Camera relocalization is a challenging task to estimate camera pose within a known scene, with wide applications in the fields of Virtual Reality (VR), Augmented Reality (AR), robotics, and etc. Most existing learning-based methods invariably utilize all ...

Simultaneously mapping and exploring a complex unknown scene is an NP-hard problem, which is still challenging with the rapid development of deep learning techniques. We present CSO, a deep reinforcement learning-based framework for efficient active ...

• Our study delved into the intricate dynamics of information propagation in social networks, unraveling the complexities of competing information from various sources.
• Unlike traditional models assuming static attractiveness, we ...

The ubiquity of social media has facilitated the simultaneous dissemination of large-scale information within online social networks. By assuming that information attractiveness is static, numerous studies have been devoted to the analysis of ...

This article focuses on the adaptive fuzzy practical predefined-time bipartite consensus tracking control (BCTC) problem for heterogeneous nonlinear multiagent systems (HNMASs) with actuator faults. First, the fuzzy logic systems are used to approximate ...

We propose a novel Text-to-Image Generation Network, Attention-bridged Modal Interaction Generative Adversarial Network (AMI-GAN), to better explore modal interaction and perception for high-quality image synthesis. The AMI-GAN contains two novel designs: ...

Recently, heterogeneous cluster networks (HCNs) have been the subject of significant research. The nature of the next‐generation HCN environment is decentralized and highly dynamic; optimization techniques cannot quite express the dynamic ...

We propose a Hybrid‐Q Learning (Hybrid QL)‐based clustering for IoT and WSN. Self‐learning solution to solve the problem of decentralized and dynamic self‐access for heterogeneous nodes. Our proposed model dynamic accessing system on node/agents ...

Event cameras, or dynamic vision sensors, have recently achieved success from fundamental vision tasks to high-level vision researches. Due to its ability to asynchronously capture light intensity changes, event camera has an inherent advantage to capture ...

We propose a novel Text-to-Image Generation Network, Adaptive Layout Refinement Generative Adversarial Network (ALR-GAN), to adaptively refine the layout of synthesized images without any auxiliary information. The ALR-GAN includes an Adaptive Layout ...

Matrix-variate Restricted Boltzmann Machine (MVRBM), a variant of Restricted Boltzmann Machine, has demonstrated excellent capacity of modelling matrix variable. However, MVRBM is still an unsupervised generative model, and is usually used to ...

Low Rank Representation (LRR) based unsupervised clustering methods have achieved great success since these methods could explore low-dimensional subspace structure embedded in original data effectively. The conventional LRR methods generally ...

Variational Auto-Encoder (VAE) is an important probabilistic technology to model 1D vectorial data. However, when applying VAE model to 2D image, vectorization is necessary. Vectorization process may lead to dimension curse and lose valuable ...

High-quality depth information has been increasingly used in many real-world multimedia applications in recent years. Due to the limitation of depth sensor and sensing technology, actually, the captured depth map usually has low resolution and black ...

Bus arrival time prediction intends to improve the level of the services provided by transportation agencies. Intuitively, many stochastic factors affect the predictability of the arrival time, <italic>e.g.</italic>, weather and local events. Moreover, ...

Dimensionality reduction is widely used to deal with high-dimensional data. As a famous dimensionality reduction method, principal component analysis (PCA) aiming at finding the low dimension feature of original data has made great successes, and many ...

Restricted Boltzmann machine (RBM) is a famous model for feature extraction and can be used as an initializer for neural networks. When applying the classic RBM to multidimensional data such as 2D/3D tensors, one needs to vectorize such as high-order ...

Human action recognition based on 3D skeleton joints is an important yet challenging task. While many research work are devoted to 3D action recognition, they mainly suffer from two problems: complex model representation and low implementation ...

Human poses admit complicated articulations and multigranular similarity. Previous works on learning human pose metric utilize sparse models, which concentrate large weights on highly similar poses and fail to depict an overall structure of poses with ...

The tensor completion issues have obtained a great deal of attention in the past few years. However, the data fidelity part minimizes a squared loss function, which may be inappropriate for the case of noisy one-bit observations. In this paper, we ...

As increasing volumes of urban data are being available, new opportunities arise for data-driven analysis that can lead to improvements in the lives of citizens through evidence-based policies. In particular, taxi trip is an important urban sensor that ...

Subspace data representation has recently become a common practice in many computer vision tasks. Low-rank representation (LRR) is one of the most successful models for clustering vectorial data according to their subspace structures. This paper explores ...