Search Results for author: Yu Zheng

Found 52 papers, 20 papers with code

Rotation-robust Intersection over Union for 3D Object Detection

no code implementations ECCV 2020 Yu Zheng, Danyang Zhang, Sinan Xie, Jiwen Lu, Jie zhou

In this paper, we propose a Rotation-robust Intersection over Union ($ extit{RIoU}$) for 3D object detection, which aims to jointly learn the overlap of rotated bounding boxes.

2D object detection 3D Object Detection

HyperDet3D: Learning a Scene-conditioned 3D Object Detector

no code implementations12 Apr 2022 Yu Zheng, Yueqi Duan, Jiwen Lu, Jie zhou, Qi Tian

A bathtub in a library, a sink in an office, a bed in a laundry room -- the counter-intuition suggests that scene provides important prior knowledge for 3D object detection, which instructs to eliminate the ambiguous detection of similar objects.

3D Object Detection

Deep AutoAugment

1 code implementation11 Mar 2022 Yu Zheng, Zhi Zhang, Shen Yan, Mi Zhang

In this work, instead of fixing a set of hand-picked default augmentations alongside the searched data augmentations, we propose a fully automated approach for data augmentation search named Deep AutoAugment (DeepAA).

AutoML Data Augmentation +1

Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement

2 code implementations10 Mar 2022 Xiuwei Xu, Yifan Wang, Yu Zheng, Yongming Rao, Jie zhou, Jiwen Lu

In this paper, we propose a weakly-supervised approach for 3D object detection, which makes it possible to train a strong 3D detector with position-level annotations (i. e. annotations of object centers).

3D Object Detection Domain Adaptation

Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs

no code implementations17 Feb 2022 Ming Jin, Yu Zheng, Yuan-Fang Li, Siheng Chen, Bin Yang, Shirui Pan

Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction.

Multivariate Time Series Forecasting Time Series +1

Towards Unsupervised Deep Graph Structure Learning

1 code implementation17 Jan 2022 Yixin Liu, Yu Zheng, Daokun Zhang, Hongxu Chen, Hao Peng, Shirui Pan

To solve the unsupervised GSL problem, we propose a novel StrUcture Bootstrapping contrastive LearnIng fraMEwork (SUBLIME for abbreviation) with the aid of self-supervised contrastive learning.

Contrastive Learning Graph structure learning

Crowd-sensing Enhanced Parking Patrol using Trajectories of Sharing Bikes

no code implementations29 Oct 2021 Tianfu He, Jie Bao, Yexin Li, Hui He, Yu Zheng

Illegal vehicle parking is a common urban problem faced by major cities in the world, as it incurs traffic jams, which lead to air pollution and traffic accidents.

Multi-agent Reinforcement Learning

Poformer: A simple pooling transformer for speaker verification

no code implementations10 Oct 2021 Yufeng Ma, Yiwei Ding, Miao Zhao, Yu Zheng, Min Liu, Minqiang Xu

Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network.

Frame Speaker Verification

Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network

1 code implementation8 Oct 2021 Xiyue Zhang, Chao Huang, Yong Xu, Lianghao Xia, Peng Dai, Liefeng Bo, Junbo Zhang, Yu Zheng

Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment.

Traffic Prediction

Enhancing semi-supervised learning via self-interested coalitional learning

no code implementations29 Sep 2021 Huiling Qin, Xianyuan Zhan, Yuanxun li, Haoran Xu, Yu Zheng

Jointly solving these two tasks allows full utilization of information from both labeled and unlabeled data, thus alleviating the problem of over-reliance on labeled data.

Spatiotemporal Representation Learning on Time Series with Dynamic Graph ODEs

no code implementations29 Sep 2021 Ming Jin, Yuan-Fang Li, Yu Zheng, Bin Yang, Shirui Pan

Spatiotemporal representation learning on multivariate time series has received tremendous attention in forecasting traffic and energy data.

Graph structure learning Representation Learning +1

NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction

1 code implementation8 Sep 2021 Yi Sun, Yu Zheng, Chao Hao, Hangping Qiu

Using prompts to utilize language models to perform various downstream tasks, also known as prompt-based learning or prompt-learning, has lately gained significant success in comparison to the pre-train and fine-tune paradigm.

Entity Linking Language Modelling +1

Spatio-Temporal Graph Contrastive Learning

no code implementations26 Aug 2021 Xu Liu, Yuxuan Liang, Yu Zheng, Bryan Hooi, Roger Zimmermann

Second, data augmentations that are used for defeating noise are less explored for STG data.

