ABSTRACT Green metals are an important type of geoscience resource and also essential components for building a clean energy future. However, their substantial price fluctuations make accurate price forecasting a crucial decision‐making enabler for energy transitions. Previous studies have paid limited attention to the adaptive selection of effective subseries‐level predictors. Consequently, this paper develops a novel multi‐objective ensemble system with an adaptive selection mechanism for geoscience resource market management, called DPBPAPSME. Four modules are designed in DPBPAPSME. Specifically, the data preprocessing module reduces the negative impact of noise and modeling complexity of the original time series. The basic predictor module introduces four different artificial intelligence models to overcome the shortcomings of using a specific predictor. The adaptive predictor selection module overcomes the limitations of traditional subjective and objective indicator selection, adaptively identifies effective predictors, and improves the prediction precision and robustness. Furthermore, a multi‐objective ensemble module optimizes and adjusts the weight coefficients of the predictors of the selected subseries and fully integrates the complementary forecasting information provided by the selected predictors. Three green metals, platinum, zinc, and copper, were used in the main experiments, and an additional gold dataset was employed to examine the generalizability of the proposed system. The mean absolute percentage errors of DPBPAPSME on the three datasets were 0.161292%, 0.143030%, and 0.091245%, respectively. The results indicate that the proposed DPBPAPSME system is a promising tool for the management of the geoscience resource market.

Human emotional states in real life are varied and complex. It is difficult for existing methods to capture robust facial expression features dynamically, especially in a large head pose and occlusion. In this paper, a novel end-to-end graph-guided spatiotemporal convolutional network (GSTCN) is proposed to achieve frame-level facial affect analysis. The GSTCN utilizes graph structure to model face images with missing data and extracts spatial and temporal information of expression sequences. Moreover, a trajectory oscillating coefficient algorithm is designed to evaluate the motion of facial landmarks and help GSTCN adaptively build the graph structures of the most representative facial regions according to the dynamical emotion features, effectively improving the robustness of human affect analysis in the wild. The proposed method is evaluated on two large-scale databases, Aff-Wild2 and AFEW-VA. The experimental results demonstrate the superiority of the proposed method over the state-of-the-art approaches.

Abstract Human pose estimation is an important task in computer vision, which can provide key point detection of human body and obtain bone information. At present, human pose estimation is mainly utilized for detection of large targets, and there is no solution for detection of small targets. This paper proposes a multi-channel spatial information feature based human pose (MCSF-Pose) estimation algorithm to address the issue of medium and small targets inaccurate detection of human key points in scenarios involving occlusion and multiple poses. The MCSF-Pose network is a bottom-up regression network. Firstly, an UP-Focus module is designed to expand the feature information while reducing parameter computation during the up-sampling process. Then, the channel segmentation strategy is adopted to cut the features, and the feature information of multiple dimensions is retained through different convolutional groups, which reduces the parameter lightweight network model and makes up for the loss of the feature information associated with the depth of the network. Finally, the three-layer PANet structure is designed to reduce the complexity of the model. With the aid of the structure, it also to improve the detection accuracy and anti-interference ability of human key points. The experimental results indicate that the proposed algorithm outperforms YOLO-Pose and other human pose estimation algorithms on COCO2017 and MPII human pose datasets.

People tend to focus on changes in a certain complex human affect in the majority of practical applications of affective computing. Facial expression classification models are unable to represent all human affects through a limited number of expression categories. In this backdrop, this paper studies the Sequence-level affective level estimation (S-ALE), which is more relevant to real scenarios and can depict individual affective level in continuous manner. A spatio-temporal framework applied to S-ALE is proposed, which consists of a Facial Expression Features Pyramid Network (FEFPN) and a Temporal Transformer Encoder (TTE). FEFPN is capable of extracting pyramidal facial expression features, while TTE can effectively capture coarse-grained and fine-grained temporal variations of facial sequences. The proposed model is evaluated on six public datasets across three typical S-ALE tasks (engagement prediction, fatigue detection, and pain assessment), and experimental results show that our method is comparable to or outperforms the state-of-the-art algorithms.

