When ground base stations are not available in the aftermath of a disaster, unmanned aerial vehicle (UAV) acting as flying relay is a promising option. The UAVs with limited energy as flying relays allow for wider data coverage and more stable data transmission. However, with the changes of ground devices topology and channel, it is challenging to consider quality of service (QoS) and the age of information (AoI) in UAV communication under the energy constraint. In this paper, we propose a dynamic priority packet scheduling for UAV assisted AoI-aware network whose utility is maximized subject to QoS to get the best tradeoff of the energy consumption and the weighted AoI. Specifically, the dynamics of devices are characterized by Gauss-Markov mobility model. Dynamic priority is affected by devices' movement, channel changes and others. We optimize the trajectory of the UAV and the scheduling scheme of the packets by the Dueling Double Deep Q Network (D3QN) algorithm. Simulations show that the scheme significantly improves the utility of the system compared to the benchmarks.

Unmanned aerial vehicles (UAVs) have shown great potential in live video streaming applications, especially in surveillance and reconnaissance. However, ensuring high quality of service (QoS) remains a challenge due to the dynamic nature of wireless channels. In this paper, we tackle the crucial challenge of energy-efficient and secure UAV-enabled live video streaming. To maximize long-term energy efficiency, we propose a cross-layer optimization framework that coordinates the adjustment of video coding parameters, wireless resource allocation, and UAV trajectory planning. We formulate the joint optimization as a constrained Markov decision process (CMDP) to capture the complex interdependencies between video quality, energy usage, and security risks. We introduce a new performance metric that captures the trade-off between video quality and energy consumption. The core of our method is a customized first-order constrained policy optimization, which efficiently handle complex real-world constraints like UAV battery capacities and end-to-end transmission delays. Our approach achieves scalability and sample efficiency with minimal gradient information. Through extensive system modeling and simulations under various network conditions, we validate the effectiveness of the proposed method compared with existing reinforcement learning algorithms.

Autostereoscopic display technology, despite decades of development, has not achieved extensive application, primarily due to the daunting challenge of three-dimensional (3D) content creation for non-specialists. The emergence of Radiance Field as an innovative 3D representation has markedly revolutionized the domains of 3D reconstruction and generation, simplifying 3D content creation for common users and broadening the applicability of Light Field Displays (LFDs). However, the combination of these two technologies remains largely unexplored. The standard paradigm to create optimal content for parallax-based light field displays demands rendering at least 45 slightly shifted views preferably at high resolution per frame, a substantial hurdle for real-time rendering. We introduce DirectL, a novel rendering paradigm for Radiance Fields on autostereoscopic displays with lenticular lens. By thoroughly analyzing the interleaved mapping of spatial rays to screen sub-pixels, we accurately render only the light rays entering the human eye and propose subpixel repurposing to significantly reduce the pixel count required for rendering. Tailored for the two predominant radiance fields---Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS), we propose corresponding optimized rendering pipelines that directly render the light field images instead of multi-view images, achieving state-of-the-art rendering speeds on autostereoscopic displays. Extensive experiments across various autostereoscopic displays and user visual perception assessments demonstrate that DirectL accelerates rendering by up to 40 times compared to the standard paradigm without sacrificing visual quality. Its rendering process-only modification allows seamless integration into subsequent radiance field tasks. Finally, we incorporate DirectL into diverse applications, showcasing the stunning visual experiences and the synergy between Light Field Displays and Radiance Fields, which reveals the immense potential for application prospects. DirectL Project Homepage: direct-l.github.io

Removing degradation from document images not only improves their visual quality and readability, but also enhances the performance of numerous automated document analysis and recognition tasks. However, existing regression-based methods optimized for pixel-level distortion reduction tend to suffer from significant loss of high-frequency information, leading to distorted and blurred text edges. To compensate for this major deficiency, we propose DocDiff, the first diffusion-based framework specifically designed for diverse challenging document enhancement problems, including document deblurring, denoising, and removal of watermarks and seals. DocDiff consists of two modules: the Coarse Predictor (CP), which is responsible for recovering the primary low-frequency content, and the High-Frequency Residual Refinement (HRR) module, which adopts the diffusion models to predict the residual (high-frequency information, including text edges), between the ground-truth and the CP-predicted image. DocDiff is a compact and computationally efficient model that benefits from a well-designed network architecture, an optimized training loss objective, and a deterministic sampling process with short time steps. Extensive experiments demonstrate that DocDiff achieves state-of-the-art (SOTA) performance on multiple benchmark datasets, and can significantly enhance the readability and recognizability of degraded document images. Furthermore, our proposed HRR module in pre-trained DocDiff is plug-and-play and ready-to-use, with only 4.17M parameters. It greatly sharpens the text edges generated by SOTA deblurring methods without additional joint training. Available codes: https://github.com/Royalvice/DocDiff https://github.com/Royalvice/DocDiff.

