Search Results for author: Bo Yang

Found 141 papers, 52 papers with code

How to leverage the multimodal EHR data for better medical prediction?

no code implementations EMNLP 2021 Bo Yang, Lijun Wu

Therefore, in this paper, we first extract the accompanying clinical notes from EHR and propose a method to integrate these data, we also comprehensively study the different models and the data leverage methods for better medical task prediction performance.

UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment

1 code implementation25 Mar 2024 Kaipeng Zeng, Bo Yang, Xin Zhao, Yu Zhang, Fan Nie, Xiaokang Yang, Yaohui Jin, Yanyan Xu

Single-step retrosynthesis prediction, a crucial step in the planning process, has witnessed a surge in interest in recent years due to advancements in AI for science.

Graph-to-Sequence molecular representation +3

Adversarial example soups: averaging multiple adversarial examples improves transferability without increasing additional generation time

no code implementations27 Feb 2024 Bo Yang, Hengwei Zhang, Chenwei Li, Jindong Wang

For transfer-based attacks, the adversarial examples are crafted on the surrogate model, which can be implemented to mislead the target model effectively.

Scalable Volt-VAR Optimization using RLlib-IMPALA Framework: A Reinforcement Learning Approach

no code implementations24 Feb 2024 Alaa Selim, Yanzhu Ye, Junbo Zhao, Bo Yang

To address this challenge, our research presents a novel framework that harnesses the potential of Deep Reinforcement Learning (DRL), specifically utilizing the Importance Weighted Actor-Learner Architecture (IMPALA) algorithm, executed on the RAY platform.

Distributed Computing reinforcement-learning

Computation Offloading for Multi-server Multi-access Edge Vehicular Networks: A DDQN-based Method

no code implementations21 Feb 2024 Siyu Wang, Bo Yang, Zhiwen Yu, Xuelin Cao, Yan Zhang, Chau Yuen

In this paper, we investigate a multi-user offloading problem in the overlapping domain of a multi-server mobile edge computing system.

Decision Making Edge-computing +1

Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization

1 code implementation3 Feb 2024 Bo Yang, Chen Wang, Xiaoshuang Ma, Beiping Song, Zhuang Liu

To address this gap, our study introduces a novel zero-shot, sketch-based retrieval method for remote sensing images, leveraging multi-level feature extraction, self-attention-guided tokenization and filtering, and cross-modality attention update.

Cross-Modal Retrieval Image Retrieval +2

Seismic Traveltime Tomography with Label-free Learning

1 code implementation1 Feb 2024 Feng Wang, Bo Yang, Renfang Wang, Hong Qiu

To avoid generating and/or collecting labeled samples, we propose a novel method by integrating deep learning and dictionary learning to enhance the VMs with low resolution by using the traditional tomography-least square method (LSQR).

Dictionary Learning

Fine-Grained Prototypes Distillation for Few-Shot Object Detection

1 code implementation15 Jan 2024 Zichen Wang, Bo Yang, Haonan Yue, Zhenghao Ma

However, the class-level prototypes are difficult to precisely generate, and they also lack detailed information, leading to instability in performance. New methods are required to capture the distinctive local context for more robust novel object detection.

Few-Shot Object Detection Meta-Learning +3

Joint Trading and Scheduling among Coupled Carbon-Electricity-Heat-Gas Industrial Clusters

no code implementations20 Dec 2023 Dafeng Zhu, Bo Yang, Yu Wu, Haoran Deng, ZhaoYang Dong, Kai Ma, Xinping Guan

This paper presents a carbon-energy coupling management framework for an industrial park, where the carbon flow model accompanying multi-energy flows is adopted to track and suppress carbon emissions on the user side.

energy trading Management +1

Multi-stages attention Breast cancer classification based on nonlinear spiking neural P neurons with autapses

no code implementations20 Dec 2023 Bo Yang, Hong Peng, Xiaohui Luo, Jun Wang

Downsampling in deep networks may lead to loss of information, so for compensating the detail and edge information and allowing convolutional neural networks to pay more attention to seek the lesion region, we propose a multi-stages attention architecture based on NSNP neurons with autapses.

Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Images

1 code implementation8 Dec 2023 Yafei Yang, Bo Yang

We first introduce seven complexity factors to quantitatively measure the distributions of background and foreground object biases in appearance and geometry for datasets with human annotations.