Contrastive Learning Data Augmentation +2

Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection

no code implementations23 Aug 2021 Yu Zheng, Ming Jin, Yixin Liu, Lianhua Chi, Khoa T. Phan, Yi-Ping Phoebe Chen

While the generative attribute regression module allows us to capture the anomalies in the attribute space, the multi-view contrastive learning module can exploit richer structure information from multiple subgraphs, thus abling to capture the anomalies in the structure space, mixing of structure, and attribute information.

Anomaly Detection Contrastive Learning +1

DGCN: Diversified Recommendation with Graph Convolutional Networks

1 code implementation16 Aug 2021 Yu Zheng, Chen Gao, Liang Chen, Depeng Jin, Yong Li

These years much effort has been devoted to improving the accuracy or relevance of the recommendation system.

Collaborative Filtering

Sequential Recommendation with Graph Neural Networks

1 code implementation27 Jun 2021 Jianxin Chang, Chen Gao, Yu Zheng, Yiqun Hui, Yanan Niu, Yang song, Depeng Jin, Yong Li

This helps explicitly distinguish users' core interests, by forming dense clusters in the interest graph.

Metric Learning Sequential Recommendation

CSCAD: Correlation Structure-based Collective Anomaly Detection in Complex System

no code implementations30 May 2021 Huiling Qin, Xianyuan Zhan, Yu Zheng

We propose a correlation structure-based collective anomaly detection (CSCAD) model for high-dimensional anomaly detection problem in large systems, which is also generalizable to semi-supervised or supervised settings.

Anomaly Detection

DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning

no code implementations23 Feb 2021 Xianyuan Zhan, Haoran Xu, Yue Zhang, Xiangyu Zhu, Honglei Yin, Yu Zheng

Optimizing the combustion efficiency of a thermal power generating unit (TPGU) is a highly challenging and critical task in the energy industry.

Continuous Control Offline RL +1

Topological Transformations in Pentagonal 2D Materials Induced by Stone-Wales Defects

no code implementations22 Dec 2020 Yu Zheng, Duyu Chen, Lei Liu, Houlong Zhuang, Yang Jiao

We discover two distinct topological pathways through which the pentagonal Cairo tiling (P5), a structural model for single-layer $AB_2$ pyrite materials, respectively transforms into a crystalline rhombus-hexagon (C46) tiling and random rhombus-pentagon-hexagon (R456) tilings, by continuously introducing the Stone-Wales (SW) topological defects.

Soft Condensed Matter Disordered Systems and Neural Networks Materials Science

Disentangling User Interest and Conformity for Recommendation with Causal Embedding

2 code implementations19 Jun 2020 Yu Zheng, Chen Gao, Xiang Li, Xiangnan He, Depeng Jin, Yong Li

We further demonstrate that the learned embeddings successfully capture the desired causes, and show that DICE guarantees the robustness and interpretability of recommendation.

Causal Inference

Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?

1 code implementation NeurIPS 2020 Shen Yan, Yu Zheng, Wei Ao, Xiao Zeng, Mi Zhang

Existing Neural Architecture Search (NAS) methods either encode neural architectures using discrete encodings that do not scale well, or adopt supervised learning-based methods to jointly learn architecture representations and optimize architecture search on such representations which incurs search bias.

Neural Architecture Search

Urban Anomaly Analytics: Description, Detection, and Prediction

no code implementations25 Apr 2020 Mingyang Zhang, Tong Li, Yue Yu, Yong Li, Pan Hui, Yu Zheng

Urban anomalies may result in loss of life or property if not handled properly.

Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment

no code implementations CVPR 2020 Qiuyu Chen, Wei zhang, Ning Zhou, Peng Lei, Yi Xu, Yu Zheng, Jianping Fan

Specifically, the fractional dilated kernel is adaptively constructed according to the image aspect ratios, where the interpolation of nearest two integers dilated kernels is used to cope with the misalignment of fractional sampling.

Price-aware Recommendation with Graph Convolutional Networks

1 code implementation9 Mar 2020 Yu Zheng, Chen Gao, Xiangnan He, Yong Li, Depeng Jin

Price, an important factor in marketing --- which determines whether a user will make the final purchase decision on an item --- surprisingly, has received relatively little scrutiny.

