Sorry, you need to enable JavaScript to visit this website.

Depth prediction from a single monocular image is a challenging yet valuable task, as often a depth sensor is not available. The state-of-the-art approach \cite{Liu2016} combines a deep fully convolutional network (DFCN) with a conditional random field (CRF), allowing the CRF to correct and smooth the depth values estimated by the DFCN according to efficient contextual modeling.

Videos of complex events are difficult to represent solely as
bags of low level features. Increasingly, supervised concepts
or attributes are being employed as the intermediate representation
of such videos. We propose a probabilistic framework
that models the conditional relationships between the
concepts and events and devise an approximate yet tractable
solution to infer the posterior distribution to perform event
classification. Using noisy outputs of pre-trained concept detectors,
we learn semantic and visual dependencies between

Polarimetric synthetic aperture radar (PolSAR) plays an indispensable part in remote sensing. With its development and application, rapid and accurate online classification for PolSAR data becomes more and more important. PolSAR data can be depicted by different features such as polarimetric, texture and color features, which can be considered as multiple views. In this paper, we propose an online multiview

Realistic image composite requires the appearance of foreground and background layers to be consistent. This is difficult to achieve because the foreground and the background may be taken from very different environments. This paper proposes a novel composite adjustment method that can harmonize appearance of different composite layers. We introduce the Best-Buddy Prior (BBP), which is a novel compact representations of the joint co-occurrence distribution of natural image patches. BBP can be learned from unlabelled images given only the unsupervised regional segmentation.

This paper proposes a simple spatial-temporal smoothness based method for solving dense non-rigid structure-from-motion (NRSfM). First, we revisit the temporal smoothness and demonstrate that it can be extended to dense case directly. Second, we propose to exploit the spatial smoothness by resorting to the Laplacian of the 3D non-rigid shape. Third, to handle real world noise and outliers in measurements, we robustify the data term by using the L1 norm.

Separating diffuse and specular reflection components is important for preprocessing of various computer vision techniques such as photometric stereo. In this paper, we address diffuse-specular separation for photometric stereo based on light fields. Specifically, we reveal the low-rank structure of the multi-view images under varying light source directions, and then formulate the diffuse-specular separation as a low-rank approximation of the 3rd order tensor.

In this research, we propose an object localization method to boost the performance of current object detection techniques. This method utilizes the image edge information as a clue to determine the location of the objects. The Generic Edge Tokens (GETs) of the image are extracted based on the perceptual organization elements of human vision. These edge tokens are parsed according to the Best First Search algorithm to fine-tune the location of objects, where the objective function is the detection score returned by the Deep Convolutional Neural Network.