Augmented displays (ADs), where AR extends the workspace of a physical display, are gaining momentum across productivity, visual analytics, and collaborative scenarios; yet, the field lacks a unified conceptual foundation. We present the first scoping survey on ADs, synthesizing 62 papers (2010-2024), including one earlier paper from 2005. From the corpus, we derive the AR-Display Spatial Integration Framework, capturing recurring patterns across AD systems along four core dimensions: extension type, AR content type, placement, and layout. We map existing systems across the framework to identify design patterns and translate them into recommendations. We further consolidate insights on development and evaluation practices, followed by a discussion on using the framework, AD applications, cross-cutting factors, and managing the complexity of AD systems. Our survey also outlines research gaps for advancing the field, particularly in the design space of AR-Display integration and the broader support and use of AD.

Crack segmentation is a pivotal task in assessing structural integrity across diverse domains, ranging from civil infrastructure such as bridges and buildings to the fabrication of heavy vehicles, which is crucial for ensuring the longevity and safety of materials. Despite its critical importance, the domain remains relatively underexplored within the academic sphere, particularly in accommodating the crack segmentation on resource-constrained devices. This challenge arises due to the inherent demand for deeper and broader network structures to achieve optimal performance, resulting in heavier computational and storage overhead. Thus, deploying crack segmentation models on practical platforms poses a formidable challenge. This paper presents a novel lightweight hybrid framework comprising robust Attention UNet architecture to assimilate comprehensive contextual information alongside the efficient MobileVit block to extract and integrate global contextual information utilizing the intricate self-attention mechanism. The intensive experiment results illustrate that our proposed method outperforms the existing state-of-the-art methods on the public benchmark datasets despite employing a reduced parameter space. The dataset and code can be accessed at: https://github.com/REINS-SJTU/TransAUnet

Software systems are increasingly relying on deep learning components, due to their remarkable capability of identifying complex data patterns and powering intelligent behaviour. A core enabler of this change in software development is the availability of easy-to-use deep learning libraries. Libraries like PyTorch and TensorFlow empower a large variety of intelligent systems, offering a multitude of algorithms and configuration options, applicable to numerous domains of systems. However, bugs in those popular deep learning libraries also may have dire consequences for the quality of systems they enable; thus, it is important to understand how bugs are identified and fixed in those libraries.Inspired by a study of Jia et al., which investigates the bug identification and fixing process at TensorFlow, we characterize bugs in the PyTorch library, a very popular deep learning framework. We investigate the causes and symptoms of bugs identified during PyTorch’s development, and assess their locality within the project, and extract patterns of bug fixes. Our results highlight that PyTorch bugs are more like traditional software projects bugs, than related to deep learning characteristics. Finally, we also compare our results with the study on TensorFlow, highlighting similarities and differences across the bug identification and fixing process.

Hand actions classification is an imperative field for acquiring smart functionality in modern electronic devices because hand actions classification offers interactive and innovative methods to communicate and interact. Therefore, we develop a novel architecture based on you only looking at coefficients (YOLACT), a real-time instance segmentation approach, and a temporal relation network (TRN) for hand actions understanding. In addition, our framework consists of a face recognition-based security network (FRB-SN) for user identification. We trained the YOLACT and the TRN models using the segmented version of the 20BN jester dataset composed of hand actions images and ground truths while the FRB-SN is trained using the VGGFace2 dataset. For testing, the YOLACT is used to segment the object from the given image sequence and then passed to the TRN-trained model to predict the corresponding action. Our experimental results showed that the accuracy and frame rate of the proposed framework are competitive.