Benchmarking Object +2

A multi-layer refined network model for the identification of essential proteins

no code implementations6 Dec 2023 Haoyue Wang, Li Pan, Bo Yang, Junqiang Jiang, Wenbin Li

In order to improve the accuracy of the identification of essential proteins, researchers attempted to obtain a refined PIN by combining multiple biological information to filter out some unreliable interactions in the PIN.

Specificity

PerCNet: Periodic Complete Representation for Crystal Graphs

no code implementations3 Dec 2023 Jiao Huang, Qianli Xing, Jinglong Ji, Bo Yang

To solve this many-to-one issue, we consider the global information by further considering dihedral angles, which can guarantee that the proposed representation corresponds one-to-one with the crystal material.

Graph Learning Representation Learning

Learning Continuous Network Emerging Dynamics from Scarce Observations via Data-Adaptive Stochastic Processes

1 code implementation25 Oct 2023 Jiaxu Cui, Bingyi Sun, Jiming Liu, Bo Yang

Learning network dynamics from the empirical structure and spatio-temporal observation data is crucial to revealing the interaction mechanisms of complex networks in a wide range of domains.

Computational Efficiency

Learning Generalizable Agents via Saliency-Guided Features Decorrelation

no code implementations NeurIPS 2023 Sili Huang, Yanchao Sun, Jifeng Hu, Siyuan Guo, Hechang Chen, Yi Chang, Lichao Sun, Bo Yang

Our experimental results demonstrate that SGFD can generalize well on a wide range of test environments and significantly outperforms state-of-the-art methods in handling both task-irrelevant variations and task-relevant variations.

Reinforcement Learning (RL)

Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4

1 code implementation29 Sep 2023 Jiaxian Guo, Bo Yang, Paul Yoo, Bill Yuchen Lin, Yusuke Iwasawa, Yutaka Matsuo

Unlike perfect information games, where all elements are known to every player, imperfect information games emulate the real-world complexities of decision-making under uncertain or incomplete information.

Card Games Decision Making +1

Analysis and Experimental Validation of the WPT Efficiency of the Both-Sides Retrodirective System

no code implementations25 Sep 2023 Charleston Dale M. Ambatali, Shinichi Nakasuka, Bo Yang, Naoki Shinohara

The retrodirective antenna array is considered as a mechanism to enable target tracking of a power receiver for long range wireless power transfer (WPT) due to its simplicity in implementation using only analog circuits.

A Novel Neural-symbolic System under Statistical Relational Learning

no code implementations16 Sep 2023 Dongran Yu, Xueyan Liu, Shirui Pan, Anchen Li, Bo Yang

A key objective in field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities.

Relational Reasoning

A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading

1 code implementation2 Sep 2023 Ruihuai Liang, Bo Yang, Zhiwen Yu, Xuelin Cao, Derrick Wing Kwan Ng, Chau Yuen

To improve the MEC performance, it is required to design an optimal offloading strategy that includes offloading decision (i. e., whether offloading or not) and computational resource allocation of MEC.

Edge-computing Multi-Task Learning

Hydrogen Supply Infrastructure Network Planning Approach towards Chicken-egg Conundrum

no code implementations14 Aug 2023 Haoran Deng, Bo Yang, Mo-Yuen Chow, Gang Yao, Cailian Chen, Xinping Guan

However, there is a strong causality between HFCVs and hydrogen refueling stations (HRSs): the planning decisions of HRSs could affect the hydrogen refueling demand of HFCVs, and the growth of demand would in turn stimulate the further investment in HRSs, which is also known as the ``chicken and egg'' conundrum.

EFLNet: Enhancing Feature Learning for Infrared Small Target Detection

1 code implementation27 Jul 2023 Bo Yang, Xinyu Zhang, Jian Zhang, Jun Luo, Mingliang Zhou, Yangjun Pi

To address this problem, we propose a new adaptive threshold focal loss (ATFL) function that decouples the target and the background, and utilizes the adaptive mechanism to adjust the loss weight to force the model to allocate more attention to target features.

regression

Monadic Deep Learning

no code implementations23 Jul 2023 Bo Yang, Zhihao Zhang Kirisame Marisa, Kai Shi

These dynamically typed deep learning frameworks treat neural networks as differentiable expressions that contain many trainable variable, and perform automatic differentiation on those expressions when training them.

EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detection

no code implementations4 Jun 2023 Guangtao Wang, Jun Li, Jie Xie, Jianhua Xu, Bo Yang

In face detection, low-resolution faces, such as numerous small faces of a human group in a crowded scene, are common in dense face prediction tasks.

