Search

Given video streams, we aim to correctly detect unsegmented signs related to continuous sign language recognition (CSLR). Despite the increase in proposed deep learning methods in this area, most of them mainly focus on using only an RGB feature, either the full-frame image or details of hands and face. The scarcity of information for the CSLR training process heavily constrains the capability to learn multiple features using the video input frames. Moreover, exploiting all frames in a video for the CSLR task could lead to suboptimal performance since each frame contains a different level of information, including main features in the inferencing of noise. Therefore, we propose novel spatio-temporal continuous sign language recognition using the attentive multi-feature network to enhance CSLR by providing extra keypoint features. In addition, we exploit the attention layer in the spatial and temporal modules to simultaneously emphasize multiple important features. Experimental results from both CSLR datasets demonstrate that the proposed method achieves superior performance in comparison with current state-of-the-art methods by 0.76 and 20.56 for the WER score on CSL and PHOENIX datasets, respectively. [ABSTRACT FROM AUTHOR]

Due to the great advances in mobility techniques, an increasing number of point-of-interest (POI)-related services have emerged, which could help users to navigate or predict POIs that may be interesting. Obviously, predicting POIs is a challenging task, mainly because of the complicated sequential transition regularities, and the heterogeneity and sparsity of the collected trajectory data. Most prior studies on successive POI recommendation mainly focused on modeling the correlation among POIs based on users’ check-in data. However, given a user’s check-in sequence, generally, the relationship between two consecutive POIs is usually both time and distance subtle. In this article, we propose a novel POI recommendation system to capture and learn the complicated sequential transitions by incorporating time and distance irregularity. In addition, we propose a feasible way to dynamically weight the decay values into the model learning process. The learned awareness weights offer an easy-to-interpret way to translate how much each context is emphasized in the prediction process. The performance evaluations are conducted on real mobility datasets to demonstrate the effectiveness and practicability of the POI recommendations. The experimental results show that the proposed methods significantly outperform the state-of-the-art models in all metrics. [ABSTRACT FROM AUTHOR]

Mangroves are grown in intertidal zones along tropical and subtropical climate areas, which have many benefits for humans and ecosystems. The knowledge of mangrove conditions is essential to know the statuses of mangroves. Recently, satellite imagery has been widely used to generate mangrove and degradation mapping. Sentinel-2 is a volume of free satellite image data that has a temporal resolution of 5 days. When Hurricane Irma hit the southwest Florida coastal zone in 2017, it caused mangrove degradation. The relationship of satellite images between pre and post-hurricane events can provide a deeper understanding of the degraded mangrove areas that were affected by Hurricane Irma. This study proposed an MDPrePost-Net that considers images before and after hurricanes to classify non-mangrove, intact/healthy mangroves, and degraded mangroves classes affected by Hurricane Irma in southwest Florida using Sentinel-2 data. MDPrePost-Net is an end-to-end fully convolutional network (FCN) that consists of two main sub-models. The first sub-model is a pre-post deep feature extractor used to extract the spatial–spectral–temporal relationship between the pre, post, and mangrove conditions after the hurricane from the satellite images and the second sub-model is an FCN classifier as the classification part from extracted spatial–spectral–temporal deep features. Experimental results show that the accuracy and Intersection over Union (IoU) score by the proposed MDPrePost-Net for degraded mangrove are 98.25% and 96.82%, respectively. Based on the experimental results, MDPrePost-Net outperforms the state-of-the-art FCN models (e.g., U-Net, LinkNet, FPN, and FC-DenseNet) in terms of accuracy metrics. In addition, this study found that 26.64% (41,008.66 Ha) of the mangrove area was degraded due to Hurricane Irma along the southwest Florida coastal zone and the other 73.36% (112,924.70 Ha) mangrove area remained intact. [ABSTRACT FROM AUTHOR]