Collaborative Filtering Recommendation Systems

Revisiting Convolutional Neural Networks for Citywide Crowd Flow Analytics

1 code implementation28 Feb 2020 Yuxuan Liang, Kun Ouyang, Yiwei Wang, Ye Liu, Junbo Zhang, Yu Zheng, David S. Rosenblum

This framework consists of three parts: 1) a local feature extraction module to learn representations for each region; 2) a global context module to extract global contextual priors and upsample them to generate the global features; and 3) a region-specific predictor based on tensor decomposition to provide customized predictions for each region, which is very parameter-efficient compared to previous methods.

Tensor Decomposition

Federated Extra-Trees with Privacy Preserving

no code implementations18 Feb 2020 Yang Liu, Mingxin Chen, Wenxi Zhang, Junbo Zhang, Yu Zheng

It is commonly observed that the data are scattered everywhere and difficult to be centralized.

Fine-Grained Urban Flow Inference

1 code implementation5 Feb 2020 Kun Ouyang, Yuxuan Liang, Ye Liu, Zekun Tong, Sijie Ruan, Yu Zheng, David S. Rosenblum

To tackle these issues, we develop a model entitled UrbanFM which consists of two major parts: 1) an inference network to generate fine-grained flow distributions from coarse-grained inputs that uses a feature extraction module and a novel distributional upsampling module; 2) a general fusion subnet to further boost the performance by considering the influence of different external factors.

Index Tracking with Cardinality Constraints: A Stochastic Neural Networks Approach

no code implementations12 Nov 2019 Yu Zheng, Bowei Chen, Timothy M. Hospedales, Yongxin Yang

Compared with the benchmarked models, our model has the lowest tracking error, across a range of portfolio sizes.

HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking

no code implementations31 Aug 2019 Shen Yan, Biyi Fang, Faen Zhang, Yu Zheng, Xiao Zeng, Hui Xu, Mi Zhang

Without the constraint imposed by the hand-designed heuristics, our searched networks contain more flexible and meaningful architectures that existing weight sharing based NAS approaches are not able to discover.

Neural Architecture Search

Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning

1 code implementation KDD '19 2019 Zheyi Pan, Yuxuan Liang, Weifeng Wang, Yong Yu, Yu Zheng, Junbo Zhang

Predicting urban traffic is of great importance to intelligent transportation systems and public safety, yet is very challenging because of two aspects: 1) complex spatio-temporal correlations of urban traffic, including spatial correlations between locations along with temporal correlations among timestamps; 2) diversity of such spatiotemporal correlations, which vary from location to location and depend on the surrounding geographical information, e. g., points of interests and road networks.

Graph Attention Meta-Learning +3

Reward Advancement: Transforming Policy under Maximum Causal Entropy Principle

no code implementations11 Jul 2019 Guojun Wu, Yanhua Li, Zhenming Liu, Jie Bao, Yu Zheng, Jieping Ye, Jun Luo

In this paper, we define and investigate a general reward trans-formation problem (namely, reward advancement): Recovering the range of additional reward functions that transform the agent's policy from original policy to a predefined target policy under MCE principle.

Decision Making

Federated Forest

no code implementations24 May 2019 Yang Liu, Yingting Liu, Zhijie Liu, Junbo Zhang, Chuishi Meng, Yu Zheng

In this paper, we tackle these challenges and propose a privacy-preserving machine learning model, called Federated Forest, which is a lossless learning model of the traditional random forest method, i. e., achieving the same level of accuracy as the non-privacy-preserving approach.

Modeling cell migration regulated by cell-ECM micromechanical coupling

no code implementations16 May 2019 Yu Zheng, Hanqing Nan, Qihui Fan, Xiaochen Wang, LiYu Liu, Ruchuan Liu, Fangfu Ye, Bo Sun, Yang Jiao

During migration, individual cells can generate active pulling forces via actin filament contraction, which are transmitted to the ECM fibers through focal adhesion complexes, remodel the ECM, and eventually propagate to and can be sensed by other cells in the system.

Incorporating prior financial domain knowledge into neural networks for implied volatility surface prediction

no code implementations29 Apr 2019 Yu Zheng, Yongxin Yang, Bo-Wei Chen

This is one of the very first studies which discuss a methodological framework that incorporates prior financial domain knowledge into neural network architecture design and model training.

Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networks

no code implementations19 Mar 2019 Junkai Sun, Junbo Zhang, Qiaofei Li, Xiuwen Yi, Yuxuan Liang, Yu Zheng

In this paper, we formulate crowd flow forecasting in irregular regions as a spatio-temporal graph (STG) prediction problem in which each node represents a region with time-varying flows.

COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis

no code implementations CVPR 2019 Yansong Tang, Dajun Ding, Yongming Rao, Yu Zheng, Danyang Zhang, Lili Zhao, Jiwen Lu, Jie zhou

There are substantial instructional videos on the Internet, which enables us to acquire knowledge for completing various tasks.

Action Detection

UrbanFM: Inferring Fine-Grained Urban Flows

1 code implementation6 Feb 2019 Yuxuan Liang, Kun Ouyang, Lin Jing, Sijie Ruan, Ye Liu, Junbo Zhang, David S. Rosenblum, Yu Zheng

In this paper, we aim to infer the real-time and fine-grained crowd flows throughout a city based on coarse-grained observations.

Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting

3 code implementations22 Dec 2018 Bin Wang, Jie Lu, Zheng Yan, Huaishao Luo, Tianrui Li, Yu Zheng, Guangquan Zhang

We cast the weather forecasting problem as an end-to-end deep learning problem and solve it by proposing a novel negative log-likelihood error (NLE) loss function.

Weather Forecasting

HyperST-Net: Hypernetworks for Spatio-Temporal Forecasting

no code implementations28 Sep 2018 Zheyi Pan, Yuxuan Liang, Junbo Zhang, Xiuwen Yi, Yong Yu, Yu Zheng

In this paper, we propose a general framework (HyperST-Net) based on hypernetworks for deep ST models.

Spatio-Temporal Forecasting Time Series

Diversity and Sparsity: A New Perspective on Index Tracking

no code implementations6 Sep 2018 Yu Zheng, Timothy M. Hospedales, Yongxin Yang

We introduce the first index tracking method that explicitly optimises both diversity and sparsity in a single joint framework.

Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks

no code implementations10 Jan 2017 Junbo Zhang, Yu Zheng, Dekang Qi, Ruiyuan Li, Xiuwen Yi, Tianrui Li

We propose a deep-learning-based approach, called ST-ResNet, to collectively forecast two types of crowd flows (i. e. inflow and outflow) in each and every region of a city.

pg-Causality: Identifying Spatiotemporal Causal Pathways for Air Pollutants with Urban Big Data

no code implementations22 Oct 2016 Julie Yixuan Zhu, Chao Zhang, Huichu Zhang, Shi Zhi, Victor O. K. Li, Jiawei Han, Yu Zheng

Therefore, we present \emph{p-Causality}, a novel pattern-aided causality analysis approach that combines the strengths of \emph{pattern mining} and \emph{Bayesian learning} to efficiently and faithfully identify the \emph{ST causal pathways}.

Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction

3 code implementations1 Oct 2016 Junbo Zhang, Yu Zheng, Dekang Qi

The aggregation is further combined with external factors, such as weather and day of the week, to predict the final traffic of crowds in each and every region.

Crowd Flows Prediction

Gated Neural Networks for Option Pricing: Rationality by Design

1 code implementation14 Sep 2016 Yongxin Yang, Yu Zheng, Timothy M. Hospedales

We propose a neural network approach to price EU call options that significantly outperforms some existing pricing models and comes with guarantees that its predictions are economically reasonable.

ST-MVL: Filling Missing Values in Geo-Sensory Time Series Data

no code implementations IJCAI 2016 2016 Xiuwen Yi, Yu Zheng, Junbo Zhang, Tianrui Li

In this paper, we propose a spatio-temporal multi-view-based learning (ST-MVL) method to collectively fill missing readings in a collection of geosensory time series data, considering 1) the temporal correlation between readings at different timestamps in the same series and 2) the spatial correlation between different time series.

Collaborative Filtering Multivariate Time Series Imputation +2

T-Drive: Driving Directions Based on Taxi Trajectories

no code implementations ACM SIGSPATIAL GIS 2010 2010 Jing Yuan, Yu Zheng, Chengyang Zhang, Wenlei Xie, Xing Xie, Guangzhong Sun, Yan Huang

GPS-equipped taxis can be regarded as mobile sensors probing traffic flows on road surfaces, and taxi drivers are usually experienced in finding the fastest (quickest) route to a destination based on their knowledge.

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