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.
no code implementations • 31 Mar 2025 • Yijie Zheng, Bangjun Xiao, Lei Shi, Xiaoyang Li, Faming Wu, Tianyu Li, Xuefeng Xiao, Yang Zhang, Yuxuan Wang, Shouda Liu
Multimodal large language models (MLLMs), such as GPT-4o, are garnering significant attention.
no code implementations • 19 Mar 2025 • Lei Shi, Xi Fang, Naiyu Wang, Junxing Zhang
The performance of our method approaches that of the fully supervised method and outperforms several existing weakly supervised methods.
no code implementations • 9 Mar 2025 • Lei Shi, Andreas Bulling
By evaluating ablated versions of our method, we further show that the proposed integration of the action and observation representations learnt in the VAE latent space is key to these performance improvements.
no code implementations • 19 Feb 2025 • Fengjie Wang, Chengming Liu, Pang Haibo, Lei Shi
To achieve this, we introduce the Synergy Scoring Filter (SSFilter), the first fully unsupervised anomaly detection approach to leverage sample-level filtering.
1 code implementation • 13 Feb 2025 • Yuankai Luo, Lei Shi, Xiao-Ming Wu
Message-passing Graph Neural Networks (GNNs) are often criticized for their limited expressiveness, issues like over-smoothing and over-squashing, and challenges in capturing long-range dependencies, while Graph Transformers (GTs) are considered superior due to their global attention mechanisms.
Ranked #1 on
Graph Property Prediction
on ogbg-ppa
1 code implementation • 21 Jan 2025 • Zhili Cheng, Yuge Tu, Ran Li, Shiqi Dai, Jinyi Hu, Shengding Hu, Jiahao Li, Yang Shi, Tianyu Yu, Weize Chen, Lei Shi, Maosong Sun
To address this, we propose EmbodiedEval, a comprehensive and interactive evaluation benchmark for MLLMs with embodied tasks.
no code implementations • 20 Jan 2025 • Zhaoxing Li, Vahid Yazdanpanah, Jindi Wang, Wen Gu, Lei Shi, Alexandra I. Cristea, Sarah Kiden, Sebastian Stein
The integration of AI in education offers significant potential to enhance learning efficiency.
no code implementations • 14 Jan 2025 • Longtao Jiang, Zhendong Wang, Jianmin Bao, Wengang Zhou, Dongdong Chen, Lei Shi, Dong Chen, Houqiang Li
This paradigm retains the masked region in the input, using it as guidance for the removal process.
no code implementations • 12 Dec 2024 • Ting Xiao, Lei Shi, Peng Liu, Zhe Wang, Chenjia Bai
Next, the RRG model is optimized to align with the preference vector by optimizing such a reward via RL.
1 code implementation • 6 Dec 2024 • Ye Sun, Lei Shi, Yongxin Tong
Link prediction (LP) is crucial for Knowledge Graphs (KG) completion but commonly suffers from interpretability issues.
no code implementations • 21 Oct 2024 • Guanhang Lei, Zhen Lei, Lei Shi
In this paper, we focus on solving the long-time integration of nonlinear wave equations via neural operators by replacing the initial condition with the prediction in a recurrent manner.
no code implementations • 18 Oct 2024 • Weichun Xia, Jiaxin Jiang, Lei Shi
We introduce a novel diffusion-based spectral algorithm to tackle regression analysis on high-dimensional data, particularly data embedded within lower-dimensional manifolds.
no code implementations • 3 Oct 2024 • Jiading Liu, Lei Shi
This demonstrates that the proposed regularity conditions are reasonable and that the convergence analysis under these conditions is tight, capturing the essential characteristics of functional linear regression.
no code implementations • 2 Oct 2024 • JinHui Bai, Lei Shi
Inspired by the structure of spherical harmonics, we propose the truncated kernel stochastic gradient descent (T-kernel SGD) algorithm with a least-square loss function for spherical data fitting.
no code implementations • 29 Sep 2024 • Zhen Wang, Ruiqi Song, Chen Shen, Shiya Yin, Zhao Song, Balaraju Battu, Lei Shi, Danyang Jia, Talal Rahwan, Shuyue Hu
We design three types of LLMs: (i) Cooperative, aiming to assist its human associate; (ii) Selfish, focusing solely on maximizing its self-interest; and (iii) Fair, balancing its own and collective interest, while slightly prioritizing self-interest.
1 code implementation • 16 Aug 2024 • Zhonghang Li, Long Xia, Lei Shi, Yong Xu, Dawei Yin, Chao Huang
Accurate traffic forecasting is crucial for effective urban planning and transportation management, enabling efficient resource allocation and enhanced travel experiences.
no code implementations • 6 Aug 2024 • Lei Shi, Zhimeng Liu, Yi Yang, Weize Wu, Yuyang Zhang, Hongbo Zhang, Jing Lin, Siyu Wu, Zihan Chen, Ruiming Li, Nan Wang, Zipeng Liu, Huobin Tan, Hongyi Gao, Yue Zhang, Ge Wang
The extraction of Metal-Organic Frameworks (MOFs) synthesis conditions from literature text has been challenging but crucial for the logical design of new MOFs with desirable functionality.
no code implementations • 10 Jul 2024 • Dinghao Cao, Zheng-Chu Guo, Lei Shi
This paper presents a comprehensive study on the convergence rates of the stochastic gradient descent (SGD) algorithm when applied to overparameterized two-layer neural networks.
no code implementations • 9 Jul 2024 • Matteo Bortoletto, Constantin Ruhdorfer, Lei Shi, Andreas Bulling
We propose MToMnet - a Theory of Mind (ToM) neural network for predicting beliefs and their dynamics during human social interactions from multimodal input.
