Search Results - "Xiang, Xuezhi"

Optical flow and scene flow estimation: A survey by Zhai, Mingliang, Xiang, Xuezhi, Lv, Ning, Kong, Xiangdong

“…•To the best of our knowledge, this is the first survey paper to cover both optical flow and scene flow estimation comprehensively.•In contrast to existing…”
Get full text

Video event classification based on two-stage neural network by Zhang, Lei, Xiang, Xuezhi

“…Video stream is a sequence of static frames which can be described as 3D signals consisting of spatial and temporal clues. Simultaneous tackling of these two…”
Get full text

Traditional and modern strategies for optical flow: an investigation by Shah, Syed Tafseer Haider, Xuezhi, Xiang

“…Optical Flow Estimation is an essential component for many image processing techniques. This field of research in computer vision has seen an amazing…”
Get full text

Geometry understanding from autonomous driving scenarios based on feature refinement by Zhai, Mingliang, Xiang, Xuezhi

“…Nowadays, many deep learning applications benefit from multi-task learning with several related objectives. In autonomous driving scenarios, being able to…”
Get full text

Vehicle Counting Based on Vehicle Detection and Tracking from Aerial Videos by Xiang, Xuezhi, Zhai, Mingliang, Lv, Ning, El Saddik, Abdulmotaleb

“…Vehicle counting from an unmanned aerial vehicle (UAV) is becoming a popular research topic in traffic monitoring. Camera mounted on UAV can be regarded as a…”
Get full text

GloFP-MSF: monocular scene flow estimation with global feature perception by Xiang, Xuezhi, Cui, Yu, Wang, Xi, Zhai, Mingliang, El Saddik, Abdulmotaleb

“…Monocular scene flow estimation is a task that allows us to obtain 3D structure and 3D motion from consecutive monocular images. Previous monocular scene flow…”
Get full text

Engineering Vehicles Detection Based on Modified Faster R-CNN for Power Grid Surveillance by Xiang, Xuezhi, Lv, Ning, Guo, Xinli, Wang, Shuai, El Saddik, Abdulmotaleb

“…Engineering vehicles intrusion detection is a key problem for the security of power grid operation, which can warn of the regional invasion and prevent…”
Get full text

Optical Flow Estimation with Convolutional Neural Nets by Syed Tafseer Haider Shah, Xuezhi, Xiang, Ahmed, Waqas

“…In recent years, convolutional neural networks (CNNs) have been used for optical flow estimation with great success. Convolutional neural networks are…”
Get full text

Real-Time Parking Occupancy Detection for Gas Stations Based on Haar-AdaBoosting and CNN by Xuezhi Xiang, Ning Lv, Mingliang Zhai, El Saddik, Abdulmotaleb

“…Urban parking management is receiving significant attention because of the explosive increase in the number of vehicles. This paper proposes a novel parking…”
Get full text

Towards optimal VLAD for human action recognition from still images by Zhang, Lei, Li, Changxi, Peng, Peipei, Xiang, Xuezhi, Song, Jingkuan

“…Human action recognition from still image has recently drawn increasing attention in human behavior analysis and also poses great challenges due to the huge…”
Get full text

A CNNs-based method for optical flow estimation with prior constraints and stacked U-Nets by Xiang, Xuezhi, Zhai, Mingliang, Zhang, Rongfang, Qiao, Yulong, Saddik, Abdulmotaleb El

“…Traditional approaches for optical flow estimation always build an energy function which contains data term and smoothness term. However, optimizing the…”
Get full text

Learning Optical Flow Using Deep Dilated Residual Networks by Zhai, Mingliang, Xiang, Xuezhi, Zhang, Rongfang, Lv, Ning, El Saddik, Abdulmotaleb

“…Nowadays, convolutional neural networks achieve remarkable performance on optical flow estimation because of its strong non-linear fitting ability. Most of…”
Get full text

Deep Optical Flow Supervised Learning With Prior Assumptions by Xiang, Xuezhi, Zhai, Mingliang, Zhang, Rongfang, Qiao, Yulong, El Saddik, Abdulmotaleb

“…Traditional methods for estimating optical flow use variational model that includes data term and smoothness term, which can build a constraint relationship…”
Get full text

Realistic human action recognition: When CNNS meet LDS by Lei Zhang, Yangyang Feng, Xuezhi Xiang, Xiantong Zhen

“…In this paper, we proposed new framework for human action representation, which leverages the strengths of convolutional neural networks (CNNs) and the linear…”
Get full text

SKFlow: Optical Flow Estimation Using Selective Kernel Networks by Zhai, Mingliang, Xiang, Xuezhi, Lv, Ning, Masroor Ali, Syed, El Saddik, Abdulmotaleb

“…Leveraging on the recent developments in convolutional neural networks (CNNs), optical flow estimation from adjacent frames has been cast as a learning…”
Get full text

Scene Flow Estimation Based on 3D Local Rigidity Assumption and Depth Map Driven Anisotropic Smoothness by Xiang, Xuezhi, Zhai, Mingliang, Zhang, Rongfang, Xu, Wangwang, El Saddik, Abdulmotaleb

“…In this paper, we present a novel method to estimate the dense scene flow from the aligned depth map and color image using variational framework. For scene…”
Get full text

Dimensionality reduction by supervised locality analysis by Lei Zhang, Peipei Peng, Xuezhi Xiang, Xiantong Zhen

“…High-dimensional feature representations have recently been widely used for image classification, which not only induce large storage requirement and high…”
Get full text

An Improved YOLOv5 Crack Detection Method Combined With Transformer by Xiang, Xuezhi, Wang, Zhiyuan, Qiao, Yulong

“…Efficient detection of pavement cracks can effectively prevent traffic accidents and reduce pavement maintenance costs. In order to overcome the complicated…”
Get full text

Learning semantic kernels for scene classification by Lei Zhang, Xiantong Zhen, Jiqing Han, Xuezhi Xiang

“…In this paper we propose to learn semantic kernels for scene classification. We first decompose the Object Bank representation into subspaces associated with…”
Get full text

VIDF-Net: A Voxel-Image Dynamic Fusion method for 3D object detection by Xiang, Xuezhi, Li, Dianang, Wang, Xi, Zhou, Xiankun, Qiao, Yulong

“…In recent years, multi-modal fusion methods have shown excellent performance in the field of 3D object detection, which select the voxel centers and globally…”
Get full text