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

Visual tracking is a very important and challenging problem in the field of computer vision. In recent years, Siamese networks have been widely used for visual tracking due to their fast tracking speed, but many trackers based on Siamese network train their networks by utilizing either pairwise loss or triplet loss, which easily leads to over-fitting. In addition, it is difficult to distinguish some hard samples in the training samples. In this paper, we propose a novel global similarity loss to train the network.

Partial occlusions in face images pose a great problem for most face recognition algorithms due to the fact that most of these algorithms mainly focus on solving a second order loss function, e.g., mean square error (MSE), which will magnify the effect from occlusion parts. In this paper, we proposed a kernel non-second order loss function for sparse representation (KNS-SR) to recognize or restore partially occluded facial images, which both take the advantages of the correntropy and the non-second order statistics measurement.

Multi-scale object recognition and accurate object localization are two major problems for semantic segmentation in high resolution aerial images. To handle these problems, we design a Context Fuse Module to aggregate multi-scale features and propose an Attention Mix Module to combine different level features for higher localization accuracy. We further employ a Residual Convolutional Module to refine features in all levels. Based on these modules, we construct a new end-to-end network for semantic labeling in aerial images.

From video streaming to security and surveillance applications , video data play an important role in our daily living today. However, managing a large amount of video data and retrieving the most useful information for the user remain a challenging task. In this paper, we propose a novel video classification system that would benefit the scene understanding task. We define our classification problem as classifying background and foreground motions using the same feature representation for outdoor scenes.

Stereo high dynamic range (HDR) image/video can be generated by using a pair of stereo cameras with different exposure parameters. This paper proposes a new stereo HDR imaging method using generative adversarial networks (GAN) with a low dynamic range (LDR) stereo imaging system. It is assumed here that the left-view (LV) image is under-exposed and the right-view (RV) image is over-exposed.

We detect and classify Table Tennis strokes in videos recorded in natural condition. The goal is to develop an intelligent computer environment where teachers and students can analyse their games for improving players performance.

The region proposal task is generating a set of candidate regions that contain an object. In this task, it is most important to propose as many candidates of ground-truth in a fixed number of proposals. However, in an image, there are too small number of hard negative examples compared to the vast number of easy negatives, so the region proposal networks struggle to train hard negatives. Because of these problem, network tends to propose hard negatives as the candidates and fails to propose the ground-truth, which leads poor performance.

A new way of performing pixel by pixel comparison between two images is proposed, taking advantage of interesting invariance properties with respect to illumination conditions and camera settings.