24 citations · 54 across the 15 of their papers we have counts for
15 papers
SAN: Structure-Aware Network for Complex and Long-tailed Chinese Text Recognition
Junyi Zhang, Chang Liu, Chun Yang
In text recognition, complex glyphs and tail classes have always been factors affecting model performance. Specifically for Chinese text recognition, the lack of shape-awareness ca…
Deep Learning-empowered Predictive Precoder Design for OTFS Transmission in URLLC
Chang Liu, Shuangyang Li, Weijie Yuan +2
To guarantee excellent reliability performance in ultra-reliable low-latency communications (URLLC), pragmatic precoder design is an effective approach. However, an efficient preco…
Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
Chang Liu, Weiming Zhang, Xiangru Lin +6
With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that…
Detection of Uncertainty in Exceedance of Threshold (DUET): An Adversarial Patch Localizer
Terence Jie Chua, Wenhan Yu, Jun Zhao
Development of defenses against physical world attacks such as adversarial patches is gaining traction within the research community. We contribute to the field of adversarial patc…
Resource Allocation of Federated Learning for the Metaverse with Mobile Augmented Reality
Xinyu Zhou, Chang Liu, Jun Zhao
The Metaverse has received much attention recently. Metaverse applications via mobile augmented reality (MAR) require rapid and accurate object detection to mix digital data with t…
Time Minimization in Hierarchical Federated Learning
Chang Liu, Terence Jie Chua, Jun Zhao
Federated Learning is a modern decentralized machine learning technique where user equipments perform machine learning tasks locally and then upload the model parameters to a centr…
Robust Bayesian Inference for Moving Horizon Estimation
Wenhan Cao, Chang Liu, Zhiqian Lan +3
The accuracy of moving horizon estimation (MHE) suffers significantly in the presence of measurement outliers. Existing methods address this issue by treating measurements leading…
The path integral formula for the stochastic evolutionary game dynamics in the Moran process
Chao Wang
The Moran process is one of an basic mathematical structure in the evolutionary game theory. In this work, we introduce the formulation of the path integral approach for evolutiona…
Open-set Text Recognition via Character-Context Decoupling
Chang Liu, Chun Yang, Xu-Cheng Yin
The open-set text recognition task is an emerging challenge that requires an extra capability to cognize novel characters during evaluation. We argue that a major cause of the limi…
Primal-dual Estimator Learning: an Offline Constrained Moving Horizon Estimation Method with Feasibility and Near-optimality Guarantees
Wenhan Cao, Jingliang Duan, Shengbo Eben Li +3
This paper proposes a primal-dual framework to learn a stable estimator for linear constrained estimation problems leveraging the moving horizon approach. To avoid the online compu…
Adaptive Online Distributed Optimal Control of Very-Large-Scale Robotic Systems
Pingping Zhu, Chang Liu, Silvia Ferrari
This paper presents an adaptive online distributed optimal control approach that is applicable to optimal planning for very-large-scale robotics systems in highly uncertain environ…
Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection
Shi-Xue Zhang, Xiaobin Zhu, Jie-Bo Hou +4
Arbitrary shape text detection is a challenging task due to the high variety and complexity of scenes texts. In this paper, we propose a novel unified relational reasoning graph ne…
Mixed Reinforcement Learning with Additive Stochastic Uncertainty
Yao Mu, Shengbo Eben Li, Chang Liu +4
Reinforcement learning (RL) methods often rely on massive exploration data to search optimal policies, and suffer from poor sampling efficiency. This paper presents a mixed reinfor…
DWM: A Decomposable Winograd Method for Convolution Acceleration
Di Huang, Xishan Zhang, Rui Zhang +9
Winograd's minimal filtering algorithm has been widely used in Convolutional Neural Networks (CNNs) to reduce the number of multiplications for faster processing. However, it is on…
Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning
Dezhao Luo, Chang Liu, Yu Zhou +4
We propose a novel self-supervised method, referred to as Video Cloze Procedure (VCP), to learn rich spatial-temporal representations. VCP first generates "blanks" by withholding v…