Search

Image restoration is the task of aiming to obtain a high-quality image from a corrupt input image, such as deblurring and deraining. In image restoration, it is typically necessary to maintain a complex balance between spatial details and contextual information. Although a multi-stage network can optimally balance these competing goals and achieve significant performance, this also increases the system's complexity. In this paper, we propose a mountain-shaped single-stage design, which achieves the performance of multi-stage networks through a plug-and-play feature fusion middleware. Specifically, we propose a plug-and-play feature fusion middleware mechanism as an information exchange component between the encoder-decoder architectural levels. It seamlessly integrates upper-layer information into the adjacent lower layer, sequentially down to the lowest layer. Finally, all information is fused into the original image resolution manipulation level. This preserves spatial details and integrates contextual information, ensuring high-quality image restoration. Simultaneously, we propose a multi-head attention middle block as a bridge between the encoder and decoder to capture more global information and surpass the limitations of the receptive field of CNNs. In order to achieve low system complexity, we removes or replaces unnecessary nonlinear activation functions. Extensive experiments demonstrate that our approach, named as M3SNet, outperforms previous state-of-the-art models while using less than half the computational costs, for several image restoration tasks, such as image deraining and deblurring. The code and the pre-trained models will be released at https://github.com/Tombs98/M3SNet. [ABSTRACT FROM AUTHOR]

Recently, mashup developers seek to integrate multiple services with complementary functionalities from a large amount of web services. With so many available web services, it is difficult for developers to choose the right one to develop new mashups. Therefore, it is critical to create and recommend appropriate web services for mashup developers based on their development needs. In the past, various deep models have been proposed to facilitate web service recommendation based on semantic matching of textual descriptions. However, existing deep approaches mainly match global semantic representations while ignoring descriptive structure and tag information. In this paper, we propose a multi-representation web service recommendation model, which simultaneously extracts global, local and tag representations of the description and tag information, respectively. Moreover, we propose a tag-driven attention mechanism to guide the process of information extraction. Experiments over a real-world dataset demonstrate that our proposed service recommendation algorithm can achieve remarkable performance. [ABSTRACT FROM AUTHOR]

The estimation of spacecraft pose is crucial in numerous space missions, including rendezvous and docking, debris removal, and on-orbit maintenance. Estimating the pose of space objects is significantly more challenging than that of objects on Earth, primarily due to the widely varying lighting conditions, low resolution, and limited amount of data available in space images. Our main proposal is a new deep learning neural network architecture, which can effectively extract orbiting spacecraft features from images captured by inverse synthetic aperture radar (ISAR) for pose estimation of non-cooperative on orbit spacecraft. Specifically, our model enhances spacecraft imaging by improving image contrast, reducing noise, and using transfer learning to mitigate data sparsity issues via a pre-trained model. To address sparse features in spacecraft imaging, we propose a dense residual U-Net network that employs dense residual block to reduce feature loss during downsampling. Additionally, we introduce a multi-head self-attention block to capture more global information and improve the model's accuracy. The resulting tightly interlinked architecture, named as SU-Net, delivers strong performance gains on pose estimation by spacecraft ISAR imaging. Experimental results show that we achieve the state of the art results, and the absolute error of our model is 0.128 ∘ to 0.4491 ∘ , the mean error is about 0.282 ∘ , and the standard deviation is about 0.065 ∘ . The code are released at https://github.com/Tombs98/SU-Net. [ABSTRACT FROM AUTHOR]

Information Extraction (IE) in Natural Language Processing (NLP) aims to extract structured information from unstructured text to assist a computer in understanding natural language. Machine learning-based IE methods bring more intelligence and possibilities but require an extensive and accurate labeled corpus. In the materials science domain, giving reliable labels is a laborious task that requires the efforts of many professionals. To reduce manual intervention and automatically generate materials corpus during IE, in this work, we propose a semi-supervised IE framework for materials via automatically generated corpus. Taking the superalloy data extraction in our previous work as an example, the proposed framework using Snorkel automatically labels the corpus containing property values. Then Ordered Neurons-Long Short-Term Memory (ON-LSTM) network is adopted to train an information extraction model on the generated corpus. The experimental results show that the F1-score of γ' solvus temperature, density and solidus temperature of superalloys are 83.90%, 94.02%, 89.27%, respectively. Furthermore, we conduct similar experiments on other materials, the experimental results show that the proposed framework is universal in the field of materials. [ABSTRACT FROM AUTHOR]

