Image restoration aims to recover high-quality images from their corrupted counterparts. Many existing methods focus on the spatial domain while overlooking frequency variations between sharp/degraded image pairs. Meanwhile, they typically establish skip connections between encoder and decoder features using addition or concatenation to enhance image restoration. However, since encoder features may contain degradation factors, this approach can inadvertently introduce implicit noise. In this paper, we introduce a multi-scale frequency selection network (MFSNet) that seamlessly integrates spatial and frequency domain knowledge, selectively recovering richer and more accurate information. Specifically, we initially capture spatial features and input them into dynamic filter selection modules (DFS) at different scales to integrate frequency knowledge. DFS utilizes learnable filters to generate high and low-frequency information and a frequency cross-attention mechanism (FCAM) to determine the most information to recover. To learn a multi-scale and accurate set of hybrid features, we develop a skip feature fusion block (SFF) that leverages contextual features to discriminatively determine which information should be propagated in skip-connections. It is worth noting that our DFS and SFF are generic plug-in modules that can be directly employed in existing networks without any adjustments, leading to performance improvements. Extensive experiments across various image restoration tasks demonstrate that our MFSNet achieves performance that is either superior or comparable to state-of-the-art algorithms. The code and the pre-trained models are released athttps://github.com/Tombs98/MFSNet_.

Document-level relation extraction (RE) aims to determine the relations between entities scattered across different sentences through reading and reasoning. Existing methods use semantic segmentation to obtain global information among triples by analyzing entity-level matrices. However, complete document input may introduce certain interference, making it challenging to express the underlying relationships. To address this, we propose a novel approach introducing a low-entity redundancy feature map, achieved by removing certain entities. The proposed optimal path filtering (OPF) selects entity-related sentences using heuristic rules and formulates sentence selection as a set cover problem, solved via backtracking pruning. U-Net is then applied to obtain global features. Our experiment achieves state-of-the-art results on two common document-level RE datasets, Re-DocRED and CDR, outperforming previous methods.

Open Relation Extraction (OpenRE) is a task that involves discovering new relation types by referring to labeled instances. Existing methods mainly rely on large pre-trained models to obtain the relation representation of entity pairs, and then jointly train the supervised and unsupervised data using a joint loss function. Some researchers enhance their relation representation by introducing additional information as prompt. However, these approaches have several major issues. Firstly, many of them rely on external knowledge bases, which require a large amount of high-quality data. Secondly, They fail to consider the rich semantic and prior knowledge existing in the labels. To this end, we propose a novel method to incorporate the prior knowledge into prompt-tuning and introduce a multi-view algorithm to optimize the relation representations. We conduct experiments on two common datasets, and the results show that our proposed method significantly outperforms the previous state-of-the-art methods.

Image deblurring aims to restore a high-quality image from its corresponding blurred. The emergence of CNNs and Transformers has enabled significant progress. However, these methods often face the dilemma between eliminating long-range degradation perturbations and maintaining computational efficiency. While the selective state space model (SSM) shows promise in modeling long-range dependencies with linear complexity, it also encounters challenges such as local pixel forgetting and channel redundancy. To address this issue, we propose an efficient image deblurring network that leverages selective state spaces model to aggregate enriched and accurate features. Specifically, we introduce an aggregate local and global information block (ALGBlock) designed to effectively capture and integrate both local invariant properties and non-local information. The ALGBlock comprises two primary modules: a module for capturing local and global features (CLGF), and a feature aggregation module (FA). The CLGF module is composed of two branches: the global branch captures long-range dependency features via a selective state spaces model, while the local branch employs simplified channel attention to model local connectivity, thereby reducing local pixel forgetting and channel redundancy. In addition, we design a FA module to accentuate the local part by recalibrating the weight during the aggregation of the two branches for restoration. Experimental results demonstrate that the proposed method outperforms state-of-the-art approaches on widely used benchmarks.

