Search Results for author: Lei Shi

Found 50 papers, 9 papers with code

Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition

1 code implementation ECCV 2020 Ke Cheng, Yifan Zhang, Congqi Cao, Lei Shi, Jian Cheng, Hanqing Lu

Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem for industrial deployment.

Action Recognition Skeleton Based Action Recognition

Solving parametric partial differential equations with deep rectified quadratic unit neural networks

no code implementations14 Mar 2022 Zhen Lei, Lei Shi, Chenyu Zeng

In this study, we investigate the expressive power of deep rectified quadratic unit (ReQU) neural networks for approximating the solution maps of parametric PDEs.

Learning with Asymmetric Kernels: Least Squares and Feature Interpretation

no code implementations3 Feb 2022 Mingzhen He, Fan He, Lei Shi, Xiaolin Huang, Johan A. K. Suykens

Asymmetric kernels naturally exist in real life, e. g., for conditional probability and directed graphs.

Few-shot Learning Based on Multi-stage Transfer and Class-Balanced Loss for Diabetic Retinopathy Grading

no code implementations24 Sep 2021 Lei Shi, Junxing Zhang

The experimental results show that the application of multi-stage transfer and class-balanced loss function can effectively improve the grading performance metrics such as accuracy and quadratic weighted kappa.

Diabetic Retinopathy Grading Few-Shot Learning +2

Dense Contrastive Visual-Linguistic Pretraining

no code implementations24 Sep 2021 Lei Shi, Kai Shuang, Shijie Geng, Peng Gao, Zuohui Fu, Gerard de Melo, Yunpeng Chen, Sen Su

To overcome these issues, we propose unbiased Dense Contrastive Visual-Linguistic Pretraining (DCVLP), which replaces the region regression and classification with cross-modality region contrastive learning that requires no annotations.

Contrastive Learning Data Augmentation +1

Provably Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs

no code implementations26 Jul 2021 Zhuoqing Song, Lei Shi, Shi Pu, Ming Yan

In this work, we consider the decentralized optimization problem in which a network of $n$ agents, each possessing a smooth and convex objective function, wish to collaboratively minimize the average of all the objective functions through peer-to-peer communication in a directed graph.

Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks

no code implementations14 Jun 2021 Zhuoqing Song, Lei Shi, Shi Pu, Ming Yan

The second algorithm is a broadcast-like version of CPP (B-CPP), and it also achieves linear convergence rate under the same conditions on the objective functions.

Multi-modal Scene-compliant User Intention Estimation in Navigation

no code implementations13 Jun 2021 Kavindie Katuwandeniya, Stefan H. Kiss, Lei Shi, Jaime Valls Miro

A multi-modal framework to generate user intention distributions when operating a mobile vehicle is proposed in this work.

Exploring Bayesian Deep Learning for Urgent Instructor Intervention Need in MOOC Forums

no code implementations26 Apr 2021 Jialin Yu, Laila Alrajhi, Anoushka Harit, Zhongtian Sun, Alexandra I. Cristea, Lei Shi

Learners may post their feelings of confusion and struggle in the respective MOOC forums, but with the large volume of posts and high workloads for MOOC instructors, it is unlikely that the instructors can identify all learners requiring intervention.

Variational Inference

AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition

no code implementations ICCV 2021 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Existing methods for skeleton-based action recognition mainly focus on improving the recognition accuracy, whereas the efficiency of the model is rarely considered.

Action Recognition Skeleton Based Action Recognition

Topological charge engineering in lasing bound states in continuum

no code implementations31 Dec 2020 Sughra Mohamed, Jie Wang, Heikki Rekola, Janne Heikkinen, Benjamin Asamoah, Lei Shi, Tommi K. Hakala

We experimentally analyze all four observed lasing BICs by imaging their far-field polarization vortices and their associated topological charges.


Fast algorithms for robust principal component analysis with an upper bound on the rank

1 code implementation18 Aug 2020 Ningyu Sha, Lei Shi, Ming Yan

The first type of algorithm applies regularization terms on the singular values of a matrix to obtain a low-rank matrix.

Predicting MOOCs Dropout Using Only Two Easily Obtainable Features from the First Week's Activities

no code implementations12 Aug 2020 Ahmed Alamri, Mohammad Alshehri, Alexandra I. Cristea, Filipe D. Pereira, Elaine Oliveira, Lei Shi, Craig Stewart

While Massive Open Online Course (MOOCs) platforms provide knowledge in a new and unique way, the very high number of dropouts is a significant drawback.

Social Interactions Clustering MOOC Students: An Exploratory Study

no code implementations10 Aug 2020 Lei Shi, Alexandra Cristea, Ahmad Alamri, Armando M. Toda, Wilk Oliveira

An exploratory study on social interactions of MOOC students in FutureLearn was conducted, to answer "how can we cluster students based on their social interactions?"

