Abstract: The curse of kernelization affects most kernel-based models, including SVM, despite their strong generalization ability. Hyperparameter tuning, which requires computational resources, affects their predictive performance. Kernel methods have these issues with large datasets. We…
Abstract: Background clutter often affects RGBT tracking methods that localize a target object with a bounding box. This article introduces noise-robust cross-modal ranking to reduce background effects in RGBT target bounding boxes. We address noise…
Abstract: Machine learning models have excelled in machine translation, face recognition, and recommendation thanks to representation learning. Most representation learning methods require many consistent and noise-free labels. Labels are often limited due to budget constraints…
Abstract: Modern semantic segmentation methods require labeled data and require fine-tuning to work on unseen classes. Thus, few-shot segmentation proposes learning a model that quickly adapts to new classes with a few labeled support samples….
Abstract: Geographical topic models are used in recommendations, user mobility modeling, event detection, and geo-tagged document mining. Studying effective geographical topic models ignores efficiency. It takes days to train a geographical topic model on a…
Abstract: The initial proximity matrix affects the performance of most proximity-based multi-view clustering methods. Initial value sensitivity problem. Tuning the initial proximity matrix is unrealistic for unsupervised clustering. Thus, proximity-based multi-view clustering’s initial value sensitivity…
Abstract: Million-point large-scale subspace clustering (LS 2 C) is examined in this article. Despite being state-of-the-art for small-scale data points, many subspace clustering methods cannot directly solve the LS 2 C problem. These methods use…
Abstract: Many real-world applications require learning over massive, distributed data. With the rise of smart mobile devices and Internet of Things (IoT) devices, privacy and security concerns make data sharing difficult. Federated learning can jointly…
Abstract: Audio signal processing values music information retrieval. Musical instrument playing techniques have been neglected. This study proposes a GPT classification system. Because playing techniques vary slightly, GPT classification is difficult. This research uses spectral–temporal…
Abstract: Recommender systems provide relevant products, information, and services to users. Deep reinforcement learning has been successfully applied to recommender systems, but data sparsity and cold-start still plague real-world tasks. We propose using users’ pervasive…
Abstract: Since many real-world applications require semantic understanding of short texts, inferring discriminative and coherent latent topics is crucial. Since short texts have little word co-occurrence information, traditional long text topic modeling algorithms like PLSA…
Abstract: Because ensemble learning improves classification model prediction, it has many applications. This article proposes semisupervised multiple choice learning (SemiMCL) to jointly train a network ensemble on partially labeled data. Our model improves labeled data…
WhatsApp us