Stereo image super-resolution (stereoSR) strives to improve the quality of super-resolution by leveraging the auxiliary information provided by another perspective. Most approaches concentrate on refining module design, and stacking massive network blocks to extract and integrate information. Although there have been advancements, the memory and computation costs are increasing as well. To tackle this issue, we propose a lattice structure that autonomously learns the optimal combination patterns of network blocks, which enables the efficient and precise acquisition of feature representations, and ultimately achieves lightweight stereoSR. Specifically, we draw inspiration from the lattice phase equalizer and design lattice stereo NAFBlock (LSNB) to bridge pairs of NAFBlocks using re-weight block (RWBlock) through a coupled butterfly-style topological structures. RWBlock empowers LSNB with the capability to explore various combination patterns of pairwise NAFBlocks by adaptive re-weighting of feature. Moreover, we propose a lattice stereo attention module (LSAM) to search and transfer the most relevant features from another view. The resulting tightly interlinked architecture, named as LSSR, extensive experiments demonstrate that our method performs competitively to the state-of-the-art.

Spacecraft Inverse Synthetic Aperture Radar (ISAR) imaging super-resolution aims to enhance the resolution of low-resolution images to produce high-resolution images. However, spacecraft ISAR imaging presents challenges such as sparse, fuzzy boundaries, and the intricate differentiation between background and spacecraft, rendering current methods less effective in achieving satisfactory super-resolution results. In this letter, we propose a sparse and selective feature fusion network for super-resolution spacecraft ISAR images. At the heart of our approach lies a multi-scale residual block featuring the following essential components: (a) parallel multi-resolution streams to extract multi-scale features, (b) trainable top-k selection operator that intelligently retains the most critical attention scores from the keys for each query, enhancing the distinction between background and spacecraft information within the local region, and (c) selective cross fusion to discriminatively determine which low-and high-scale information to retain when aggregating multi-scale features. The resulting tightly interlinked architecture, named as SSNet, learns a set of more accurate features. Extensive experiments on real ISAR images of spacecraft unequivocally illustrate the superior performance of the proposed method compared to state-of-the-art approaches, achieving an impressive 33.27dB. The code are released at https://github.com/Tombs98/SSNet.

Image restoration aims to recover the high-quality images from their degraded observations. Since most existing methods have been dedicated into single degradation removal, they may not yield optimal results on other types of degradations, which do not satisfy the applications in real world scenarios. In this paper, we propose a novel data ingredient-oriented approach that leverages prompt-based learning to enable a single model to efficiently tackle multiple image degradation tasks. Specifically, we utilize a encoder to capture features and introduce prompts with degradation-specific information to guide the decoder in adaptively recovering images affected by various degradations. In order to model the local invariant properties and non-local information for high-quality image restoration, we combine CNNs operations and Transformers. Simultaneously, we make several key designs in the Transformer blocks (multi-head rearranged attention with prompts and simple-gate feed-forward network) to reduce computational requirements and selectively determines what information should be persevered to facilitate efficient recovery of potentially sharp images. Furthermore, we incorporate a feature fusion mechanism further explores the multi-scale information to improve the aggregated features. The resulting tightly interlinked hierarchy architecture, named as CAPTNet, extensive experiments demonstrate that our method performs competitively to the state-of-the-art. The code and the pre-trained models are released at https://github.com/Tombs98/CAPTNet.

Inverse Synthetic Aperture Radar (ISAR) is a popular space object detection method. However, due to the complex flight conditions of spacecraft and limited observation time, the resolution of spacecraft ISAR images are reduced. Although there are many methods of ISAR image super resolution, but none of them aim at spacecraft. To this end, in this letter, we analyze the characteristics of spacecraft ISAR images, and firstly propose an approach Space Super Resolution Network(SSRN), suitable for spacecraft ISAR images. Specially, our approach is designed to utilize the repetitive structures commonly observed in spacecraft ISAR images. So we introduce Non-Local Sparse Attention(NLSA) to capture the long-distance self-similarity in the spacecraft ISAR image. Spherical Locality Sensitive Hashing is used to construct multiple attention buckets, and the query feature and features in the same and adjacent buckets are used for attention operations. In order to effectively extract multi-scale features and contrast features from spacecraft ISAR image, we design the Residual Atrous Spatial Pyramid Pooling block(ResASPPblock), connect a number of atrous convolution layers with different dilation rates, and add the skip connection. The experiment on the real ISAR image of a certain type spacecraft proves the effectiveness of our approach, and the performance of our approach is higher than the popular ISAR super resolution method. Overall, our approach provides a promising solution for improving the resolution of spacecraft ISAR images.

