Search Results for author: Bo Yang

Found 69 papers, 25 papers with code

Spectrum Learning-Aided Reconfigurable Intelligent Surfaces for 'Green' 6G Networks

no code implementations3 Sep 2021 Bo Yang, Xuelin Cao, Chongwen Huang, Yong Liang Guan, Chau Yuen, Marco Di Renzo, Dusit Niyato, Merouane Debbah, Lajos Hanzo

In the sixth-generation (6G) era, emerging large-scale computing based applications (for example processing enormous amounts of images in real-time in autonomous driving) tend to lead to excessive energy consumption for the end users, whose devices are usually energy-constrained.

Autonomous Driving

Distributed Urban Freeway Traffic Optimization Considering Congestion Propagation

no code implementations11 Jun 2021 Fengkun Gao, Bo Yang, Cailian Chen, Xinping Guan, Yang Zhang

Most exiting works develop traffic optimization strategies depending on the local traffic states of congested road segments, where the congestion propagation is neglected.

Effect of Adaptive and Fixed Shared Steering Control on Distracted Driver Behavior

no code implementations7 Jun 2021 Zheng Wang, Satoshi Suga, Edric John Cruz Nacpil, Bo Yang, Kimihiko Nakano

Evaluation results indicated that, for both attentive and distracted drivers, haptic guidance with adaptive authority yielded lower driver workload and reduced lane departure risk than manual driving and fixed authority.

Steering Control

A Joint Energy and Latency Framework for Transfer Learning over 5G Industrial Edge Networks

no code implementations19 Apr 2021 Bo Yang, Omobayode Fagbohungbe, Xuelin Cao, Chau Yuen, Lijun Qian, Dusit Niyato, Yan Zhang

In this paper, we propose a transfer learning (TL)-enabled edge-CNN framework for 5G industrial edge networks with privacy-preserving characteristic.

Transfer Learning

Hyperbolic Neural Collaborative Recommender

no code implementations15 Apr 2021 Anchen Li, Bo Yang, Hongxu Chen, Guandong Xu

In the second phase, we develop a deep framework based on hyperbolic geometry to integrate constructed neighbor sets into recommendation.

Collaborative Filtering Representation Learning

NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering

no code implementations15 Apr 2021 Dongsheng Li, Haodong Liu, Chao Chen, Yingying Zhao, Stephen M. Chu, Bo Yang

In collaborative filtering (CF) algorithms, the optimal models are usually learned by globally minimizing the empirical risks averaged over all the observed data.

Collaborative Filtering Ensemble Learning

Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks

1 code implementation CVPR 2021 Yu Cheng, Bo wang, Bo Yang, Robby T. Tan

Besides the integration of top-down and bottom-up networks, unlike existing pose discriminators that are designed solely for single person, and consequently cannot assess natural inter-person interactions, we propose a two-person pose discriminator that enforces natural two-person interactions.

3D Multi-Person Pose Estimation (absolute) 3D Multi-Person Pose Estimation (root-relative) +2

RadarLoc: Learning to Relocalize in FMCW Radar

no code implementations22 Mar 2021 Wei Wang, Pedro P. B. de Gusmo, Bo Yang, Andrew Markham, Niki Trigoni

There is considerable work in the field of deep camera relocalization, which directly estimates poses from raw images.

Camera Relocalization

Intelligent Spectrum Learning for Wireless Networks with Reconfigurable Intelligent Surfaces

no code implementations2 Mar 2021 Bo Yang, Xuelin Cao, Chongwen Huang, Chau Yuen, Lijun Qian, Marco Di Renzo

Reconfigurable intelligent surface (RIS) has become a promising technology for enhancing the reliability of wireless communications, which is capable of reflecting the desired signals through appropriate phase shifts.

ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems

no code implementations17 Feb 2021 Yi Lin, Bo Yang, Linchao Li, Dongyue Guo, Jianwei Zhang, Hu Chen, Yi Zhang

Finally, by integrating the SRL with ASR, an end-to-end multilingual ASR framework is formulated in a supervised manner, which is able to translate the raw wave into text in one model, i. e., wave-to-text.

automatic-speech-recognition End-To-End Speech Recognition +3

D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis

1 code implementation16 Feb 2021 Yunhui Zheng, Saurabh Pujar, Burn Lewis, Luca Buratti, Edward Epstein, Bo Yang, Jim Laredo, Alessandro Morari, Zhong Su

However, existing datasets to train models for vulnerability identification suffer from multiple limitations such as limited bug context, limited size, and synthetic and unrealistic source code.

Vulnerability Detection

Improving speech recognition models with small samples for air traffic control systems

no code implementations16 Feb 2021 Yi Lin, Qin Li, Bo Yang, Zhen Yan, Huachun Tan, Zhengmao Chen

By virtue of the common terminology used in the ATC domain, the transfer learning task can be regarded as a sub-domain adaption task, in which the transferred model is optimized using a joint corpus consisting of baseline samples and new transcribed samples from the target dataset.

automatic-speech-recognition Domain Adaptation +2

HSR: Hyperbolic Social Recommender

no code implementations15 Feb 2021 Anchen Li, Bo Yang

With the prevalence of online social media, users' social connections have been widely studied and utilized to enhance the performance of recommender systems.

Click-Through Rate Prediction Recommendation Systems

DEFT: Distilling Entangled Factors by Preventing Information Diffusion

no code implementations8 Feb 2021 Jiantao Wu, Lin Wang, Bo Yang, Fanqi Li, Chunxiuzi Liu, Jin Zhou

Disentanglement is a highly desirable property of representation owing to its similarity to human understanding and reasoning.

Solid Texture Synthesis using Generative Adversarial Networks

no code implementations8 Feb 2021 Xin Zhao, Jifeng Guo, Lin Wang, Fanqi Li, Junteng Zheng, Bo Yang

Solid texture synthesis (STS), as an effective way to extend 2D exemplar to a 3D solid volume, exhibits advantages in numerous application domains.

Texture Synthesis

Adversarial example generation with AdaBelief Optimizer and Crop Invariance

no code implementations7 Feb 2021 Bo Yang, Hengwei Zhang, Yuchen Zhang, Kaiyong Xu, Jindong Wang

ABI-FGM and CIM can be readily integrated to build a strong gradient-based attack to further boost the success rates of adversarial examples for black-box attacks.

Black-Box Optimization via Generative Adversarial Nets

no code implementations7 Feb 2021 Minfang Lu, Fengyang Sun, Lin Wang, Shuai Ning, Shuangrong Liu, Bo Yang

Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details.

Testing Scalable Bell Inequalities for Quantum Graph States on IBM Quantum Devices

1 code implementation25 Jan 2021 Bo Yang, Rudy Raymond, Hiroshi Imai, Hyungseok Chang, Hidefumi Hiraishi

We are able to show violations of the inequalities on various graph states by constructing low-depth quantum circuits producing them, and by applying the readout error mitigation technique.

Quantum Physics

Random Transformation of Image Brightness for Adversarial Attack

1 code implementation12 Jan 2021 Bo Yang, Kaiyong Xu, Hengjun Wang, Hengwei Zhang

Before deep neural networks are deployed, adversarial attacks can thus be an important method to evaluate and select robust models in safety-critical applications.

Adversarial Attack Image Augmentation

Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos

1 code implementation22 Dec 2020 Yu Cheng, Bo wang, Bo Yang, Robby T. Tan

To tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that do not require camera parameters.

3D Absolute Human Pose Estimation 3D Multi-Person Pose Estimation (absolute) +5

Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems

no code implementations NeurIPS 2020 Songtao Lu, Meisam Razaviyayn, Bo Yang, Kejun Huang, Mingyi Hong

To the best of our knowledge, this is the first time that first-order algorithms with polynomial per-iteration complexity and global sublinear rate are designed to find SOSPs of the important class of non-convex problems with linear constraints (almost surely).