Benchmarking Face Detection +1

GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds

1 code implementation CVPR 2023 Zihui Zhang, Bo Yang, Bing Wang, Bo Li

Our method consists of three major components, 1) the feature extractor to learn per-point features from input point clouds, 2) the superpoint constructor to progressively grow the sizes of superpoints, and 3) the semantic primitive clustering module to group superpoints into semantic elements for the final semantic segmentation.

3D Semantic Segmentation Segmentation +1

When Federated Recommendation Meets Cold-Start Problem: Separating Item Attributes and User Interactions

no code implementations22 May 2023 Chunxu Zhang, Guodong Long, Tianyi Zhou, Zijian Zhang, Peng Yan, Bo Yang

However, this separation of the recommendation model and users' private data poses a challenge in providing quality service, particularly when it comes to new items, namely cold-start recommendations in federated settings.

Attribute Federated Learning +1

Do We Need an Encoder-Decoder to Model Dynamical Systems on Networks?

no code implementations20 May 2023 Bing Liu, Wei Luo, Gang Li, Jing Huang, Bo Yang

As deep learning gains popularity in modelling dynamical systems, we expose an underappreciated misunderstanding relevant to modelling dynamics on networks.

Time Series

Graph-guided Personalization for Federated Recommendation

no code implementations13 May 2023 Chunxu Zhang, Guodong Long, Tianyi Zhou, Peng Yan, Zijjian Zhang, Bo Yang

Federated Recommendation is a new service architecture providing recommendations without sharing user data with the server.

NeUDF: Leaning Neural Unsigned Distance Fields with Volume Rendering

no code implementations CVPR 2023 Yu-Tao Liu, Li Wang, Jie Yang, Weikai Chen, Xiaoxu Meng, Bo Yang, Lin Gao

Multi-view shape reconstruction has achieved impressive progresses thanks to the latest advances in neural implicit surface rendering.

Neural Rendering Surface Reconstruction +1

Pretrained Embeddings for E-commerce Machine Learning: When it Fails and Why?

no code implementations9 Apr 2023 Da Xu, Bo Yang

The use of pretrained embeddings has become widespread in modern e-commerce machine learning (ML) systems.

NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Images

1 code implementation CVPR 2023 Xiaoxu Meng, Weikai Chen, Bo Yang

In particular, NeAT represents the 3D surface as a level set of a signed distance function (SDF) with a validity branch for estimating the surface existence probability at the query positions.

Neural Rendering Surface Reconstruction

ADCNet: Learning from Raw Radar Data via Distillation

no code implementations21 Mar 2023 Bo Yang, Ishan Khatri, Michael Happold, Chulong Chen

As autonomous vehicles and advanced driving assistance systems have entered wider deployment, there is an increased interest in building robust perception systems using radars.

Autonomous Driving Pseudo Label

Decoupling Skill Learning from Robotic Control for Generalizable Object Manipulation

no code implementations7 Mar 2023 Kai Lu, Bo Yang, Bing Wang, Andrew Markham

Our experiments on manipulating complex articulated objects show that the proposed approach is more generalizable to unseen objects with large intra-class variations, outperforming previous approaches.

Imitation Learning Reinforcement Learning (RL)

Dual Personalization on Federated Recommendation

1 code implementation16 Jan 2023 Chunxu Zhang, Guodong Long, Tianyi Zhou, Peng Yan, Zijian Zhang, Chengqi Zhang, Bo Yang

Moreover, we provide visualizations and in-depth analysis of the personalization techniques in item embedding, which shed novel insights on the design of recommender systems in federated settings.

Privacy Preserving Recommendation Systems

How to Share: Balancing Layer and Chain Sharing in Industrial Microservice Deployment

no code implementations29 Dec 2022 Yuxiang Liu, Bo Yang, Yu Wu, Cailian Chen, Xinping Guan

However, due to the limited resources of edge servers, it is difficult to meet the optimization goals of the two methods at the same time.

Edge-computing

Text2Struct: A Machine Learning Pipeline for Mining Structured Data from Text

1 code implementation18 Dec 2022 Chaochao Zhou, Bo Yang

However, an annotation scheme and a training dataset have not been available for training machine learning models to mine structured data from text without special templates and patterns.

text annotation

Distributionally Robust Day-ahead Scheduling for Power-traffic Network under a Potential Game Framework

no code implementations4 Dec 2022 Haoran Deng, Bo Yang, Chao Ning, Cailian Chen, Xinping Guan

In order to ensure the individual optimality of the two networks in a unified framework in day-ahead power scheduling, a two-stage distributionally robust centralized optimization model is established to carry out the equilibrium of power-transportation coupled network.

