253 citations · 1.2k across the 46 of their papers we have counts for
11 papers · 1 filter
Asymmetric Transfer Hashing with Adaptive Bipartite Graph Learning
Jianglin Lu, Jie Zhou, Yudong Chen +2
Thanks to the efficient retrieval speed and low storage consumption, learning to hash has been widely used in visual retrieval tasks. However, existing hashing methods assume that…
Vision Transformer with Convolutions Architecture Search
Haichao Zhang, Kuangrong Hao, Witold Pedrycz +3
Transformers exhibit great advantages in handling computer vision tasks. They model image classification tasks by utilizing a multi-head attention mechanism to process a series of…
Robust and Precise Facial Landmark Detection by Self-Calibrated Pose Attention Network
Jun Wan, Hui Xi, Jie Zhou +4
Current fully-supervised facial landmark detection methods have progressed rapidly and achieved remarkable performance. However, they still suffer when coping with faces under larg…
LDNet: End-to-End Lane Marking Detection Approach Using a Dynamic Vision Sensor
Farzeen Munir, Shoaib Azam, Moongu Jeon +2
Modern vehicles are equipped with various driver-assistance systems, including automatic lane keeping, which prevents unintended lane departures. Traditional lane detection methods…
Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion
Young-min Song, Young-chul Yoon, Kwangjin Yoon +3
In this paper, we propose a highly practical fully online multi-object tracking and segmentation (MOTS) method that uses instance segmentation results as an input. The proposed met…
G-image Segmentation: Similarity-preserving Fuzzy C-Means with Spatial Information Constraint in Wavelet Space
Cong Wang, Witold Pedrycz, ZhiWu Li +2
G-images refer to image data defined on irregular graph domains. This work elaborates a similarity-preserving Fuzzy C-Means (FCM) algorithm for G-image segmentation and aims to dev…
Exploring Thermal Images for Object Detection in Underexposure Regions for Autonomous Driving
Farzeen Munir, Shoaib Azam, Muhammd Aasim Rafique +3
Underexposure regions are vital to construct a complete perception of the surroundings for safe autonomous driving. The availability of thermal cameras has provided an essential al…
A Novel Granular-Based Bi-Clustering Method of Deep Mining the Co-Expressed Genes
Kaijie Xu, Witold Pedrycz, Zhiwu Li +2
Traditional clustering methods are limited when dealing with huge and heterogeneous groups of gene expression data, which motivates the development of bi-clustering methods. Bi-clu…
Residual-Sparse Fuzzy -Means Clustering Incorporating Morphological Reconstruction and Wavelet frames
Cong Wang, Witold Pedrycz, ZhiWu Li +2
Instead of directly utilizing an observed image including some outliers, noise or intensity inhomogeneity, the use of its ideal value (e.g. noise-free image) has a favorable impact…
Kullback-Leibler Divergence-Based Fuzzy -Means Clustering Incorporating Morphological Reconstruction and Wavelet Frames for Image Segmentation
Cong Wang, Witold Pedrycz, ZhiWu Li +1
Although spatial information of images usually enhance the robustness of the Fuzzy C-Means (FCM) algorithm, it greatly increases the computational costs for image segmentation. To…
Entropic one-class classifiers
Lorenzo Livi, Alireza Sadeghian, Witold Pedrycz
The one-class classification problem is a well-known research endeavor in pattern recognition. The problem is also known under different names, such as outlier and novelty/anomaly…