Intention-Based Lane Changing and Lane Keeping Haptic Guidance Steering System

no code implementations15 Nov 2020 Zhanhong Yan, Kaiming Yang, Zheng Wang, Bo Yang, Tsutomu Kaizuka, Kimihiko Nakano

By exerting continuous torque on the steering wheel, both the driver and support system can share lateral control of the vehicle.

Steering Control

Learning Personalized Discretionary Lane-Change Initiation for Fully Autonomous Driving Based on Reinforcement Learning

no code implementations29 Oct 2020 Zhuoxi Liu, Zheng Wang, Bo Yang, Kimihiko Nakano

In this article, the authors present a novel method to learn the personalized tactic of discretionary lane-change initiation for fully autonomous vehicles through human-computer interactions.

Autonomous Driving

Optimising Stochastic Routing for Taxi Fleets with Model Enhanced Reinforcement Learning

no code implementations22 Oct 2020 Shen Ren, Qianxiao Li, Liye Zhang, Zheng Qin, Bo Yang

The future of mobility-as-a-Service (Maas)should embrace an integrated system of ride-hailing, street-hailing and ride-sharing with optimised intelligent vehicle routing in response to a real-time, stochastic demand pattern.

Learning to Reconstruct and Segment 3D Objects

1 code implementation19 Oct 2020 Bo Yang

To endow machines with the ability to perceive the real-world in a three dimensional representation as we do as humans is a fundamental and long-standing topic in Artificial Intelligence.

Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization

no code implementations13 Oct 2020 Cheng Yu, Bo wang, Bo Yang, Robby T. Tan

Addressing these problems, we introduce a spatio-temporal network for robust 3D human pose estimation.

Pose Prediction

GRF: Learning a General Radiance Field for 3D Representation and Rendering

1 code implementation ICCV 2021 Alex Trevithick, Bo Yang

We present a simple yet powerful neural network that implicitly represents and renders 3D objects and scenes only from 2D observations.

3D Scene Reconstruction

Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges

1 code implementation CVPR 2021 Qingyong Hu, Bo Yang, Sheikh Khalid, Wen Xiao, Niki Trigoni, Andrew Markham

An essential prerequisite for unleashing the potential of supervised deep learning algorithms in the area of 3D scene understanding is the availability of large-scale and richly annotated datasets.

Scene Understanding Semantic Segmentation

Offloading Optimization in Edge Computing for Deep Learning Enabled Target Tracking by Internet-of-UAVs

no code implementations18 Aug 2020 Bo Yang, Xuelin Cao, Chau Yuen, Lijun Qian

This motivates us to consider offloading this type of deep learning (DL) tasks to a mobile edge computing (MEC) server due to limited computational resource and energy budget of the UAV, and further improve the inference accuracy.


Computation Offloading in Multi-Access Edge Computing Networks: A Multi-Task Learning Approach

no code implementations29 Jun 2020 Bo Yang, Xuelin Cao, Joshua Bassey, Xiangfang Li, Timothy Kroecker, Lijun Qian

Multi-access edge computing (MEC) has already shown the potential in enabling mobile devices to bear the computation-intensive applications by offloading some tasks to a nearby access point (AP) integrated with a MEC server (MES).

Edge-computing Multi-Task Learning

Lessons Learned from Accident of Autonomous Vehicle Testing: An Edge Learning-aided Offloading Framework

no code implementations27 Jun 2020 Bo Yang, Xuelin Cao, Xiangfang Li, Chau Yuen, Lijun Qian

This letter proposes an edge learning-based offloading framework for autonomous driving, where the deep learning tasks can be offloaded to the edge server to improve the inference accuracy while meeting the latency constraint.

Autonomous Driving

A Novel Graphic Bending Transformation on Benchmark

no code implementations21 Apr 2020 Chunxiuzi Liu, Fengyang Sun, Qingrui Ni, Lin Wang, Bo Yang

Classical benchmark problems utilize multiple transformation techniques to increase optimization difficulty, e. g., shift for anti centering effect and rotation for anti dimension sensitivity.

GRATE: Granular Recovery of Aggregated Tensor Data by Example

no code implementations27 Mar 2020 Ahmed S. Zamzam, Bo Yang, Nicholas D. Sidiropoulos

In this paper, we address the challenge of recovering an accurate breakdown of aggregated tensor data using disaggregation examples.

PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization

no code implementations5 Mar 2020 Wei Wang, Bing Wang, Peijun Zhao, Changhao Chen, Ronald Clark, Bo Yang, Andrew Markham, Niki Trigoni

In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map.


Geom-GCN: Geometric Graph Convolutional Networks

1 code implementation ICLR 2020 Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, Bo Yang

From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses.

Node Classification Representation Learning

A Block-based Generative Model for Attributed Networks Embedding

no code implementations6 Jan 2020 Xueyan Liu, Bo Yang, Wenzhuo Song, Katarzyna Musial, Wanli Zuo, Hongxu Chen, Hongzhi Yin

To preserve the attribute information, we assume that each node has a hidden embedding related to its assigned block.

Network Embedding

DeepPCO: End-to-End Point Cloud Odometry through Deep Parallel Neural Network

no code implementations13 Oct 2019 Wei Wang, Muhamad Risqi U. Saputra, Peijun Zhao, Pedro Gusmao, Bo Yang, Changhao Chen, Andrew Markham, Niki Trigoni

There is considerable work in the area of visual odometry (VO), and recent advances in deep learning have brought novel approaches to VO, which directly learn salient features from raw images.

Translation Visual Odometry

SNAP: Finding Approximate Second-Order Stationary Solutions Efficiently for Non-convex Linearly Constrained Problems

no code implementations9 Jul 2019 Songtao Lu, Meisam Razaviyayn, Bo Yang, Kejun Huang, Mingyi Hong

This paper proposes low-complexity algorithms for finding approximate second-order stationary points (SOSPs) of problems with smooth non-convex objective and linear constraints.

Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds

1 code implementation NeurIPS 2019 Bo Yang, Jianan Wang, Ronald Clark, Qingyong Hu, Sen Wang, Andrew Markham, Niki Trigoni

The framework directly regresses 3D bounding boxes for all instances in a point cloud, while simultaneously predicting a point-level mask for each instance.

Ranked #7 on 3D Instance Segmentation on S3DIS (mPrec metric)

3D Instance Segmentation Semantic Segmentation

Deep Bayesian Optimization on Attributed Graphs

3 code implementations31 May 2019 Jiaxu Cui, Bo Yang, Xia Hu

Attributed graphs, which contain rich contextual features beyond just network structure, are ubiquitous and have been observed to benefit various network analytics applications.

Gaussian Processes

Deep Neural Architecture Search with Deep Graph Bayesian Optimization

2 code implementations14 May 2019 Lizheng Ma, Jiaxu Cui, Bo Yang

Based on the new surrogate, we then develop a graph Bayesian optimization framework to address the challenging task of deep neural architecture search.

Gaussian Processes Neural Architecture Search

Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification Tasks

1 code implementation6 May 2019 Chunxu Zhang, Jiaxu Cui, Bo Yang

Although we can benefit a lot from DA, designing appropriate DA policies requires a lot of expert experience and time consumption, and the evaluation of searching the optimal policies is costly.

General Classification Image Augmentation +2

Energy Storage Management via Deep Q-Networks

no code implementations26 Mar 2019 Ahmed S. Zamzam, Bo Yang, Nicholas D. Sidiropoulos

Energy storage devices represent environmentally friendly candidates to cope with volatile renewable energy generation.

Learning Nonlinear Mixtures: Identifiability and Algorithm

no code implementations6 Jan 2019 Bo Yang, Xiao Fu, Nicholas D. Sidiropoulos, Kejun Huang

Linear mixture models have proven very useful in a plethora of applications, e. g., topic modeling, clustering, and source separation.

Enhanced Network Embedding with Text Information

2 code implementations 24th International Conference on Pattern Recognition (ICPR) 2018 Shuang Yang, Bo Yang

TENE learns the representations of nodes under the guidance of both proximity matrix which captures the network structure and text cluster membership matrix derived from clustering for text information.