Contrastive Visual-Linguistic Pretraining

no code implementations26 Jul 2020 Lei Shi, Kai Shuang, Shijie Geng, Peng Su, Zhengkai Jiang, Peng Gao, Zuohui Fu, Gerard de Melo, Sen Su

We evaluate CVLP on several down-stream tasks, including VQA, GQA and NLVR2 to validate the superiority of contrastive learning on multi-modality representation learning.

Contrastive Learning Representation Learning +2

Leader-Driven Opinion Dynamics in Signed Social Networks With Asynchronous Trust/Distrust Level Evolution

no code implementations19 Jul 2020 Lei Shi, Yuhua Cheng, Jinliang Shao, Xiaofan Wang, Hanmin Sheng

Trust and distrust are common in the opinion interactions among agents in social networks, and they are described by the edges with positive and negative weights in the signed digraph, respectively.

Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition

1 code implementation7 Jul 2020 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Besides, from the data aspect, we introduce a skeletal data decoupling technique to emphasize the specific characteristics of space/time and different motion scales, resulting in a more comprehensive understanding of the human actions. To test the effectiveness of the proposed method, extensive experiments are conducted on four challenging datasets for skeleton-based gesture and action recognition, namely, SHREC, DHG, NTU-60 and NTU-120, where DSTA-Net achieves state-of-the-art performance on all of them.

Action Recognition Skeleton Based Action Recognition

Analysis of Regularized Least Squares in Reproducing Kernel Krein Spaces

no code implementations1 Jun 2020 Fanghui Liu, Lei Shi, Xiaolin Huang, Jie Yang, Johan A. K. Suykens

In this paper, we study the asymptotic properties of regularized least squares with indefinite kernels in reproducing kernel Krein spaces (RKKS).

What and Where: Modeling Skeletons from Semantic and Spatial Perspectives for Action Recognition

no code implementations7 Apr 2020 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

The two perspectives are orthogonal and complementary to each other; and by fusing them in a unified framework, our method achieves a more comprehensive understanding of the skeleton data.

Action Recognition Skeleton Based Action Recognition

Sub/super-stochastic matrix with applications to bipartite tracking control over signed networks

no code implementations4 Apr 2020 Lei Shi, Wei Xing Zheng, Jinliang Shao, Yuhua Cheng

In the first part, we examine the dynamics of bipartite tracking for first-order MASs, second-order MASs and general linear MASs in the presence of asynchronous interactions, respectively.

Mobility Inference on Long-Tailed Sparse Trajectory

no code implementations21 Jan 2020 Lei Shi

How can we infer such a mobility model from the single trajectory information?

Multi-Layer Content Interaction Through Quaternion Product For Visual Question Answering

no code implementations3 Jan 2020 Lei Shi, Shijie Geng, Kai Shuang, Chiori Hori, Songxiang Liu, Peng Gao, Sen Su

To solve the issue for the intermediate layers, we propose an efficient Quaternion Block Network (QBN) to learn interaction not only for the last layer but also for all intermediate layers simultaneously.

Question Answering Video Description +2

Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks

2 code implementations15 Dec 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Second, the second-order information of the skeleton data, i. e., the length and orientation of the bones, is rarely investigated, which is naturally more informative and discriminative for the human action recognition.

Action Recognition graph construction +1

Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision

no code implementations28 Nov 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

Existing methods exploit the joint positions to extract the body-part features from the activation map of the convolutional networks to assist human action recognition.

Action Recognition Skeleton Based Action Recognition

Non-Local Graph Convolutional Networks for Skeleton-Based Action Recognition

1 code implementation arXiv 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

However, the topology of the graph is set by hand and fixed over all layers, which may be not optimal for the action recognition task and the hierarchical CNN structures.

Action Recognition Skeleton Based Action Recognition

Gaussian Mixture Marginal Distributions for Modelling Remaining Pipe Wall Thickness of Critical Water Mains in Non-Destructive Evaluation

no code implementations2 Jul 2019 Linh Nguyen, Jaime Valls Miro, Lei Shi, Teresa Vidal-Calleja

Rapidly estimating the remaining wall thickness (RWT) is paramount for the non-destructive condition assessment evaluation of large critical metallic pipelines.

Gaussian Processes

Skeleton-Based Action Recognition With Directed Graph Neural Networks

1 code implementation CVPR 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

The skeleton data have been widely used for the action recognition tasks since they can robustly accommodate dynamic circumstances and complex backgrounds.

Action Recognition Skeleton Based Action Recognition

Fine-Grained Named Entity Recognition using ELMo and Wikidata

1 code implementation23 Apr 2019 Cihan Dogan, Aimore Dutra, Adam Gara, Alfredo Gemma, Lei Shi, Michael Sigamani, Ella Walters

Fine-grained Named Entity Recognition is a task whereby we detect and classify entity mentions to a large set of types.

Named Entity Recognition

MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks

1 code implementation15 Jan 2019 Dan Li, Dacheng Chen, Lei Shi, Baihong Jin, Jonathan Goh, See-Kiong Ng

The prevalence of networked sensors and actuators in many real-world systems such as smart buildings, factories, power plants, and data centers generate substantial amounts of multivariate time series data for these systems.

