Pseudo-random number generators (PRNGs) are essential in a wide range of applications, from cryptography to statistical simulations and optimization algorithms. While uniform randomness is crucial for security-critical areas like cryptography, many domains, such as simulated annealing and CMOS-based Ising Machines, benefit from controlled or nonuniform randomness to enhance solution exploration and optimize performance. This paper presents a hardware PRNG that can simultaneously generate multiple uncorrelated sequences with programmable statistics tailored to specific application needs. Designed in 65nm process, the PRNG occupies an area of approximately 0.0013mm2and has an energy consumption of 0.57pJ/bit. Simulations confirm the PRNG's effectiveness in modulating the statistical distribution while demonstrating high-quality randomness properties.

As a popular brand management practice, firms communicate with consumers using images on social media platforms such as Instagram. Image-based brand communications on social media have two important characteristics. First, brand communications on social media are bilateral, not one-sided as those on traditional media. Second, measuring the information an image delivers is challenging. This study conceptualises a bilateral brand communication model to capture image information exchange between firms and consumers. This research examines how image information generated by firms and consumers changes in such dynamic and dyadic brand communications on Instagram and how brand communication strategies may alter the image information gap between the two parties. This study defines image information richness (IIR) based on information richness theory and applies machine learning techniques to measure IIR through the objective cues present in images. This approach provides brand managers with a practical tool to diagnose and manage their image-based brand communications. Analysis of 10,765 firm-generated images and 6,689 consumer-generated images from eight digital camera brands on Instagram reveals positive dynamic effects but asymmetrical dyadic effects of IIR. Consumer IIR can be inconsistent with firm IIR and thus form an IIR gap.

Bone Age (BA) is reckoned to be closely associated with the growth and development of teenagers, whose assessment highly depends on the accurate extraction of the reference bone from the carpal bone. Being uncertain in its proportion and irregular in its shape, wrong judgment and poor average extraction accuracy of the reference bone will no doubt lower the accuracy of Bone Age Assessment (BAA). In recent years, machine learning and data mining are widely embraced in smart healthcare systems. Using these two instruments, this article aims to tackle the aforementioned problems by proposing a Region of Interest (ROI) extraction method for wrist X-ray images based on optimized YOLO model. The method combines Deformable convolution-focus (Dc-focus), Coordinate attention (Ca) module, Feature level expansion, and Efficient Intersection over Union (EIoU) loss all together as YOLO-DCFE. With the improvement, the model can better extract the features of irregular reference bone and reduce the potential misdiscrimination between the reference bone and other similarly shaped reference bones, improving the detection accuracy. We select 10041 images taken by professional medical cameras as the dataset to test the performance of YOLO-DCFE. Statistics show the advantages of YOLO-DCFE in detection speed and high accuracy. The detection accuracy of all ROIs is 99.8%, which is higher than other models. Meanwhile, YOLO-DCFE is the fastest of all comparison models, with the Frames Per Second (FPS) reaching 16.

Few-shot object detection, which aims at detecting novel objects rapidly from extremely few annotated examples of previously unseen classes, has attracted significant research interest in the community. Most existing approaches employ the Faster R-CNN as basic detection framework, yet, due to the lack of tailored considerations for data-scarce scenario, their performance is often not satisfactory. In this paper, we look closely into the conventional Faster R-CNN and analyze its contradictions from two orthogonal perspectives, namely multi-stage (RPN vs. RCNN) and multi-task (classification vs. localization). To resolve these issues, we propose a simple yet effective architecture, named Decoupled Faster R-CNN (DeFRCN). To be concrete, we extend Faster R-CNN by introducing Gradient Decoupled Layer for multistage decoupling and Prototypical Calibration Block for multi-task decoupling. The former is a novel deep layer with redefining the feature-forward operation and gradient-backward operation for decoupling its subsequent layer and preceding layer, and the latter is an offline prototype-based classification model with taking the proposals from detector as input and boosting the original classification scores with additional pairwise scores for calibration. Extensive experiments on multiple benchmarks show our framework is remarkably superior to other existing approaches and establishes a new state-of-the-art in few-shot literature1.

