IEEE Transactions on Pattern Analysis and Machine Intelligence

Recently a deterministic method, frequent directions (FD) is proposed to solve the high dimensional low rank approximation problem. It works well in practice, but experiences high computational cost. In this paper, we establish a fast frequent directions ...

With the powerfulness of convolution neural networks (CNN), CNN based face reconstruction has recently shown promising performance in reconstructing detailed face shape from 2D face images. The success of CNN-based methods relies on a large number of ...

This paper studies the compact coding approach to approximate nearest neighbor search. We introduce a composite quantization framework. It uses the composition of several ($M$M) elements, each of which is selected from a different dictionary, to ...

We propose an algorithm for simplifying a finite mixture model into a reduced mixture model with fewer mixture components. The reduced model is obtained by maximizing a variational lower bound of the expected log-likelihood of a set of virtual samples. We ...

Bayesian nonparametrics are a class of probabilistic models in which the model size is inferred from data. A recently developed methodology in this field is small-variance asymptotic analysis, a mathematical technique for deriving learning algorithms ...

Thanks to the availability and increasing popularity of wearable devices such as GoPro cameras, smart phones, and glasses, we have access to a plethora of videos captured from first person perspective. Surveillance cameras and Unmanned Aerial Vehicles (...

Model learning from class imbalanced training data is a long-standing and significant challenge for machine learning. In particular, existing deep learning methods consider mostly either class balanced data or moderately imbalanced data in model training, ...

This paper presents an unsupervised learning approach for simultaneous sample and feature selection, which is in contrast to existing works which mainly tackle these two problems separately. In fact the two tasks are often interleaved with each other: ...

We present a robust approach for computing disparity maps with a supervised learning-based confidence prediction. This approach takes into consideration following features. First, we analyze the characteristics of various confidence measures in the random ...

Human faces are one interesting object class with numerous applications. While significant progress has been made in the generic deblurring problem, existing methods are less effective for blurry face images. The success of the state-of-the-art image ...

Depth cues have been proved very useful in various computer vision and robotic tasks. This paper addresses the problem of monocular depth estimation from a single still image. Inspired by the effectiveness of recent works on multi-scale convolutional ...

A wide variety of computer vision applications rely on superpixel or supervoxel algorithms as a preprocessing step. This underlines the overall importance that these approaches have gained in recent years. However, most methods show a lack of temporal ...

We present a physically-based approach for simulating makeup in face images. The key idea is to decompose the face image into intrinsic image layers – namely albedo, diffuse shading, and specular highlights – which are each differently affected by ...

We introduce a new multi-dimensional nonlinear embedding—Piecewise Flat Embedding (PFE)—for image segmentation. Based on the theory of sparse signal recovery, piecewise flat embedding with diverse channels attempts to recover a piecewise constant image ...

Recognising human attributes from surveillance footage is widely studied for attribute-based re-identification. However, most works assume coarse, expertly-defined categories, ineffective in describing challenging images. Such brittle representations are ...

Binary descriptors have been widely used for efficient image matching and retrieval. However, most existing binary descriptors are designed with hand-craft sampling patterns or learned with label annotation provided by datasets. In this paper, we propose ...

Video Object Segmentation, and video processing in general, has been historically dominated by methods that rely on the temporal consistency and redundancy in consecutive video frames. When the temporal smoothness is suddenly broken, such as when an ...