This research proposes a Virtual Reality Sensing System (VRSS) integrated with activity network technology to enhance emergency response coordination. By combining VR with real-time data from Wireless Sensor Networks ...
详细信息
In the digital age, image forgery is a significant concern due to advanced editing tools. This study addresses the need for reliable forgery detection, focusing on copy-move, splicing, and retouching techniques. Using...
详细信息
Online movie ratings have evolved into a serious business. Hollywood generates around $10 billion in box office revenue in the United States each year, and online ratings aggregators may have an increasing influence o...
详细信息
Augmented reality (AR) is a recent technology with applications in multiple sectors, including the healthcare industry. AR incorporates (or overlays) digital or computer-generated data such as audio, video, images, an...
详细信息
Among the deadliest types of disease is cancer. It is also the most prevalent cancer in women, and if it is not correctly identified, it can even be fatal. Although medical technology has advanced significantly over t...
详细信息
Driven by the surge in code generation using large language models (LLMs), numerous benchmarks have emerged to evaluate these LLMs capabilities. We conducted a large-scale human evaluation of HumanEval and MBPP, two p...
详细信息
Unsupervised domain adaptation (UDA) has emerged as a powerful solution for the domain shift problem via transferring the knowledge from a labeled source domain to a shifted unlabeled target domain. Despite the preval...
详细信息
Unsupervised domain adaptation (UDA) has emerged as a powerful solution for the domain shift problem via transferring the knowledge from a labeled source domain to a shifted unlabeled target domain. Despite the prevalence of UDA for visual applications, it remains relatively less explored for time-series applications. In this work, we propose a novel lightweight contrastive domain adaptation framework called CoTMix for time-series data. Unlike existing approaches that either use statistical distances or adversarial techniques, we leverage contrastive learning solely to mitigate the distribution shift across the different domains. Specifically, we propose a novel temporal mixup strategy to generate two intermediate augmented views for the source and target domains. Subsequently, we leverage contrastive learning to maximize the similarity between each domain and its corresponding augmented view. The generated views consider the temporal dynamics of time-series data during the adaptation process while inheriting the semantics among the two domains. Hence, we gradually push both domains toward a common intermediate space, mitigating the distribution shift across them. Extensive experiments conducted on five real-world time-series datasets show that our approach can significantly outperform all state-of-the-art UDA methods. Impact Statement-Unsupervised domain adaptation (UDA) aims to reduce the gap between two related but shifted domains. CurrentUDAmethods for time-series data are based on adversarial or discrepancy approaches. Thesemethods are complex in training and cannot efficiently address the large domain shift. Therefore, in this work, we propose a time-series UDA framework based purely on contrastive learning, which is simpler in implementation and training. To leverage contrastive learning to mitigate domain shift, we propose a temporal mixup strategy to generate augmentations that are robust to the domain shift and can move both domains towards an intermediate
Over the years the change in global climatic conditions, like the greenhouse effect, and global warming have led to sudden increases in natural disasters mostly weather, climates, and water extremes. which has led to ...
详细信息
The rapid proliferation of data and the intricate nature of user behavior in the online realm have presented new hurdles for recommendation systems, which aim to suggest pertinent items to users. Among the notable cha...
详细信息
Video analytics faces complex challenges in object detection and classification. Deep learning based approaches have achieved remarkable success in past decade. However, existing object identification models that util...
详细信息
暂无评论