In this paper, a novel feature line embedding (FLE) algorithm based on support vector machine (SVM), referred to as SVMFLE, is proposed for dimension reduction (DR) and for improving the performance of the generative adversarial network (GAN) in hyperspectral image (HSI) classification. The GAN has successfully shown high discriminative capability in many applications. However, owing to the traditional linear-based principal component analysis (PCA) the pre-processing step in the GAN cannot effectively obtain nonlinear information; to overcome this problem, feature line embedding based on support vector machine (SVMFLE) was proposed. The proposed SVMFLE DR scheme is implemented through two stages. In the first scatter matrix calculation stage, FLE within-class scatter matrix, FLE between-scatter matrix, and support vector-based FLE between-class scatter matrix are obtained. Then in the second weight determination stage, the training sample dispersion indices versus the weight of SVM-based FLE between-class matrix are calculated to determine the best weight between-scatter matrices and obtain the final transformation matrix. Since the reduced feature space obtained by the SVMFLE scheme is much more representative and discriminative than that obtained using conventional schemes, the performance of the GAN in HSI classification is higher. The effectiveness of the proposed SVMFLE scheme with GAN or nearest neighbor (NN) classifiers was evaluated by comparing them with state-of-the-art methods and using three benchmark datasets. According to the experimental results, the performance of the proposed SVMFLE scheme with GAN or NN classifiers was higher than that of the state-of-the-art schemes in three performance indices. Accuracies of 96.3%, 89.2%, and 87.0% were obtained for the Salinas, Pavia University, and Indian Pines Site datasets, respectively. Similarly, this scheme with the NN classifier also achieves 89.8%, 86.0%, and 76.2% accuracy rates for these three datasets. [ABSTRACT FROM AUTHOR]

The widespread occurrences of airborne outbreaks (e.g., COVID-19) and pollution (e.g., PM2.5) have urged people in the affected regions to protect themselves by wearing face masks. In certain areas, wearing masks amidst such health-endangering times is even enforced by law. While most people wear masks to guard themselves against airborne substances, some exploit such excuses and use face masks to conceal their identity for criminal purposes such as shoplifting, robbery, drug transport, and assault. While automatic face recognition models have been proposed, most of these models aim to identify clear, unobstructed faces for authentication purposes and cannot effectively handle cases where masks cover most facial areas. To mitigate such a problem, this paper proposes a deep-learning-based feature-fusion framework, FIREC , that combines additional demographic-estimated features such as age, gender, and race into the underlying facial representation to compensate for the information lost due to mask obstruction. Given an image of a masked face, our system recommends a ranked list of potential identities of the person behind the mask. Empirical results show that the best configuration of our proposed framework can recognize bare faces and masked faces with the accuracy of 99.34% and 97.65% in terms of Hit@10, respectively. The proposed framework could greatly benefit high-recall facial identity recognition applications such as identifying potential suspects from CCTV or passers-by's cameras, especially during crisis times when people commonly cover their faces with protective masks., (© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022, Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.)

Ethereum, the second-largest cryptocurrency after Bitcoin, has attracted wide attention in the last few years and accumulated significant transaction records. However, the underlying Ethereum network structure is still relatively unexplored. Also, very few attempts have been made to perform link predictability on the Ethereum transactions network. This paper presents a Detailed Analysis of the Ethereum Network on Transaction Behavior, Community Structure, and Link Prediction (DANET) framework to investigate various valuable aspects of the Ethereum network. Specifically, we explore the change in wealth distribution and accumulation on Ethereum Featured Transactional Network (EFTN) and further study its community structure. We further hunt for a suitable link predictability model on EFTN by employing state-of-the-art Variational Graph Auto-Encoders. The link prediction experimental results demonstrate the superiority of outstanding prediction accuracy on Ethereum networks. Moreover, the statistic usages of the Ethereum network are visualized and summarized through the experiments allowing us to formulate conjectures on the current use of this technology and future development., Competing Interests: The authors declare there are no competing interests., (©2021 Said et al.)