Most of the few-shot learning methods learn to transfer knowledge from datasets with abundant labeled data (i.e., the base set). From the perspective of class space on base set, existing methods either focus on utilizing all classes under a global view by normal pretraining, or pay more attention to adopt an episodic manner to train meta-tasks within few classes in a local view. However, the interaction of the two views is rarely explored. As the two views capture complementary information, we naturally think of the compatibility of them for achieving further performance gains. Inspired by the mutual learning paradigm and binocular parallax, we propose a unified framework, namely Binocular Mutual Learning (BML), which achieves the compatibility of the global view and the local view through both intraview and cross-view modeling. Concretely, the global view learns in the whole class space to capture rich inter-class relationships. Meanwhile, the local view learns in the local class space within each episode, focusing on matching positive pairs correctly. In addition, cross-view mutual interaction further promotes the collaborative learning and the implicit exploration of useful knowledge from each other. During meta-test, binocular embeddings are aggregated together to support decision-making, which greatly improve the accuracy of classification. Extensive experiments conducted on multiple benchmarks including cross-domain validation confirm the effectiveness of our method1.

We present a novel self quality evaluation metric SQE for parameters optimization in the challenging yet critical multi-object tracking task. Current evaluation metrics all require annotated ground truth, thus will fail in the test environment and realistic circumstances prohibiting further optimization after training. By contrast, our metric reflects the internal characteristics of trajectory hypotheses and measures tracking performance without ground truth. We demonstrate that trajectories with different qualities exhibit different single or multiple peaks over feature distance distribution, inspiring us to design a simple yet effective method to assess the quality of trajectories using a two-class Gaussian mixture model. Experiments mainly on MOT16 Challenge data sets verify the effectiveness of our method in both correlating with existing metrics and enabling parameters self-optimization to achieve better performance. We believe that our conclusions and method are inspiring for future multi-object tracking in practice.

Third-party interpersonal communications such as online seller reviews play an important role in buyers’ purchase decisions in online markets. Although it is empirically clear that seller reviews (volume and valence) and product price contribute to buyers’ willingness-to-pay (WTP) differently across various studies, it is theoretically less understood why such effects qualitatively differ (e.g., positive vs negative), rendering unclear managerial implications for online marketers. In this paper, we study the role of online seller reviews and product price in buyers’ WTP. We offer a conceptual framework from a risk perspective in which we argue that the different effects of seller reviews and product price on buyers’ WTP may emerge simultaneously in an online market. We highlight two important drivers for such qualitatively different effects: a difference in buyers’ risk attitudes (averse, neutral, or seeking) and a difference in WTP measures (absolute or relative). We test our hypotheses and find good support for them both internally (an experimental study) and externally (an empirical study). Our research enhances the understanding of the relationship between online user reviews and online price dispersions while shedding light on better management of online user reviews for market makers.

Consumers often use shopbots to search for information when making purchase decisions in Internet markets. Although they have varying sensitivity to shopbot bias, consumers generally prefer accurate market representation. However, in choosing the accuracy of market representation, shopbots must balance the desires of consumers with the costs of providing their services and with the desires of the vendors, who are often the largest source of their revenue. In this paper, we study how accurately shopbots represent a market and analyze the strategies shopbots adopt to achieve market representativeness. We theoretically identify two important drivers in shopbot vendor coverage strategy – how many vendors it covers (shopbot size) and which vendors it covers (shopbot affiliation) – and analytically show how the drivers affect shopbot market representativeness. We report the results of a large-scale study in which we collected 2.2 million vendor price listings from eight shopbots and develop metrics for measuring shopbot size, shopbot affiliation, and shopbot market representativeness. We found that (1) shopbots do not represent markets equally well; (2) size drives a shopbot's market representativeness positively whereas affiliation drives a shopbot's market representativeness negatively; (3) shopbots follow differnet vendor representative strategies to pursue market representativeness.