Recently, controlling air pollution has become increasingly significant due to its impact on our health and daily lives. To prevent and control pollution, it is crucial to trace its source. Many researches have been developed for tracing the source of pollution. However, traditional methods using large-scale simulations need a large number of computation resources and time-consuming. In addition, traditional traceability algorithms do not consider topographic factors, which can cause a certain amount of errors. To resolve above problems, an interactive visual analytics system for pollutant traceability is proposed. In our method, instead of three-dimensional field data, only two-dimensional grid data is enough to track pollution sources in real time. Furthermore, our method can further improve precision through considering topographic factors, which are usually ignored by existing methods. Finally, the possible pollution sources are also identified in our method. This is achieved through analysis of changes in pollutant concentration and the distribution of man-made emission sources. In order to verify the effectiveness of this method, we propose a series of application examples to comprehensively analyze the sources of pollutants.

Abstract In recent years, researchers have made significant contributions to 3D face reconstruction with the rapid development of deep learning. However, learning-based methods often suffer from time and memory consumption. Simply removing network layers hardly solves the problem. In this study, we propose a solution that achieves fast and robust 3D face reconstruction from a single image without the need for accurate 3D data for training. In terms of increasing speed, we use a lightweight network as a facial feature extractor. As a result, our method reduces the reliance on graphics processing units, allowing fast inference on central processing units alone. To maintain robustness, we combine an attention mechanism and a graph convolutional network in parameter regression to concentrate on facial details. We experiment with different combinations of three loss functions to obtain the best results. In comparative experiments, we evaluate the performance of the proposed method and state-of-the-art methods on 3D face reconstruction and sparse face alignment, respectively. Experiments on a variety of datasets validate the effectiveness of our method.

Visual relationship recognition is essential for deeper scene understanding. It poses to recognize 〈subject-predicate-object〉 triplets between object pairs. Previous methods usually treat vastly different predicates equally and neglect the subtle differences between predicates. In this paper, we propose a novel and concise perspective called "predicate-aware learning network (PAL-Net)" for visual relationship recognition. "Predicate-aware" means that we take predicates as a condition in a task-driven manner. Our PAL-Net consists of two key modules: i) a predicate-guided regularization module designed to learn more differentiated representations for various predicates; ii) a predicate-aware contextual modeling module to integrate the efficacy of contextual objects for different predicates respectively. Extensive experiments on VRD and Visual Genome dataset yield remarkable performance gains, verifying the effectiveness of PAL-Net. Besides, PAL-Net also shows good applicability and achieves substantial improvement for human-object interaction detection.

In this paper, we present a stripmap-mode raw data generator that accounts for trajectory deviations and antenna pointing errors with a nonzero squint angle for an extended scene, which is more realistic for airborne SAR system. The raw data acquired under the acquisition Doppler (AD) geometry rather than a standard cylindrical reference system. The approach utilizes one-dimensional azimuth Fourier domain processing followed by range time-domain integration. It has a higher computationally efficiency than the time domain method. Some simulation results are finally presented to demonstrate the effectiveness of the proposed algorithm.

Snow cover in cold and arid regions is a key factor controlling regional energy balances, the hydrological cycle, and water utilization. Optical remote sensing data offer an effective means of mapping snow cover, although their application is limited by solar illumination conditions, conversely, SAR technology offers the ability to measure snow wetness changes in all weather. In the present study, a new approach using combined SAR and optical data has been developed for dry and wet snow cover recognition in mountain areas. In this method, RadarSat-2 interferometric coherence images and backscattering coefficient images are analyzed, adopting snow-covered and snow-free areas obtained from GF-1 satellite observations as the “ground truth”, a dynamic thresholding algorithm was used to identify snow cover using interferometric coherence and local incidence angle images, and polarimetric target decomposition method was used to classify dry and wet snow cover. The classification results demonstrate that dry and wet snow cover extraction using this method can achieve 93.5% in snow-melt period.

The industrial information grid is a special kind of system, the users of which exclusively own geographically distributed computing resources for business service, and try to maintain the lowest total cost of ownership while guaranteeing quality of service. In this paper, we classify the industrial information grid as an extension to grid problem; develop a unified management framework for new management paradigm, which supports the distribution of administration labor and collaboration of system administrator at different locations; propose a self-organizing algorithm, which supports the initial establishment, daily management and exception processing of industrial information grid. Finally, we evaluate the performance of system management, and analyze the management overhead with this new management paradigm.