Anomaly Detection Time Series

Realizing data features by deep nets

no code implementations1 Jan 2019 Zheng-Chu Guo, Lei Shi, Shao-Bo Lin

Based on refined covering number estimates, we find that, to realize some complex data features, deep nets can improve the performances of shallow neural networks (shallow nets for short) without requiring additional capacity costs.

Generalization Properties of hyper-RKHS and its Applications

no code implementations26 Sep 2018 Fanghui Liu, Lei Shi, Xiaolin Huang, Jie Yang, Johan A. K. Suykens

This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample extensions, and proves asymptotic convergence results for the introduced regression models in an approximation theory view.

Learning Theory

Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

4 code implementations CVPR 2019 Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu

In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods.

Action Recognition graph construction +1

Fast and Strong Convergence of Online Learning Algorithms

no code implementations10 Oct 2017 Zheng-Chu Guo, Lei Shi

In this paper, we study the online learning algorithm without explicit regularization terms.

online learning

Convergence of Unregularized Online Learning Algorithms

no code implementations9 Aug 2017 Yunwen Lei, Lei Shi, Zheng-Chu Guo

In this paper we study the convergence of online gradient descent algorithms in reproducing kernel Hilbert spaces (RKHSs) without regularization.

online learning

Learning Theory of Distributed Regression with Bias Corrected Regularization Kernel Network

no code implementations7 Aug 2017 Zheng-Chu Guo, Lei Shi, Qiang Wu

Regularization kernel network is an effective and widely used method for nonlinear regression analysis.

Learning Theory

Real-time 3D Human Tracking for Mobile Robots with Multisensors

no code implementations15 Mar 2017 Mengmeng Wang, Daobilige Su, Lei Shi, Yong liu, Jaime Valls Miro

An ultrasonic sensor array is employed to provide the range information from the target person to the robot and Gaussian Process Regression is used for partial location estimation (2-D).

Visual Tracking

Mixed one-bit compressive sensing with applications to overexposure correction for CT reconstruction

no code implementations3 Jan 2017 Xiaolin Huang, Yan Xia, Lei Shi, Yixing Huang, Ming Yan, Joachim Hornegger, Andreas Maier

Aiming at overexposure correction for computed tomography (CT) reconstruction, we in this paper propose a mixed one-bit compressive sensing (M1bit-CS) to acquire information from both regular and saturated measurements.

Compressive Sensing Computed Tomography (CT) +1

Latent Topic Embedding

no code implementations COLING 2016 Di Jiang, Lei Shi, Rongzhong Lian, Hua Wu

Topic modeling and word embedding are two important techniques for deriving latent semantics from data.

Topic Models Word Embeddings

A Novel Artificial Fish Swarm Algorithm for Pattern Recognition with Convex Optimization

no code implementations1 Dec 2016 Lei Shi, Rui Guo, Yuchen Ma

Among these parameters, visual and step are very significant in view of the fact that artificial fish basically move based on these parameters.

Functional Hashing for Compressing Neural Networks

no code implementations20 May 2016 Lei Shi, Shikun Feng, ZhifanZhu

As the complexity of deep neural networks (DNNs) trend to grow to absorb the increasing sizes of data, memory and energy consumption has been receiving more and more attentions for industrial applications, especially on mobile devices.

Understand Scene Categories by Objects: A Semantic Regularized Scene Classifier Using Convolutional Neural Networks

no code implementations22 Sep 2015 Yiyi Liao, Sarath Kodagoda, Yue Wang, Lei Shi, Yong liu

As scene images have larger diversity than the iconic object images, it is more challenging for deep learning methods to automatically learn features from scene images with less samples.

General Classification Scene Classification +2

Place classification with a graph regularized deep neural network model

no code implementations12 Jun 2015 Yiyi Liao, Sarath Kodagoda, Yue Wang, Lei Shi, Yong liu

Furthermore, results show that the features automatically learned from the raw input range data can achieve competitive results to the features constructed based on statistical and geometrical information.

General Classification

Large Scale Purchase Prediction with Historical User Actions on B2C Online Retail Platform

no code implementations27 Aug 2014 Yuyu Zhang, Liang Pang, Lei Shi, Bin Wang

This paper describes the solution of Bazinga Team for Tmall Recommendation Prize 2014.

Sparse Additive Text Models with Low Rank Background

no code implementations NeurIPS 2013 Lei Shi

This paper extends to propose sparse additive model with low rank background (SAM-LRB), and simple yet efficient estimation.

Bayesian Probabilistic Co-Subspace Addition

no code implementations NeurIPS 2012 Lei Shi

Furthermore, PCSA is extended to tackling and filling missing values, to adapting its sparseness, and to modelling tensor data.

Variational Inference

Neural Implementation of Hierarchical Bayesian Inference by Importance Sampling

no code implementations NeurIPS 2009 Lei Shi, Thomas L. Griffiths

Here we propose a simple mechanism for Bayesian inference which involves averaging over a few feature detection neurons which fire at a rate determined by their similarity to a sensory stimulus.

Bayesian Inference

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