Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples under the condition that some output classes are unknown during supervised learning. To address this challenging task, GZSL leverages semantic information of the seen (source) and unseen (target) classes to bridge the gap between both seen and unseen classes. Since its introduction, many GZSL models have been formulated. In this review paper, we present a comprehensive review on GZSL. Firstly, we provide an overview of GZSL including the problems and challenges. Then, we introduce a hierarchical categorization for the GZSL methods and discuss the representative methods in each category. In addition, we discuss the available benchmark data sets and applications of GZSL, along with a discussion on the research gaps and directions for future investigations.

Rails are among the most important components of railway transportation, and real-time defects detection of the railway is an important and challenging task because of intensity inhomogeneity, low contrast, and noise. This paper presents an automatic railway visual detection system (RVDS) for surface defects and focuses on several key issues of RVDS. First, in view of challenges such as complex condition and orbital reflectance inequality, we put forward a region-of-interest detection region extraction algorithm by vertical projection and gray contrast algorithm. In addition, a curvature filter equipped with implicit computing and surface preserving power is studied to eliminate noise and keep only the details. Then, an improved fast and robust Gaussian mixture model based on Markov random field is established for accurate and rapid surface defect segmentation. Additionally, an expectation-maximization algorithm is applied to optimize the parameters. The experimental results demonstrate that the proposed method performs well with both noisy and railway images, which enables identification and segmentation of the defects from rail surface, achieving detection performance with 92% precision and 88.8% recall rate on average, and is robust compared with the related well-established approaches.

In underwater scenes, degraded underwater images caused by wavelength-dependent light absorption and scattering present huge challenges to vision tasks. Underwater image enhancement has attracted much attention due to the significance of vision-based applications in marine engineering and underwater robotics. Numerous underwater image enhancement algorithms have been proposed in the last few years. However, almost all existing approaches focus only on the enhancement of independent images. Considering that images photographed in the same underwater scene usually share similar degradation, related images can provide rich complementary information for each other’s enhancement. In this paper, we propose an Underwater Image Co-enhancement Network (UICoE-Net) based on an encoder-decoder Siamese architecture. For joint learning, we introduced correlation feature matching units into the multiple layers of our Siamese encoder-decoder structure in order to communicate the mutual correlation of the two branches. Extensive experiments using the Underwater Image Enhancement Benchmark (UIEB), Underwater Image Co-enhancement Dataset (UICoD) collected from an underwater video dataset with ground-truth reference and Stereo Quantitative Underwater Image Dataset (SQUID) dataset demonstrate the effectiveness of our method.

Emotions play a crucial role in decision-making, brain activity, human cognition, and social intercourse. This paper proposes a hierarchical network structure with subnetwork nodes to discriminate three human emotions: 1) positive; 2) neutral; and 3) negative. Each subnetwork node embedded in the network that are formed by hundreds of hidden nodes, could be functional as an independent hidden layer for feature representation. The top layer of the hierarchical network, like the mammal cortex in the brain, combine such features generated from subnetwork nodes, but simultaneously, recast these features into a mapping space so that the network can be performed to produce more reliable cognition. The proposed method is compared with other state-of-the-art methods. The experimental results from two different EEG datasets show that a promising result is obtained when using the proposed method with both single and multiple modality.