Previous answer aggregation methods for sentence-level crowdsourcing tasks extract one sentence from a collection of redundant sentences. However, these extractive methods have a drawback in that they ignore the phenomenon of answer complementarity and the spammer dilemma in crowdsourcing. To alleviate this problem, in this paper, we generate new, comprehensive sentences that synthesize all redundant sentences. To achieve this goal, we design a sequence-to-sequence neural model composed of an encoder and decoder. Specifically, considering the complementarity phenomenon, the encoder synthesizes all the collected sentences into hidden states, which are then utilized by the decoder to generate the final sentence. Next, considering the spammer dilemma, we model the workers in the neural network to detect spammers. Furthermore, to train the neural model better, we construct pseudo-sentences to enrich the training data. The experimental results demonstrate that our method can efficiently aggregate redundant sentences and generate comprehensive sentences with increased quality.

Meteorological hazards have great influence all over the world. An emergency plan is an important means of coping with meteorological hazards. The preparation of emergency plans needs to refer to historical emergency plans, but these are too numerous and are of uneven quality. We can alleviate thes e problems by means of recommender systems, which are very useful tools in many domains; however, they suffer from information overload. In this paper, we propose a Semantic-Aware Collaborative Filtering method, which is called SACF, for emergency plans recommendation to address the aforementioned challenges. It is designed to effectively present a highly targeted emergency plan recommendation list and recommend the most appropriate emergency plans for a targeted meteorological hazards event. Specifically, we use semantic knowledge to represent scenario-based meteorological hazards, including target and previous events. The search for similar events (i.e., neighbors) for a collaborative filtering recommendation algorithm is adopted. By helping to avoid both the generation of fake neighbors and also the omission of true neighbors the recommendation process is improved. Finally, extensive experiments are conducted on a real-world dataset, and the results demonstrate that SACF improves the accuracy of emergency plan recommendations.

Social networks have evolved into a popular information and communication platform, and the vast amount of data it generates are rapidly changing and spreading. Thus, it is essential to detect and trace large events and burst topics in mass social network data based on real-time Big Data parallel c omputing. In this paper, we propose a model that uses the Negative Binomial Distribution to fit the distribution of Weibo topic words. Then, we introduce the concepts of the ‘hot degree’ and the ‘dispersion degree’ of a topic with their corresponding computing methods. And we validate the efficiency of the model using real data. Furthermore, we design a topic detection and trend-tracing algorithm based on stream data, and implement the algorithm on Spark Streaming which is a streaming processing framework that uses memory computing. Finally, the experiments on real data demonstrate that our proposal is effective and efficient in tracking bursting events.

Crowdsourcing is a new emerging distributed computing and business model on the backdrop of Internet blossoming. With the development of crowdsourcing systems, the data size of crowdsourcers, contractors and tasks grows rapidly. The worker quality evaluation based on big data analysis technology has become a critical challenge. This paper first proposes a general worker quality evaluation algorithm that is applied to any critical tasks such as tagging, matching, filtering, categorization and many other emerging applications, without wasting resources. Second, we realize the evaluation algorithm in the Hadoop platform using the MapReduce parallel programming model. Finally, to effectively verify the accuracy and the effectiveness of the algorithm in a wide variety of big data scenarios, we conduct a series of experiments. The experimental results demonstrate that the proposed algorithm is accurate and effective. It has high computing performance and horizontal scalability. And it is suitable for large-scale worker quality evaluations in a big data environment.