146 citations · 291 across the 27 of their papers we have counts for
27 papers
RTrack: Accelerating Convergence for Visual Object Tracking via Pseudo-Boxes Exploration
Guotian Zeng, Bi Zeng, Hong Zhang +2
Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. However, due to the potential deformation and rotation experienced by the…
Person Re-Identification for Robot Person Following with Online Continual Learning
Hanjing Ye, Jieting Zhao, Yu Zhan +3
Robot person following (RPF) is a crucial capability in human-robot interaction (HRI) applications, allowing a robot to persistently follow a designated person. In practical RPF sc…
NPR: Nocturnal Place Recognition in Streets
Bingxi Liu, Yujie Fu, Feng Lu +3
Visual Place Recognition (VPR) is the task of retrieving database images similar to a query photo by comparing it to a large database of known images. In real-world applications, e…
Wearing Masks Implies Refuting Trump?: Towards Target-specific User Stance Prediction across Events in COVID-19 and US Election 2020
Hong Zhang, Haewoon Kwak, Wei Gao +1
People who share similar opinions towards controversial topics could form an echo chamber and may share similar political views toward other topics as well. The existence of such c…
Robot Person Following Under Partial Occlusion
Hanjing Ye, Jieting Zhao, Yaling Pan +3
Robot person following (RPF) is a capability that supports many useful human-robot-interaction (HRI) applications. However, existing solutions to person following often assume full…
ProKD: An Unsupervised Prototypical Knowledge Distillation Network for Zero-Resource Cross-Lingual Named Entity Recognition
Ling Ge, Chunming Hu, Guanghui Ma +2
For named entity recognition (NER) in zero-resource languages, utilizing knowledge distillation methods to transfer language-independent knowledge from the rich-resource source lan…
A Convolutional-Transformer Network for Crack Segmentation with Boundary Awareness
Huaqi Tao, Bingxi Liu, Jinqiang Cui +1
Cracks play a crucial role in assessing the safety and durability of manufactured buildings. However, the long and sharp topological features and complex background of cracks make…
RAPS: A Novel Few-Shot Relation Extraction Pipeline with Query-Information Guided Attention and Adaptive Prototype Fusion
Yuzhe Zhang, Min Cen, Tongzhou Wu +1
Few-shot relation extraction (FSRE) aims at recognizing unseen relations by learning with merely a handful of annotated instances. To generalize to new relations more effectively,…
NDD: A 3D Point Cloud Descriptor Based on Normal Distribution for Loop Closure Detection
Ruihao Zhou, Li He, Hong Zhang +2
Loop closure detection is a key technology for long-term robot navigation in complex environments. In this paper, we present a global descriptor, named Normal Distribution Descript…
Efficient inference of parental origin effects using case-control mother-child genotype data
Yuang Tian, Hong Zhang, Alexandre Bureau +2
Parental origin effects play an important role in mammal development and disorder. Case-control mother-child pair genotype data can be used to detect parental origin effects and is…
Perspective Phase Angle Model for Polarimetric 3D Reconstruction
Guangcheng Chen, Li He, Yisheng Guan +1
Current polarimetric 3D reconstruction methods, including those in the well-established shape from polarization literature, are all developed under the orthographic projection assu…
Sparse Optical Flow-Based Line Feature Tracking
Qiang Fu, Hongshan Yu, Islam Ali +1
In this paper we propose a novel sparse optical flow (SOF)-based line feature tracking method for the camera pose estimation problem. This method is inspired by the point-based SOF…
Snowmass21 Accelerator Modeling Community White Paper
S. Biedron, L. Brouwer, D. L. Bruhwiler +24
After a summary of relevant comments and recommendations from various reports over the last ten years, this paper examines the modeling needs in accelerator physics, from the model…
Multirate Partitioned Runge-Kutta Methods for Coupled Navier-Stokes Equations
Shinhoo Kang, Alp Dener, Aidan Hamilton +3
Earth system models are complex integrated models of atmosphere, ocean, sea ice, and land surface. Coupling the components can be a significant challenge due to the difference in p…
The PETSc Community Is the Infrastructure
Mark Adams, Satish Balay, Oana Marin +13
The communities who develop and support open source scientific software packages are crucial to the utility and success of such packages. Moreover, these communities form an import…
Continuous Real-Time Detection of Quasiparticle Trapping in Aluminum Nanobridge Josephson Junctions
James T. Farmer, Azarin Zarassi, Darian M. Hartsell +3
Nonequilibrium quasiparticles are ubiquitous in superconducting electronics. These quasiparticles can trap in the internal Andreev bound states of a phase-biased Josephson junction…
Curiosity-based Robot Navigation under Uncertainty in Crowded Environments
Kuanqi Cai, Weinan Chen, Chaoqun Wang +2
Mobile robots have become more and more popular in large-scale and crowded environments, such as airports, shopping malls, etc. However, due to sparse landmarks and crowd noise, lo…
CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Prediction
Shing Yan Loo, Ali Jahani Amiri, Syamsiah Mashohor +2
Reliable feature correspondence between frames is a critical step in visual odometry (VO) and visual simultaneous localization and mapping (V-SLAM) algorithms. In comparison with e…
PETSc/TS: A Modern Scalable ODE/DAE Solver Library
Shrirang Abhyankar, Jed Brown, Emil M. Constantinescu +3
High-quality ordinary differential equation (ODE) solver libraries have a long history, going back to the 1970s. Over the past several years we have implemented, on top of the PETS…
Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network
Sepideh Hosseinzadeh, Moein Shakeri, Hong Zhang
In recent years, various shadow detection methods from a single image have been proposed and used in vision systems; however, most of them are not appropriate for the robotic appli…
Face Recognition using Multi-Modal Low-Rank Dictionary Learning
Homa Foroughi, Moein Shakeri, Nilanjan Ray +1
Face recognition has been widely studied due to its importance in different applications; however, most of the proposed methods fail when face images are occluded or captured under…
Object Classification with Joint Projection and Low-rank Dictionary Learning
Homa Foroughi, Nilanjan Ray, Hong Zhang
For an object classification system, the most critical obstacles towards real-world applications are often caused by large intra-class variability, arising from different lightings…
Joint Projection and Dictionary Learning using Low-rank Regularization and Graph Constraints
Homa Foroughi, Nilanjan Ray, Hong Zhang
In this paper, we aim at learning simultaneously a discriminative dictionary and a robust projection matrix from noisy data. The joint learning, makes the learned projection and di…
COROLA: A Sequential Solution to Moving Object Detection Using Low-rank Approximation
Moein Shakeri, Hong Zhang
Extracting moving objects from a video sequence and estimating the background of each individual image are fundamental issues in many practical applications such as visual surveill…