Human action recognition (HAR) is a popular topic in developing a visual analysis system because of its tremendous potential in autonomous visual analysis. However, visual analysis is a sophisticated field in computer vision because an image sequence consists of various features that do not belong to a specific action. Therefore, we present a novel architecture approach for human action recognition and localization. We dubbed it DTA, an abbreviation of the detect, track, and analyze. It is inspired by yolov3, deep-sort, and 3D convolutional neural networks. Our framework is compact in analyzing human action, and the results showed that the proposed method outperforms previous state-of-the-art methods in various aspects. Moreover, the action recognition model is developed, trained, and tested using the ROI version of the KTH dataset. The experimental results showed the accuracy of the proposed model is superior compared to other traditional methods.

Abstract Deep learning has assisted the field of single‐image super‐resolution (SR) in achieving new heights. However, the task of restoring a high‐resolution (HR) image from a highly degraded low‐resolution (LR) image is sophisticated due to poor image restoration quality. A novel and effective lightweight SR method is presented as super‐resolution via an enhanced feature block network (SREFBN) that successfully reconstructs an HR image using a corresponding LR image with a purposed deep residual block. In addition, a novel shared parameters approach in the top‐down pathway among low‐level feature maps is introduced. The experimental results prove that SREFBN achieves remarkable performance. The presented framework requires lower computational cost and outperforms many state‐of‐the‐art methods. It is also highly adaptable with low‐end devices, requiring lower multiplication and adding operations. A trade‐off comparison between the number of parameters, execution time, and accuracies is given while also showing different variations of our approach to prove the effectiveness and reliability of the shared parameters. Most importantly, the results indicate that our framework has gained state‐of‐the‐art performance on larger scales 3 and 4. Code is available at https://github.com/curzii23/SREFBN .

Recently, there has been much research focus on trust and reputation modelling as one of the key strategies for the formation of successful business intelligence strategies, particularly for service in mobile applications. One of the key trust modelling activities is trust prediction. During this process, the accuracy and reliability of the predicted trust values play an important role in the making of informed business decisions. Key factors to be considered at this stage are the variability and the high levels of distortion in the input series that have to be captured when predicting the trust values at a point in time in the future. In this paper, we propose a Multi-layer Feed Forward Artificial Neural Network to predict the future trust values of entities (services, agents, products etc.) for a future point in time based on data series input. We use four different non-uniform’ data input series and measure the accuracy of the predicted values under different experimental scenarios for benchmarking and comparison with existing approaches. Results indicate that the model is reliable in predicting trust values even in scenarios where there are only limited data available on training the neural network and a high level of distortion is present in the input series.

The Digital Business Ecosystem (DBE) is the result of the co-evolution of the Business Ecosystem and the Digital Ecosystem. There are numerous approaches and enabling technologies which are used in modeling open business marketplaces and, due to the similarities between the Digital Business environments, they can also help to enable the Digital Business Ecosystem but with some limitations. The complete lifecycle of the DBE can be decomposed into the following phases: formation, evolution and dissipation. In this work, our main focus is on the importance of negotiation in the DBE formation phase and especially on the structure of Contract Net Protocol. We will present an extension to the primitive Contract Net Protocol and name it Contract Net with Quality Protocol (CNQP or Q-Contract Net) to facilitate the negotiation process by adding the quality evaluation steps during the negotiation phase of the DBE formation.

In this paper, we establish a relationship between resource discovery protocol and cluster head election procedure. While doing so, we propose a multi-resource-criteria cluster head election mechanism that reduces the computational and communication overhead incurred in resource discovery. The consequent resource discovery protocol thus necessitates a minimalist exchange of information that we provide through custom packet formats and message flows. The extent of improvement thus achieved in the proposed protocol over existing resource discovery mechanisms is shown by performance evaluation.

The concept of mashup is gaining tremendous popularity and its application can be seen in a large number of domains. Enterprises using and relying upon mashup have improved their mass collaboration and personalization. In order for mashup technology to be widely accepted and widely used, we need a methodology by which can make use of the quality of the input to the mashup process as a governing principle to carry out mashup. This paper reviews the concept of mashup in different domains and proposes a conceptual solution framework for providing quality based mashup process.