TIP Volume 29 | 2020

Graph-based transforms have been shown to be powerful tools in terms of image energy compaction. However, when the size of the support increases to best capture signal dependencies, the computation of the basis functions becomes rapidly untractable. This problem is in particular compelling for high dimensional imaging data such as light fields. The use of local transforms with limited supports is a way to cope with this computational difficulty.

This paper proposes a multi-layer neural network structure for few-shot image recognition of novel categories. The proposed multi-layer neural network architecture encodes transferable knowledge extracted from a large annotated dataset of base categories. This architecture is then applied to novel categories containing only a few samples.

RGB-induced salient object detection has recently witnessed substantial progress, which is attributed to the superior feature learning capability of deep convolutional neural networks (CNNs). However, such detections suffer from challenging scenarios characterized by cluttered backgrounds, low-light conditions and variations in illumination. Instead of improving RGB based saliency detection, this paper takes advantage of the complementary benefits of RGB and thermal infrared images.

This paper proposes a multi-layer neural network structure for few-shot image recognition of novel categories. The proposed multi-layer neural network architecture encodes transferable knowledge extracted from a large annotated dataset of base categories. This architecture is then applied to novel categories containing only a few samples.

We propose a novel multi-stream architecture and training methodology that exploits semantic labels for facial image deblurring. The proposed Uncertainty Guided Multi-Stream Semantic Network (UMSN) processes regions belonging to each semantic class independently and learns to combine their outputs into the final deblurred result. Pixel-wise semantic labels are obtained using a segmentation network. 

We introduce an effective fusion-based technique to enhance both day-time and night-time hazy scenes. When inverting the Koschmieder light transmission model, and by contrast with the common implementation of the popular dark-channel [1] , we estimate the airlight on image patches and not on the entire image.

Although many spectral unmixing models have been developed to address spectral variability caused by variable incident illuminations, the mechanism of the spectral variability is still unclear. This paper proposes an unmixing model, named illumination invariant spectral unmixing (IISU).

We present a method to compress geometry information of point clouds that explores redundancies across consecutive frames of a sequence. It uses octrees and works by progressively increasing the resolution of the octree. At each branch of the tree, we generate an approximation of the child nodes by a number of methods which are used as contexts to drive an arithmetic coder.

Image semantic segmentation tasks and methods based on weakly supervised conditions have been proposed and achieve better and better performance in recent years. However, the purpose of these tasks is mainly to simplify the labeling work. In this paper, we establish a new and more challenging task condition.

The inverse synthetic aperture radar (ISAR) imaging technique of a moving target with sparse sampling data has attracted wide attention due to its ability to reduce the data collection burden. However, traditional low-rank or 2D compressive sensing (CS)-based ISAR imaging methods can handle the random sampling or the separable sampling data only.