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

One of the most important factors in training object recognition networks using convolutional neural networks (CNN) is the provision of annotated data accompanying human judgment. Particularly, in object detection or semantic segmentation, the annotation process requires considerable human effort. In this paper, we propose a semi-supervised learning (SSL)-based training methodology for object detection, which makes use of automatic labeling of un-annotated data by applying a network previously trained from an annotated dataset.

This paper proposes a method, Dense ByNet, for single image super-resolution based on a convolutional neural network (CNN). The main innovation is a new architecture that combines several CNN design choices. Using a residual network as a basis, it introduces dense connections inside residual blocks, significantly reducing the number of parameters. Second, we apply dilation convolutions to increase the spatial context. Lastly, we propose modifications to the activation and cost functions.

Interactive image segmentation that uses a bounding box containing the foreground has gained great popularity because of its convenience. However, its performance is often degraded when the bounding box is not tight enough or covers large background regions. To solve this problem, this paper proposes a novel segmentation algorithm called ``SuperCut". This algorithm provides robust segmentation in one cut even with loose bounding boxes.

In this paper, we generate and control semantically interpretable filters that are directly learned from natural images in an unsupervised fashion. Each semantic filter learns a visually interpretable local structure in conjunction with other filters. The significance of learning these interpretable filter sets is demonstrated on two contrasting applications. The first application is image recognition under progressive decolorization, in which recognition algorithms should be color-insensitive to achieve a robust performance.

Loop filters are used in video coding to remove artifacts or improve performance. Recent advances in deploying convolutional neural network (CNN) to replace traditional loop filters show large gains but with problems for practical application.First, different model is used for frames encoded with different quantization parameter (QP), respectively. It is expensive for hardware. Second, float points operation in CNN leads to inconsistency between encoding and decoding across different platforms. Third, redundancy within CNN model consumes precious computational resources.

Pose estimation is highly valued in surveillance systems in the era of big data. However, current human pose datasets are limited in their coverage of the pose estimation challenges in outdoor surveillance scenarios. In this paper, we introduce a novel Surveillance Human Pose Dataset (SHPD).

Canonical correlation analysis (CCA) is a data-driven method that has been successfully used in functional magnetic resonance imaging (fMRI) data analysis. Standard CCA extracts meaningful information from a data set by seeking pairs of linear combinations from two sets of variables with maximum pairwise correlation. So far, however, this method has been used without incorporating prior information available for fMRI data. In this paper, we address this issue by proposing a new CCA method named PCCA (for projection CCA).