PROBLEM Recent years have witnessed the rapid progress of self-supervised language models (LMs)[1],especially large language models (LLMs)[2].LLMs not only achieved state-of-the-art performance on many natural languag...
PROBLEM Recent years have witnessed the rapid progress of self-supervised language models (LMs)[1],especially large language models (LLMs)[2].LLMs not only achieved state-of-the-art performance on many natural language processing tasks,but also captured widespread attention from the public due to their great potential in a variety of real-world applications (***,search engines,writing assistants,etc.)through providing general-purpose intelligent services.A few of the LLMs are becoming foundation models,an analogy to infrastructure,that empower hundreds of downstream applications.
Significant progress has been made in remote sensing image change detection due to the rapid development of Deep Learning techniques. Convolutional neural networks(CNNs) have become foundational models in this field. ...
详细信息
Significant progress has been made in remote sensing image change detection due to the rapid development of Deep Learning techniques. Convolutional neural networks(CNNs) have become foundational models in this field. Previous works on remote sensing image change detection has utilized domain adaptation methods, achieving promising predictive performance. However, the transferable knowledge between source and target domain has not been fully exploited. In this paper, we propose a novel cross-domain contrastive learning approach for remote sensing image change detection, which correlates source and target domain using contrastive principles. Specifically, we introduce a transferable cross-domain Dictionary Learning scheme where a shared dictionary between the source and target domains generates sparse representations. Based on these representations, we compute attention weights and propose an attention-weighted contrastive loss to enhance knowledge transfer between source and target domains. Experiments demonstrate the effectiveness of the proposed methods on public remote sensing image change detection datasets.
With the prosperity of the mobile Internet, the abundance of data makes it difficult for users to choose their favorite app. Thus, mobile app recommendation as an emerging topic attracts lots of attention. However, ex...
详细信息
Current automatic segment extraction techniques for identifying target characters in videos have several limitations, including low accuracy, slow processing speeds, and poor adaptability to diverse scenes. This paper...
详细信息
Most social networks allow connections amongst many people based on shared *** networks have to offer shared data like videos,photos with minimum latency to the group,which could be challenging as the storage cost has...
详细信息
Most social networks allow connections amongst many people based on shared *** networks have to offer shared data like videos,photos with minimum latency to the group,which could be challenging as the storage cost has to be minimized and hence entire data replication is not a *** replication of data across a network of read-intensive can potentially lead to increased savings in cost and energy and reduce the end-user’s response *** simple and adaptive replication strategies exist,the solution is non-deter-ministic;the replicas of the data need to be optimized to the data usability,perfor-mance,and stability of the application *** resolve the non-deterministic issue of replication,metaheuristics are *** this work,Harmony Search and Tabu Search algorithms are used optimizing the replication process.A novel Har-mony-Tabu search is proposed for effective placement and replication of *** on large datasets show the effectiveness of the proposed *** is seen that the bandwidth saving for proposed harmony-Tabu replication per-forms better in the range of 3.57%to 18.18%for varying number of cloud data-centers when compared to simple replication,Tabu replication and Harmony replication algorithm.
ChatGPT, an advanced language model powered by artificial intelligence, has emerged as a transformative tool in the field of education. This article explores the potential of ChatGPT in revolutionizing learning and co...
详细信息
The human lungs, crucial for supplying oxygen, are vulnerable to diseases such as lung cancer, a leading cause of mortality. Timely prediction of lung cancer is essential to enable early intervention by healthcare pro...
详细信息
Video question answering(VideoQA) is a challenging yet important task that requires a joint understanding of low-level video content and high-level textual semantics. Despite the promising progress of existing efforts...
详细信息
Video question answering(VideoQA) is a challenging yet important task that requires a joint understanding of low-level video content and high-level textual semantics. Despite the promising progress of existing efforts, recent studies revealed that current VideoQA models mostly tend to over-rely on the superficial correlations rooted in the dataset bias while overlooking the key video content, thus leading to unreliable results. Effectively understanding and modeling the temporal and semantic characteristics of a given video for robust VideoQA is crucial but, to our knowledge, has not been well investigated. To fill the research gap, we propose a robust VideoQA framework that can effectively model the cross-modality fusion and enforce the model to focus on the temporal and global content of videos when making a QA decision instead of exploiting the shortcuts in datasets. Specifically, we design a self-supervised contrastive learning objective to contrast the positive and negative pairs of multimodal input, where the fused representation of the original multimodal input is enforced to be closer to that of the intervened input based on video perturbation. We expect the fused representation to focus more on the global context of videos rather than some static keyframes. Moreover, we introduce an effective temporal order regularization to enforce the inherent sequential structure of videos for video representation. We also design a Kullback-Leibler divergence-based perturbation invariance regularization of the predicted answer distribution to improve the robustness of the model against temporal content perturbation of videos. Our method is model-agnostic and can be easily compatible with various VideoQA backbones. Extensive experimental results and analyses on several public datasets show the advantage of our method over the state-of-the-art methods in terms of both accuracy and robustness.
Plant diseases significantly threaten global food security and economic stability by reducing crop yields, increasing production costs, and exacerbating food shortages. Early and precise detection of plant diseases is...
详细信息
The Internet of things(IoT)is a wireless network designed to perform specific tasks and plays a crucial role in various fields such as environmental monitoring,surveillance,and *** address the limitations imposed by i...
详细信息
The Internet of things(IoT)is a wireless network designed to perform specific tasks and plays a crucial role in various fields such as environmental monitoring,surveillance,and *** address the limitations imposed by inadequate resources,energy,and network scalability,this type of network relies heavily on data aggregation and clustering *** various conventional studies have aimed to enhance the lifespan of a network through robust systems,they do not always provide optimal efficiency for real-time *** paper presents an approach based on state-of-the-art machine-learning *** this study,we employed a novel approach that combines an extended version of principal component analysis(PCA)and a reinforcement learning algorithm to achieve efficient clustering and data *** primary objectives of this study are to enhance the service life of a network,reduce energy usage,and improve data aggregation *** evaluated the proposed methodology using data collected from sensors deployed in agricultural fields for crop *** proposed approach(PQL)was compared to previous studies that utilized adaptive Q-learning(AQL)and regional energy-aware clustering(REAC).Our study outperformed in terms of both network longevity and energy consumption and established a fault-tolerant network.
暂无评论