Domain adaptation (DA) aims to generalize a learning model across training and testing data despite the mismatch of their data distributions. In light of a theoretical estimation of upper error bound, we argue in this paper that an effective DA method should 1) search a shared feature subspace where source and target data are not only aligned in terms of distributions as most state of the art DA methods do, but also discriminative in that instances of different classes are well separated; 2) account for the geometric structure of the underlying data manifold when inferring data labels on the target domain. In comparison with a baseline DA method which only cares about data distribution alignment between source and target, we derive three different DA models, namely CDDA, GA-DA, and DGA-DA, to highlight the contribution of Close yet Discriminative DA(CDDA) based on 1), Geometry Aware DA (GA-DA) based on 2), and finally Discriminative and Geometry Aware DA (DGA-DA) implementing jointly 1) and 2). Using both synthetic and real data, we show the effectiveness of the proposed approach which consistently outperforms state of the art DA methods over 36 image classification DA tasks through 6 popular benchmarks. We further carry out in-depth analysis of the proposed DA method in quantifying the contribution of each term of our DA model and provide insights into the proposed DA methods in visualizing both real and synthetic data.

A novel ternary 3D ZnIn₂S₄–MoS₂ microsphere/1D CdS nanorod (ZIS/MoS₂/CdS) photocatalyst was created to achieve excellent photocatalytic H₂ evolution under visible light irradiation.

No abstract

The extracellular action potentials recorded on an electrode result from the collective simultaneous electrophysiological activity of an unknown number of neurons. Identifying and assigning these action potentials to their firing neurons-'spike sorting'-is an indispensable step in studying the function and the response of an individual or ensemble of neurons to certain stimuli. Given the task of neural spike sorting, the determination of the number of clusters (neurons) is arguably the most difficult and challenging issue, due to the existence of background noise and the overlap and interactions among neurons in neighbouring regions. It is not surprising that some researchers still rely on visual inspection by experts to estimate the number of clusters in neural spike sorting. Manual inspection, however, is not suitable to processing the vast, ever-growing amount of neural data. To address this pressing need, in this paper, thirty-three clustering validity indices have been comprehensively reviewed and implemented to determine the number of clusters in neural datasets. To gauge the suitability of the indices to neural spike data, and inform the selection process, we then calculated the indices by applying k-means clustering to twenty widely used synthetic neural datasets and one empirical dataset, and compared the performance of these indices against pre-existing ground truth labels. The results showed that the top five validity indices work consistently well across variations in noise level, both for the synthetic datasets and the real dataset. Using these top performing indices provides strong support for the determination of the number of neural clusters, which is essential in the spike sorting process.

In visual tracking, holistic and part-based representations are both popular choices to model target appearance. The former is known for great efficiency and convenience while the latter for robustness against local appearance or shape variations. Based on non-negative matrix factorization (NMF), we propose a novel visual tracker that takes advantage of both groups. The idea is to model the target appearance by a non-negative combination of non-negative components learned from examples observed in previous frames. To adjust NMF to the tracking context, we include sparsity and smoothness constraints in addition to the non-negativity one. Furthermore, an online iterative learning algorithm, together with a proof of convergence, is proposed for efficient model updating. Putting these ingredients together with a particle filter framework, the proposed tracker, Constrained Online Non-negative Matrix Factorization (CONMF), achieves robustness to challenging appearance variations and non-trivial deformations while runs in real time. We evaluate the proposed tracker on various benchmark sequences containing targets undergoing large variations in scale, pose or illumination. The robustness and efficiency of CONMF is validated in comparison with several state-of-the-art trackers.

We propose a novel local nearest neighbor distance (LNND) descriptor for anomaly detection in crowded scenes. Comparing with the commonly used low-level feature descriptors in previous works, LNND descriptor has two major advantages. First, LNND descriptor efficiently incorporates spatial and temporal contextual information around the video event that is important for detecting anomalous interaction among multiple events, while most existing feature descriptors only contain the information of single event. Second, LNND descriptor is a compact representation and its dimensionality is typically much lower than the low-level feature descriptor. Therefore, not only the computation time and storage requirement can be accordingly saved by using LNND descriptor for the anomaly detection method with offline training fashion, but also the negative aspects caused by using high-dimensional feature descriptor can be avoided. We validate the effectiveness of LNND descriptor by conducting extensive experiments on different benchmark datasets. Experimental results show the promising performance of LNND-based method against the state-of-the-art methods. It is worthwhile to notice that the LNND-based approach requires less intermediate processing steps without any subsequent processing such as smoothing but achieves comparable event better performance.

Visual tracking has recently gained a great advance with the use of the convolutional neural network (CNN). Usually, existing CNN-based trackers exploit the features from a single layer or a certain combination of multiple layers. However, these features only characterise an object from an invariable aspect and cannot adapt to scene variation, which limits the performance of such trackers. To overcome this limitation, the authors study the problem from a new perspective and propose a novel convolutional layer selection method. To obtain robust appearance representation, they investigate the advantages of features extracted from different convolutional layers. To determine the correctness of the tracking prediction and updated model, they design a verification mechanism based on historical retrospect, which can estimate the deviation for each layer by bidirectionally locating the target. Meanwhile, the deviation works as the layer-wise selection criteria. Extensive evaluations on the OTB-2013, visual object tracking (VOT)-2016 and VOT-2017 benchmarks demonstrate that the proposed tracker performs favourably against several state-of-the-art trackers. The results are presented in terms of EAO, Av and Rv. The best, second and third results are marked underline, bold italic, italic, respectively. Bold represents our method and results.

In this survey, we propose to explore and discuss the common rules behind knowledge transfer works for vision recognition tasks. To achieve this, we firstly discuss the different kinds of reusable knowledge existing in a vision recognition task, and then we categorize different knowledge transfer approaches depending on where the knowledge comes from and where the knowledge goes. Compared to previous surveys on knowledge transfer that are from the problem-oriented perspective or from the technique-oriented perspective, our viewpoint is closer to the nature of knowledge transfer and reveals common rules behind different transfer learning settings and applications. Besides different knowledge transfer categories, we also show some research works that study the transferability between different vision recognition tasks. We further give a discussion about the introduced research works and show some potential research directions in this field.