10 Result(s)
-
Chapter and Conference Paper
Hybrid Spatio-Temporal Network for Face Forgery Detection
Facial manipulation techniques have aroused increasing security concerns, leading to various methods to detect forgery videos. However, existing methods suffer from a significant performance gap compared to im...
-
Article
Rectified Binary Convolutional Networks with Generative Adversarial Learning
Binarized convolutional neural networks (BNNs) are widely used to improve the memory and computational efficiency of deep convolutional neural networks for to be employed on embedded devices. However, existing...
-
Article
Binarized Neural Architecture Search for Efficient Object Recognition
Traditional neural architecture search (NAS) has a significant impact in computer vision by automatically designing network architectures for various tasks. In this paper, binarized neural architecture search ...
-
Article
Bounding Multiple Gaussians Uncertainty with Application to Object Tracking
This paper proves the uncertainty bound for the multiple Gaussian functions, termed multiple Gaussians Uncertainty (MGU), which significantly generalizes the uncertainty principle for the single Gaussian funct...
-
Article
Geometric Reinforcement Learning for Path Planning of UAVs
We proposed a new learning algorithm, named Geometric Reinforcement Learning (GRL), for path planning of Unmanned Aerial Vehicles (UAVs). The contributions of GRL are as: (1) GRL exploits a specific reward mat...
-
Chapter and Conference Paper
Object Detection and Viewpoint Estimation with Auto-masking Neural Network
Simultaneously detecting an object and determining its pose has become a popular research topic in recent years. Due to the large variances of the object appearance in images, it is critical to capture the dis...
-
Chapter and Conference Paper
Precise 3D Reconstruction from a Single Image
3D object reconstruction from single images has extensive applications in multimedia. Most of existing related methods only recover rough 3D objects and the objects are often required to be interconnected. In ...
-
Chapter and Conference Paper
Compressed Sensing Ensemble Classifier for Human Detection
This paper proposes a novel Compressed Sensing Ensemble Classifier (CSEC) for human detection. The proposed CSEC employs the compressed sensing technique to get a more sparse model with a more reasonable selec...
-
Article
A deformation model to reduce the effect of expressions in 3D face recognition
In 3D face recognition, most work utilizes the rigid parts of face surfaces for matching to exclude the distortion caused by expressions. However, across a broad range of expressions, the rigid parts may not a...
-
Chapter and Conference Paper
Degen Generalized Cylinders and Their Properties
Generalized cylinder (GC) has played an important role in computer vision since it was introduced in the 1970s. While studying GC models in human visual perception of shapes from contours, Marr assumed that GC...