Data provides a foundation for machine learning, which has accelerated data-driven materials design. The scientific literature contains a large amount of high-quality, reliable data, and automatically extracting data from the literature continues to be a challenge. We propose a natural language processing pipeline to capture both chemical composition and property data that allows analysis and prediction of superalloys. Within 3 h, 2531 records with both composition and property are extracted from 14,425 articles, covering γ′ solvus temperature, density, solidus, and liquidus temperatures. A data-driven model for γ′ solvus temperature is built to predict unexplored Co-based superalloys with high γ′ solvus temperatures within a relative error of 0.81%. We test the predictions via synthesis and characterization of three alloys. A web-based toolkit as an online open-source platform is provided and expected to serve as the basis for a general method to search for targeted materials using data extracted from the literature. [ABSTRACT FROM AUTHOR]

Web services are products in the era of service-oriented computing and cloud computing. Considering the information overload problem arising from the task of selecting web services, a recommendation system is by far the most effective solution for performing such selections. However, users calling a limited number of services will cause severe data sparseness and a weak correlation with services. In addition, fully mining the semantic features and knowledge features of the text description is also a major problem that needs to be solved urgently. This paper proposes a deep knowledge-aware approach which introduces knowledge graph and knowledge representation into web service recommendation for the first time. We solve the data sparse problem and optimize the user's feature representation. In this approach, an attention module is introduced to model the impact of tags for the candidate services on different words of user queries, and a deep neural network is used to model the high-level features of user-service invocation behaviors. The results of experiments demonstrate that the proposed approach can achieve better recommendation performance than other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Named entity recognition (NER) is the basis for many natural language processing (NLP) tasks such as information extraction and question answering. The accuracy of the NER directly affects the results of downstream tasks. Most of the relevant methods are implemented using neural networks, however, the word vectors obtained from a small data set cannot describe unusual, previously-unseen entities accurately and the results are not sufficiently accurate. Recently, the use of XLNet as a new pre-trained model has yielded satisfactory results in many NLP tasks, integration of XLNet embeddings in existent NLP tasks is not straightforward. In this paper, a new neural network model is proposed to improve the effectiveness of the NER by using a pre-trained XLNet, bi-directional long-short term memory (Bi-LSTM) and conditional random field (CRF). Pre-trained XLNet model is used to extract sentence features, then the classic NER neural network model is combined with the obtained features. In addition, the superiority of XLNet in NER tasks is demonstrated. We evaluate our model on the CoNLL-2003 English dataset and WNUT-2017 and show that the XLNet-BiLSTM-CRF obtains state-of-the-art results. [ABSTRACT FROM AUTHOR]

Natural language question answering over knowledge graph has received widespread attention. However, the existing methods always aim to improve every phase of natural language question answering and neglect the defects; namely, not all query intentions can be identified and mapped to the correct SPARQL statement. In contrast, keyword search relies on the links among multiple keywords regardless of the exact logic relations in question. Therefore, we propose a framework (abbreviated as NLQSK for title of this paper) that introduces keyword search into natural language question answering to compensate for the defects mentioned above. First, we translate a natural language question into top-k SPARQL statements by using the existing methods. Second, we transform the valuable information that cannot be identified and mapped into keywords, and then, return the neighboring information in a knowledge graph by keyword index. Third, we combine the SPARQL block (i.e., the SPARQL statement and its result) and keyword search to produce the answer to the natural language question. Finally, the experiments on the benchmark dataset confirm that keyword search can compensate for the defects of natural language question answering and that NLQSK can answer more questions than the existing state-of-the-art question answering systems. [ABSTRACT FROM AUTHOR]