmarks corresponding to the eyes, eyebrows, nose, mouth and face contour are shown as red dots. |
|
We are able to track face, head and eyebrow height, and the system detects no wh non-manual marker. |
|
Facial Expression Recognition and Intensity Estimation. |
|
Dyadic Synchrony as a Measure of Trust and Veracity We investigate how degree of interactional synchrony can signal whether trust is present, absent, increasing or declining. |
|
Fatigue detection by capturing eyelid blinking We develop a system to detect fatigues by tracking slow eyelid closure using a single camera. |
|
In this project we try to assess natural movements of children with Autism Spectrum Disorders in the classroom settings. |
|
Expression Flow for Face Compositing We address the problem of correcting an undesirable expression on a face photo by transferring local facial components. |
|
This project models human group activities in video sequences. |