38 Result(s)
within
Chapter
Zhigang **
Algorithm Analysis and Problem Complexity
Image Processing and Computer Vision
-
Chapter and Conference Paper
DiffMoCa: Diffusion Model Based Multi-modality Cut and Paste
The Multi-mOdality Cut and pAste (MoCa) method cuts data from other frames and pastes it onto the current training data frame to increase the number of training object samples. However, the samples used by MoC...
-
Chapter and Conference Paper
CSFuser: A Cascade Siamese Fusion Architecture for RGB-Infrared Object Detection
RGB-Infrared multi-modal object detection harnesses diverse and complementary information from RGB and infrared images, offering significant advantages in intelligent transportation. The primary challenge lies...
-
Chapter and Conference Paper
Parallelized ADMM with General Objectives for Deep Learning
While considerable efforts have been dedicated to improving models that employ regularized functions, the direct solution of non-convex models using most stochastic gradient optimization algorithms poses signi...
-
Chapter and Conference Paper
Segmenta: Pipelined BFT Consensus with Slicing Broadcast
Bandwidth is an essential resource for blockchain systems since BFT protocols require a series of communication steps to reach a consensus. Reducing available bandwidth will directly hurt system performance, e...
-
Chapter and Conference Paper
Attentional Residual Dense Factorized Network for Real-Time Semantic Segmentation
Semantic segmentation is a pixel-level image dense labeling task and plays a core role in autonomous driving. In this regard, how to balance between precision and speed is a frequently-studied issue. In this p...
-
Chapter and Conference Paper
Multi Step Prediction of Landslide Displacement Time Series Based on Extended Kalman Filter and Back Propagation Trough Time
Landslide is a complex geological natural disaster that brings harm or damage to human beings and their living environment. By strengthening landslide monitoring and forecasting technology, people can avoid or...
-
Chapter and Conference Paper
Relaxed 2-D Principal Component Analysis by Lp Norm for Face Recognition
A relaxed two-dimensional principal component analysis (R2DPCA) approach is proposed for face recognition. Different to the 2DPCA, 2DPCA-L1 and G2DPCA, the R2DPCA utilizes the label information (if known) of trai...
-
Chapter and Conference Paper
A Novel Second-Order Consensus Control in Multi-agent Dynamical Systems
In this paper, a new type protocol is proposed. Second-order consensus in multi-agent dynamical systems with this protocol is studied using a new analytical method
-
Chapter and Conference Paper
Global Stabilization for Delayed Fuzzy Inertial Neural Networks
This paper studies the global stabilization problem for a class of fuzzy inertial neural networks (FINN) with time delays and deals with the FINN directly by non-reduced order method
-
Chapter and Conference Paper
Formal Specification of Concurrent Enforcement UCON Model with CTL Logic
Usage Control (UCON) model has been considered as the next generation access control model, its distinguishing properties of attribute mutability and decision continuity were more suit for dynamic and open net...
-
Chapter and Conference Paper
WeiboCluster: An Event-Oriented Sina Weibo Dataset with Estimating Credit
The earliest and the most famous micro-blogging platform is Twitter, which was created in 2006. But in China, Sina Weibo, the latecomer, has become bigger than Twitter and plays a vital role in the social medi...
-
Chapter and Conference Paper
R-RTRL Based on Recurrent Neural Network with K-Fold Cross-Validation for Multi-step-ahead Prediction Landslide Displacement
The reinforced real-time recurrent learning (R-RTRL) algorithm with K-fold cross-validation for recurrent neural networks (RNNs) are applied to forecast multi-step-ahead landslide displacement (K-R-RTRL). The pro...
-
Chapter and Conference Paper
Boundedness and Stability for a Class of Timescale-Type Time-Varying Systems
This paper investigated a class of time-varying systems on time scales. Based on the general theory of time scales, the ultimate boundedness and asymptotic stability of the system is studied. Two examples illu...
-
Chapter and Conference Paper
Learning Misclassification Costs for Imbalanced Datasets, Application in Gene Expression Data Classification
Cost-sensitive algorithms have been widely used to solve imbalanced classification problem. However, the misclassification costs are usually determined empirically, leading to uncertain performance. Hence an e...
-
Chapter and Conference Paper
Robot Path Planning Based on A Hybrid Approach
In this paper, an optimal method based on combination of improved genetic algorithm (IGA) and improved artificial potential field (IAPF) for path planning of mobile robot is proposed. This method consists of t...
-
Chapter and Conference Paper
Classifying Non-linear Gene Expression Data Using a Novel Hybrid Rotation Forest Method
Rotation forest (RoF) is an ensemble classifier based on the combination of linear analysis theories and decision tree algorithms. In existing works, the RoF has demonstrated high classification accuracy and g...
-
Chapter and Conference Paper
A New Cuckoo Search
In this paper, we intend to formulate a new Cuckoo Search (NCS) for solving optimization problems. This algorithm is based on the obligate brood parasitic behavior of some cuckoo species in combination with th...
-
Chapter and Conference Paper
Automatic Collimation Detection in Digital Radiographs with the Directed Hough Transform and Learning-Based Edge Detection
Collimation is widely used for X-ray examinations to reduce the overall radiation exposure to the patient and improve the contrast resolution in the region of interest (ROI), that has been exposed directly to ...
-
Chapter and Conference Paper
Mobile Panoramic Vision for Assisting the Blind via Indexing and Localization
In this paper, we propose a first-person localization and navigation system for hel** blind and visually-impaired people navigate in indoor environments. The system consists of a mobile vision front end with...
-
Chapter and Conference Paper
Activity Recognition in Still Images with Transductive Non-negative Matrix Factorization
Still image based activity recognition is a challenging problem due to changes in appearance of persons, articulation in poses, cluttered backgrounds, and absence of temporal features. In this paper, we propos...