Scheduling

Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images

1 code implementation5 Oct 2022 Yafei Yang, Bo Yang

We firstly introduce four complexity factors to quantitatively measure the distributions of object- and scene-level biases in appearance and geometry for datasets with human annotations.

Object Semantic Segmentation +1

DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images

1 code implementation15 Aug 2022 Bing Wang, Lu Chen, Bo Yang

In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views.

Object

Reconfigurable Intelligent Computational Surfaces: When Wave Propagation Control Meets Computing

no code implementations9 Aug 2022 Bo Yang, Xuelin Cao, Jindan Xu, Chongwen Huang, George C. Alexandropoulos, Linglong Dai, M'erouane Debbah, H. Vincent Poor, Chau Yuen

The envisioned sixth-generation (6G) of wireless networks will involve an intelligent integration of communications and computing, thereby meeting the urgent demands of diverse applications.

Motion Prediction for Beating Heart Surgery with GRU

1 code implementation SSRN 2022 Yiyang Li, Bo Yang, Wanruo Zhang, Wenfeng Zheng, Chao Liu

This work aims to predict the 3D coordinates of the point of interest (POI) on the surface of beating heart in dynamic minimally invasive surgery, which can improve the manoeuvrability of cardiac surgical robots and expand their functions.

motion prediction

Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach

no code implementations NeurIPS 2021 Fan Yang, Kai He, Linxiao Yang, Hongxia Du, Jingbang Yang, Bo Yang, Liang Sun

The learning problem is framed as a subset selection task in which a subset of all possible rules needs to be selected to form an accurate and interpretable rule set.

GR-GAN: Gradual Refinement Text-to-image Generation

1 code implementation23 May 2022 Bo Yang, Fangxiang Feng, Xiaojie Wang

We also introduce a new metric Cross-Model Distance (CMD) for simultaneously evaluating image quality and image-text consistency.

Generative Adversarial Network Image-text matching +3

RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds

2 code implementations19 Apr 2022 Bing Wang, Zhengdi Yu, Bo Yang, Jie Qin, Toby Breckon, Ling Shao, Niki Trigoni, Andrew Markham

We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds.

Semantic Segmentation Surface Reconstruction

Multi-scale Context-aware Network with Transformer for Gait Recognition

1 code implementation ICCV 2021 Duowang Zhu, Xiaohu Huang, Xinggang Wang, Bo Yang, Botao He, Wenyu Liu, Bin Feng

Although gait recognition has drawn increasing research attention recently, since the silhouette differences are quite subtle in spatial domain, temporal feature representation is crucial for gait recognition.

Multiview Gait Recognition Relation

Stack operation of tensor networks

1 code implementation28 Mar 2022 Tianning Zhang, Tianqi Chen, Erping Li, Bo Yang, L. K. Ang

The tensor network, as a facterization of tensors, aims at performing the operations that are common for normal tensors, such as addition, contraction and stacking.

Tensor Networks

On the Advances and Challenges of Adaptive Online Testing

no code implementations15 Mar 2022 Da Xu, Bo Yang

In recent years, the interest in developing adaptive solutions for online testing has grown significantly in the industry.

Towards Robust Off-policy Learning for Runtime Uncertainty

no code implementations27 Feb 2022 Da Xu, Yuting Ye, Chuanwei Ruan, Bo Yang

Off-policy learning plays a pivotal role in optimizing and evaluating policies prior to the online deployment.

Energy Management Based on Multi-Agent Deep Reinforcement Learning for A Multi-Energy Industrial Park

no code implementations8 Feb 2022 Dafeng Zhu, Bo Yang, Yuxiang Liu, Zhaojian Wang, Kai Ma, Xinping Guan

Owing to large industrial energy consumption, industrial production has brought a huge burden to the grid in terms of renewable energy access and power supply.

counterfactual energy management +2

Sentiment-Aware Automatic Speech Recognition pre-training for enhanced Speech Emotion Recognition

no code implementations27 Jan 2022 Ayoub Ghriss, Bo Yang, Viktor Rozgic, Elizabeth Shriberg, Chao Wang

We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more ``emotion aware''.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds

no code implementations12 Jan 2022 Qingyong Hu, Bo Yang, Sheikh Khalid, Wen Xiao, Niki Trigoni, Andrew Markham

Each point in the dataset has been labelled with fine-grained semantic annotations, resulting in a dataset that is three times the size of the previous existing largest photogrammetric point cloud dataset.

