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

Intra interpolation filters for intra angular prediction play an important role in the coding performance. In the intra angular prediction of VVC, which is being standardized by the joint video coding expert team (JVET), block-size based switchable interpolation filters between 4-tap cubic and Gaussian interpolation filters is being studied. Although the two filters have different frequency characteristics, block size-based criteria are insufficient to represent the reference sample characteristics.

Recent works have shown the vulnerability of deep convolu-tional neural network (DCNN) to adversarial examples withmalicious perturbations. In particular, Black-Box attackswithout information of parameter and architectures of thetarget models are feared as realistic threats. To address thisproblem, we propose a method using an ensemble of mod-els trained by color-quantized data with loss maximization.Color-quantization can allow the trained models to focuson learning conspicuous spatial features to enhance the ro-bustness of DCNNs to adversarial examples.

The image blur assessment is of various practical use such as feedback of microscope dynamic focusing and assessment of the quality of pictures in social media. However, the prob- lem of providing a fast and sensitive assessment toward im- age blur is not easy to deal with. In this paper, we provide a new effective way to evaluate the blur level of the image.

This paper proposes a method for depth estimation from a single multispectral image by using a lens property known as chromatic aberration.

In order to predict where humans look in a 3D immersive en- vironment, saliency can be computed using either 3D saliency models or view-based approaches (2D projection). In fact, building a 3D complete model is still a challenging task that is not investigated enough in the research field while 2D imag- ing approaches have been extensively studied and have shown solid performances.

An important problem in artificial intelligence is to develop an ef-
ficient system that can adapt to new knowledge in an incremen-
tal manner without forgetting previously learned knowledge. Al-
though Convolutional Neural Networks (CNNs) are good at learn-
ing strong classifier and discriminative features, CNNs can not per-
form well in incremental classifier learning due to the catastrophic
forgetting problem in the retraining process. In this paper, we pro-
pose a novel yet extremely simple approach to enhance the discrim-

High-quality depth sensing is highly demanded in intelligent computer vision, 3DTV, and many other related fields. However, prevalent time-of-fly (ToF) depth sensors are of low resolution as the number of pixel-level demodulators is limited. Moreover, the rectangular sampling does not consider the signal characteristics of depth maps. Being a departure of previous resolution enhancement on rectangular sampling, this paper investigates the non-uniform sampling of depth maps, and the high-resolution depth reconstruction from limited non-uniformly distributed samples.