Deep learning models such as convolutional neural networks and recurrent networks are widely applied in text classification. In spite of their great success, most deep learning models neglect the importance of modeling context information, which is crucial to understanding texts. In this work, we propose the Adaptive Region Embedding to learn context representation to improve text classification. Specifically, a metanetwork is learned to generate a context matrix for each region, and each word interacts with its corresponding context matrix to produce the regional representation for further classification. Compared to previous models that are designed to capture context information, our model contains less parameters and is more flexible. We extensively evaluate our method on 8 benchmark datasets for text classification. The experimental results prove that our method achieves state-of-the-art performances and effectively avoids word ambiguity.

Convolutional neural network (CNN) has been successfully applied to many fields, such as image classification and object detection. It relies on huge amount of data. However, labelling a large amount of data is expensive. Active learning is one of the approaches to alleviate the labelling effort. We propose a new active learning approach for CNN. Different from existing active learning algorithms for CNN, first, the active query strategy is measured from multiple views, not only the last output of CNN; second, multiple views are obtained from multiple hidden layers in CNN, not from other related data or models. We evaluate our approach on three widely used datasets: Fashion-MNIST, SVHN and CIFAR-10. Experimental results show that the proposed method outperforms baseline methods in image classification.

Deep structure has been widely applied in a large variety of fields for its excellence of representing data. Attributes are a unique type of data descriptions that have been successfully utilized in numerous tasks to enhance performance. However, to introduce attributes into deep structure is complicated and challenging, because different layers in deep structure accommodate features of different abstraction levels, while different attributes may naturally represent the data in different abstraction levels. This demands adaptively and jointly modeling of attributes and deep structure by carefully examining their relationship. Different from existing works that treat attributes straightforwardly as the same level without considering their abstraction levels, we can make better use of attributes in deep structure by properly connecting them. In this paper, we move forward along this new direction by proposing a deep structure named Attribute Gated Deep Belief Network (AG-DBN) that includes a tunable attribute-layer gating mechanism and automatically learns the best way of connecting attributes to appropriate hidden layers. Experimental results on a manually-labeled subset of ImageNet, a-Yahoo and a-Pascal data set justify the superiority of AG-DBN against several baselines including CNN model and other AG-DBN variants. Specifically, it outperforms the CNN model, VGG19, by significantly reducing the classification error from 26.70% to 13.56% on a-Pascal.

A commercial Web page typically contains many information blocks. Apart from the main content blocks, it usually has such blocks as navigation panels, copyright and privacy notices, and advertisements (for business purposes and for easy user access). We call these blocks that are not the main content blocks of the page the noisy blocks. We show that the information contained in these noisy blocks can seriously harm Web data mining. Eliminating these noises is thus of great importance. In this paper, we propose a noise elimination technique based on the following observation: In a given Web site, noisy blocks usually share some common contents and presentation styles, while the main content blocks of the pages are often diverse in their actual contents and/or presentation styles. Based on this observation, we propose a tree structure, called Style Tree, to capture the common presentation styles and the actual contents of the pages in a given Web site. By sampling the pages of the site, a Style Tree can be built for the site, which we call the Site Style Tree (SST). We then introduce an information based measure to determine which parts of the SST represent noises and which parts represent the main contents of the site. The SST is employed to detect and eliminate noises in any Web page of the site by mapping this page to the SST. The proposed technique is evaluated with two data mining tasks, Web page clustering and classification. Experimental results show that our noise elimination technique is able to improve the mining results significantly.

Frequent substructure discovery from a collection of semi-structured objects can serve for storage, browsing, querying, indexing and classification of semi-structured documents. This paper examines the problem of discovering frequent substructures from a collection of hierarchical semi-structured objects of the same type. The use of wildcard is an important aspect of substructure discovery from semi-structured data due to the irregularity and lack of fixed structure of such data. This paper proposes a more general and powerful wildcard mechanism, which allows us to find more complex and interesting substructures than existing techniques. Furthermore, the complexity of structural information of semi-structured data and the usage of wildcard make the existing frequent set mining algorithms inapplicable for substructure discovery. In this work, we adopt a vertical format for the storage of semi-structured objects, and adapt a frequent set mining algorithm for our purpose. The application of our approach to real-life data shows that it is very effective.

The Web is increasingly becoming an important channel for conducting businesses, disseminating information, and communicating with people on a global scale. More and more companies, organizations, and individuals are publishing their information on the Web. With all this information publicly available, naturally companies and individuals want to find useful information from these Web pages. As an example, companies always want to know what their competitors are doing and what products and services they are offering. Knowing such information, the companies can learn from their competitors and/or design countermeasures to improve their own competitiveness. The ability to effectively find such business intelligence information is increasingly becoming crucial to the survival and growth of any company. Despite its importance, little work has been done in this area. In this paper, we propose a novel visualization technique to help the user find useful information from his/her competitors' Web site easily and quickly. It involves visualizing (with the help of a clustering system) the comparison of the user's Web site and the competitor's Web site to find similarities and differences between the sites. The visualization is such that with a single glance, the user is able to see the key similarities and differences of the two sites. He/she can then quickly focus on those interesting clusters and pages to browse the details. Experiment results and practical applications show that the technique is effective.