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.
no code implementations • 12 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.
1 code implementation • 11 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).
Ranked #1 on
Data Augmentation
on ImageNet
2 code implementations • 10 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).
1 code implementation • 26 Feb 2022 • Yu Zheng, Chen Gao, Jianxin Chang, Yanan Niu, Yang song, Depeng Jin, Yong Li
Modeling user's long-term and short-term interests is crucial for accurate recommendation.
no code implementations • 17 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.
no code implementations • 11 Feb 2022 • Yu Zheng, Ming Jin, Yixin Liu, Lianhua Chi, Khoa T. Phan, Shirui Pan, Yi-Ping Phoebe Chen
Anomaly detection from graph data is an important data mining task in many applications such as social networks, finance, and e-commerce.
1 code implementation • 17 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.
no code implementations • 29 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.
no code implementations • 10 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.
1 code implementation • 8 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.
no code implementations • 29 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.
no code implementations • 29 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.
1 code implementation • submitted to TOIS 2021 • Chen Gao, Yu Zheng, Nian Li, Yinfeng Li, Yingrong Qin, Jinghua Piao, Yuhan Quan, Jianxin Chang, Depeng Jin, Xiangnan He, Yong Li
Recommender system is one of the most important information services on today's Internet.
no code implementations • 20 Sep 2021 • Tianfu He, Guochun Chen, Chuishi Meng, Huajun He, Zheyi Pan, Yexin Li, Sijie Ruan, Huimin Ren, Ye Yuan, Ruiyuan Li, Junbo Zhang, Jie Bao, Hui He, Yu Zheng
People often refer to a place of interest (POI) by an alias.
1 code implementation • 8 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.
no code implementations • 26 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.
no code implementations • 23 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.
1 code implementation • 16 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.
1 code implementation • 27 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.
no code implementations • 30 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.
no code implementations • 16 May 2021 • Dandan Zhang, Yu Zheng, Qiang Li, Lei Wei, Dongsheng Zhang, Zhengyou Zhang
To accurately pour drinks into various containers is an essential skill for service robots.
3 code implementations • 27 Feb 2021 • Yixin Liu, Ming Jin, Shirui Pan, Chuan Zhou, Yu Zheng, Feng Xia, Philip S. Yu
Deep learning on graphs has attracted significant interests recently.
no code implementations • 23 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.
no code implementations • 22 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
2 code implementations • 19 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.
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.
no code implementations • 25 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.
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.
1 code implementation • 9 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.
1 code implementation • 28 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.
no code implementations • 18 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.
1 code implementation • 5 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.
no code implementations • 12 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.
no code implementations • 31 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.
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.
no code implementations • 11 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.
no code implementations • 24 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.
no code implementations • 16 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.
no code implementations • 29 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.
no code implementations • 19 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.
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.
1 code implementation • 6 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.
3 code implementations • 22 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.
no code implementations • 28 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.
no code implementations • 6 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.
no code implementations • 10 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.
no code implementations • 22 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}.
3 code implementations • 1 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.
1 code implementation • 14 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.
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
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.