Robust Visual Question Answering: Datasets, Methods, and Future Challenges.

Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often tend to memorize biases present in the training data rather than learning proper behaviors, such as grounding images before predicting answers. Therefore, these methods usually achieve high in-distribution but poor out-of-distribution performance. In recent years, various datasets and debiasing methods have been proposed to evaluate and enhance the VQA robustness, respectively. This paper provides the first comprehensive survey focused on this emerging fashion. Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives. Then, we examine the evaluation metrics employed by these datasets. Third, we propose a typology that presents the development process, similarities and differences, robustness comparison, and technical features of existing debiasing methods. Furthermore, we analyze and discuss the robustness of representative vision-and-language pre-training models on VQA. Finally, through a thorough review of the available literature and experimental analysis, we discuss the key areas for future research from various viewpoints.

LaenNet: Learning robust GCNs by propagating labels.

Graph Convolutional Networks (GCNs) can be acknowledged as one of the most significant methodologies for graph representation learning, and the family of GCNs has recently achieved great success in the community. However, in real-world scenarios, the graph data may be imperfect, e.g., with noisy and sparse features or labels, which poses a great challenge to the robustness of GCNs. To meet this challenge, we propose a simple-yet-effective LAbel-ENhanced Networks (LaenNet) architecture for GCNs, where the basic spirit is to propagate labels together with features. Specifically, we add an extra LaenNet module at one hidden layer of GCNs, which propagates labels along the graph and then integrates them with the hidden representations as the inputs to the deeper layer. The proposed LaenNet can be directly generalized to the variants of GCNs. We conduct extensive experiments to verify LaenNet on semi-supervised node classification tasks under four noisy and sparse graph data scenarios, including the graphs with noisy features, sparse features, noisy labels, and sparse labels. Empirical results indicate the superiority and robustness of LaenNet compared to the state-of-the-art baseline models. The implementation code is available to ease reproducibility1.

Active Surveillance via Group Sparse Bayesian Learning.

The key to the effective control of a diffusion system lies in how accurately we could predict its unfolding dynamics based on the observation of its current state. However, in the real-world applications, it is often infeasible to conduct a timely and yet comprehensive observation due to resource constraints. In view of such a practical challenge, the goal of this work is to develop a novel computational method for performing active observations, termed active surveillance, with limited resources. Specifically, we aim to predict the dynamics of a large spatio-temporal diffusion system based on the observations of some of its components. Towards this end, we introduce a novel measure, the γ value, that enables us to identify the key components by means of modeling a sentinel network with a row sparsity structure. Having obtained a theoretical understanding of the γ value, we design a backward-selection sentinel network mining algorithm (SNMA) for deriving the sentinel network via group sparse Bayesian learning. In order to be practically useful, we further address the issue of scalability in the computation of SNMA, and moreover, extend SNMA to the case of a non-linear dynamical system that could involve complex diffusion mechanisms. We show the effectiveness of SNMA by validating it using both synthetic datasets and five real-world datasets. The experimental results are appealing, which demonstrate that SNMA readily outperforms the state-of-the-art methods.

Next Generation Technology for Epidemic Prevention and Control: Data-Driven Contact Tracking.

Contact tracking is one of the key technologies in prevention and control of infectious diseases. In the face of a sudden infectious disease outbreak, contact tracking systems can help medical professionals quickly locate and isolate infected persons and high-risk individuals, preventing further spread and a large-scale outbreak of infectious disease. Furthermore, the transmission networks of infectious diseases established using contact tracking technology can aid in the visualization of actual virus transmission paths, which enables simulations and predictions of the transmission process, assessment of the outbreak trend, and further development and deployment of more effective prevention and control strategies. Exploring effective contact tracking methods will be significant. Governments, academics, and industries have all given extensive attention to this goal. In this paper, we review the developments and challenges of current contact tracing technologies regarding individual and group contact from both static and dynamic perspectives, including static individual contact tracing, dynamic individual contact tracing, static group contact tracing, and dynamic group contact tracing. With the purpose of providing useful reference and inspiration for researchers and practitioners in related fields, directions in multi-view contact tracing, multi-scale contact tracing, and AI-based contact tracing are provided for next-generation technologies for epidemic prevention and control.

Characterizing and Discovering Spatiotemporal Social Contact Patterns for Healthcare.

During an epidemic, the spatial, temporal and demographic patterns of disease transmission are determined by multiple factors. In addition to the physiological properties of the pathogens and hosts, the social contact of the host population, which characterizes the reciprocal exposures of individuals to infection according to their demographic structure and various social activities, are also pivotal to understanding and predicting the prevalence of infectious diseases. How social contact is measured will affect the extent to which we can forecast the dynamics of infections in the real world. Most current work focuses on modeling the spatial patterns of static social contact. In this work, we use a novel perspective to address the problem of how to characterize and measure dynamic social contact during an epidemic. We propose an epidemic-model-based tensor deconvolution framework in which the spatiotemporal patterns of social contact are represented by the factors of the tensors. These factors can be discovered using a tensor deconvolution procedure with the integration of epidemic models based on rich types of data, mainly heterogeneous outbreak surveillance data, socio-demographic census data and physiological data from medical reports. Using reproduction models that include SIR/SIS/SEIR/SEIS models as case studies, the efficacy and applications of the proposed framework are theoretically analyzed, empirically validated and demonstrated through a set of rigorous experiments using both synthetic and real-world data.

[Effects of organic manure on wheat growth under lead stress].

A pot experiment was conducted to study the effects of organic manure on the wheat growth under different levels of lead stress. With increasing lead stress level, whether fertilization or not, the plant height, shoot dry mass, adventitious root number, root total length, root dry mass, root activity, root total and active absorbing area, and root SOD and POD activities decreased, and root MDA content presented an increasing trend. The decrement of the above-mentioned parameters differed with fertilization treatments. Applying organic manure mitigated the impact of lead stress on wheat growth to some extent, delayed the senescence of wheat roots, and promoted root development and growth, ultimately leading to the increase of wheat yield and the decrease of lead content in grain.