Multi-class Classification Network Embedding +1

Efficient Metropolitan Traffic Prediction Based on Graph Recurrent Neural Network

no code implementations2 Nov 2018 Xiaoyu Wang, Cailian Chen, Yang Min, Jianping He, Bo Yang, Yang Zhang

Traffic prediction is a fundamental and vital task in Intelligence Transportation System (ITS), but it is very challenging to get high accuracy while containing low computational complexity due to the spatiotemporal characteristics of traffic flow, especially under the metropolitan circumstances.

Traffic Prediction

Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction

1 code implementation2 Aug 2018 Bo Yang, Sen Wang, Andrew Markham, Niki Trigoni

However, GRU based approaches are unable to consistently estimate 3D shapes given different permutations of the same set of input images as the recurrent unit is permutation variant.

3D Object Reconstruction 3D Reconstruction

Graph Bayesian Optimization: Algorithms, Evaluations and Applications

no code implementations3 May 2018 Jiaxu Cui, Bo Yang

Network structure optimization is a fundamental task in complex network analysis.

3D-PhysNet: Learning the Intuitive Physics of Non-Rigid Object Deformations

1 code implementation25 Apr 2018 Zhihua Wang, Stefano Rosa, Bo Yang, Sen Wang, Niki Trigoni, Andrew Markham

This is further confounded by the fact that shape information about encountered objects in the real world is often impaired by occlusions, noise and missing regions e. g. a robot manipulating an object will only be able to observe a partial view of the entire solid.

Defo-Net: Learning Body Deformation using Generative Adversarial Networks

1 code implementation16 Apr 2018 Zhihua Wang, Stefano Rosa, Linhai Xie, Bo Yang, Sen Wang, Niki Trigoni, Andrew Markham

Modelling the physical properties of everyday objects is a fundamental prerequisite for autonomous robots.


Dense 3D Object Reconstruction from a Single Depth View

2 code implementations1 Feb 2018 Bo Yang, Stefano Rosa, Andrew Markham, Niki Trigoni, Hongkai Wen

Unlike existing work which typically requires multiple views of the same object or class labels to recover the full 3D geometry, the proposed 3D-RecGAN++ only takes the voxel grid representation of a depth view of the object as input, and is able to generate the complete 3D occupancy grid with a high resolution of 256^3 by recovering the occluded/missing regions.

3D Object Reconstruction

Group Sparse Bayesian Learning for Active Surveillance on Epidemic Dynamics

no code implementations21 Nov 2017 Hongbin Pei, Bo Yang, Jiming Liu, Lei Dong

To address the challenge, we study the problem of active surveillance, i. e., how to identify a small portion of system components as sentinels to effect monitoring, such that the epidemic dynamics of an entire system can be readily predicted from the partial data collected by such sentinels.

3D Object Reconstruction from a Single Depth View with Adversarial Learning

2 code implementations26 Aug 2017 Bo Yang, Hongkai Wen, Sen Wang, Ronald Clark, Andrew Markham, Niki Trigoni

In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks.

3D Object Reconstruction

Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering

8 code implementations ICML 2017 Bo Yang, Xiao Fu, Nicholas D. Sidiropoulos, Mingyi Hong

To recover the `clustering-friendly' latent representations and to better cluster the data, we propose a joint DR and K-means clustering approach in which DR is accomplished via learning a deep neural network (DNN).

Dimensionality Reduction

Robust Volume Minimization-Based Matrix Factorization for Remote Sensing and Document Clustering

no code implementations15 Aug 2016 Xiao Fu, Kejun Huang, Bo Yang, Wing-Kin Ma, Nicholas D. Sidiropoulos

This paper considers \emph{volume minimization} (VolMin)-based structured matrix factorization (SMF).

Learning From Hidden Traits: Joint Factor Analysis and Latent Clustering

no code implementations21 May 2016 Bo Yang, Xiao Fu, Nicholas D. Sidiropoulos

Dimensionality reduction is usually performed in a preprocessing stage that is separate from subsequent data analysis, such as clustering or classification.

Dimensionality Reduction

Cannot find the paper you are looking for? You can Submit a new open access paper.