CDRec: Cayley-Dickson Recommender

no code implementations16 Dec 2021 Anchen Li, Bo Yang, Huan Huo, Farookh Hussain

In this paper, we propose a recommendation framework named Cayley-Dickson Recommender.

Precise Learning of Source Code Contextual Semantics via Hierarchical Dependence Structure and Graph Attention Networks

no code implementations20 Nov 2021 Zhehao Zhao, Bo Yang, Ge Li, Huai Liu, Zhi Jin

Based on that, we also designed a neural network that depends on the graph attention mechanism. Specifically, we introduced the syntactic structural of the basic block, i. e., its corresponding AST, in source code model to provide sufficient information and fill the gap.

Feature Engineering Graph Attention

A Survey on Neural-symbolic Learning Systems

no code implementations10 Nov 2021 Dongran Yu, Bo Yang, Dayou Liu, Hui Wang, Shirui Pan

In recent years, neural systems have demonstrated highly effective learning ability and superior perception intelligence.

Speech recognition for air traffic control via feature learning and end-to-end training

no code implementations4 Nov 2021 Peng Fan, Dongyue Guo, Yi Lin, Bo Yang, Jianwei Zhang

In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

A Comparative Study of Speaker Role Identification in Air Traffic Communication Using Deep Learning Approaches

no code implementations3 Nov 2021 Dongyue Guo, Jianwei Zhang, Bo Yang, Yi Lin

Most importantly, a multi-modal speaker role identification network (MMSRINet) is designed to achieve the SRI task by considering both the speech and textual modality features.

Binary Classification

OctField: Hierarchical Implicit Functions for 3D Modeling

no code implementations NeurIPS 2021 Jia-Heng Tang, Weikai Chen, Jie Yang, Bo wang, Songrun Liu, Bo Yang, Lin Gao

We achieve this goal by introducing a hierarchical octree structure to adaptively subdivide the 3D space according to the surface occupancy and the richness of part geometry.

How to Leverage Multimodal EHR Data for Better Medical Predictions?

1 code implementation29 Oct 2021 Bo Yang, Lijun Wu

Therefore, in this paper, we first extract the accompanying clinical notes from EHR and propose a method to integrate these data, we also comprehensively study the different models and the data leverage methods for better medical task prediction.

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.

Privacy Preserving Transfer 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

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

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 Automatic Speech Recognition (ASR) +3

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 Automatic Speech Recognition (ASR) +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.

Bug fixing Vulnerability Detection

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

STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?

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

Solid texture synthesis (STS), an effective way to extend a 2D exemplar to a 3D solid volume, exhibits advantages in computational photography.

STS Texture Synthesis

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.

Disentanglement

OPT-GAN: A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution

1 code implementation7 Feb 2021 Minfang Lu, Shuai Ning, Shuangrong Liu, Fengyang Sun, Bo Zhang, Bo Yang, Lin Wang

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

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.

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 Reinforcement Learning (RL)

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.

reinforcement-learning Reinforcement Learning (RL)

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.

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 Position

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

no code implementations28 Sep 2020 Alex Trevithick, Bo Yang

The function models 3D scenes as a general radiance field, which takes a set of 2D images with camera poses and intrinsics as input, constructs an internal representation for each 3D point of the scene, and renders the corresponding appearance and geometry of any 3D point viewing from an arbitrary angle.

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

2 code implementations 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.

Edge-computing

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.

Evolutionary Algorithms

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.

Total Energy

PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization

2 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.

Robotics

Geom-GCN: Geometric Graph Convolutional Networks

4 code implementations 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 on Non-Homophilic (Heterophilic) Graphs Representation Learning +1

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.

Attribute Clustering +1

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 #13 on 3D Instance Segmentation on S3DIS (mPrec metric)

3D Instance Segmentation Clustering +2

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.

Bayesian Optimization 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.

Bayesian Optimization Gaussian Processes +1

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.

Bayesian Optimization General Classification +5

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.

Management Reinforcement Learning (RL)

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.

Clustering

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.

Clustering Multi-class Classification +2

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 +1

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.

Bayesian Optimization

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.

Robotics

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 Object

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 Object

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

10 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).

Clustering Dimensionality Reduction

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.

Clustering Dimensionality Reduction

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