1 code implementation • 6 Jul 2024 • Min Zhang, Xian Fu, Jianye Hao, Peilong Han, Hao Zhang, Lei Shi, Hongyao Tang, Yan Zheng
To this end, based on the characteristics of embodied task planning, we first develop a systematic evaluation framework, which encapsulates four crucial capabilities of MFMs: object understanding, spatio-temporal perception, task understanding, and embodied reasoning.
no code implementations • 2 Jul 2024 • Adnen Abdessaied, Lei Shi, Andreas Bulling
Then, it predicts the missing underlying structure of the selected constituents of each modality by learning local latent graphs using a novel multi-modal graph structure learning method.
no code implementations • 25 Jun 2024 • Matteo Bortoletto, Constantin Ruhdorfer, Lei Shi, Andreas Bulling
We are the first to study how prompt variations impact probing performance on theory of mind tasks.
1 code implementation • 13 Jun 2024 • Yuankai Luo, Lei Shi, Xiao-Ming Wu
Graph Transformers (GTs) have recently emerged as popular alternatives to traditional message-passing Graph Neural Networks (GNNs), due to their theoretically superior expressiveness and impressive performance reported on standard node classification benchmarks, often significantly outperforming GNNs.
Ranked #1 on
Node Classification
on questions
no code implementations • 6 Jun 2024 • Yue Wang, Jianhua Zhao, Fen Jiang, Lei Shi, Jianxin Pan
Although robust modeling using the $t$ distribution is an appealing idea, the existing work, that explores the use of the $t$ distribution only for random effects, involves complicated numerical integration and numerical optimization.
1 code implementation • 3 Jun 2024 • Fan He, Mingzhen He, Lei Shi, Xiaolin Huang, Johan A. K. Suykens
Ridgeless regression has garnered attention among researchers, particularly in light of the ``Benign Overfitting'' phenomenon, where models interpolating noisy samples demonstrate robust generalization.
1 code implementation • 26 May 2024 • Yuankai Luo, Hongkang Li, Qijiong Liu, Lei Shi, Xiao-Ming Wu
We present a novel end-to-end framework that generates highly compact (typically 6-15 dimensions), discrete (int4 type), and interpretable node representations, termed node identifiers (node IDs), to tackle inference challenges on large-scale graphs.
no code implementations • 21 May 2024 • Matteo Bortoletto, Constantin Ruhdorfer, Adnen Abdessaied, Lei Shi, Andreas Bulling
This finding calls for a deeper understanding of the role of ToM in CPA and beyond, as well as new methods for modelling and evaluating mental states in computational collaborative agents.
no code implementations • 16 May 2024 • Fengjie Wang, Chengming Liu, Lei Shi, Pang Haibo
In our methodology, any dataset can be unified under the framework of feature-rich anomaly detection, in a way that the benefits far outweigh the drawbacks.
Ranked #1 on
Anomaly Classification
on GoodsAD
(AUROC metric)
no code implementations • 6 May 2024 • Anna Penzkofer, Lei Shi, Andreas Bulling
Our method is based on the Semantic Pointer Architecture (SPA) to encode objects in a hyperdimensional vector space.
no code implementations • 28 Apr 2024 • Zhili Cheng, Zhitong Wang, Jinyi Hu, Shengding Hu, An Liu, Yuge Tu, Pengkai Li, Lei Shi, Zhiyuan Liu, Maosong Sun
Despite advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), their integration into language-grounded, human-like embodied agents remains incomplete, hindering complex real-life task performance in physical environments.
no code implementations • 24 Apr 2024 • Zhaoxing Li, Jujie Yang, Jindi Wang, Lei Shi, Sebastian Stein
However, with the development of Intelligent Tutoring Systems, large-scale datasets containing long-sequence data began to emerge.
no code implementations • 10 Apr 2024 • Guanhang Lei, Zhen Lei, Lei Shi, Chenyu Zeng
We propose the POD-DNN, a novel algorithm leveraging deep neural networks (DNNs) along with radial basis functions (RBFs) in the context of the proper orthogonal decomposition (POD) reduced basis method (RBM), aimed at approximating the parametric mapping of parametric partial differential equations on irregular domains.
no code implementations • 3 Apr 2024 • Lei Shi, Ian Chen, Hiroo Takayama, Vijay Vedula
The iFEA framework relies on a novel nested optimization scheme, in which the outer iterations utilize a traditional optimization method to best approximate material parameters that fit image data, while the inner iterations employ an augmented Sellier's algorithm to estimate the stress-free reference configuration.
no code implementations • 13 Mar 2024 • Lei Shi, Paul Bürkner, Andreas Bulling
We show that by adding action embeddings into the noise mask the diffusion model can better learn action temporal dependencies and increase the performances on procedure planning.
no code implementations • 6 Mar 2024 • Weichun Xia, Lei Shi
Our paper introduces a new perspective, asserting that input data are situated within a low-dimensional manifold embedded in a higher-dimensional Euclidean space.
no code implementations • 4 Mar 2024 • Zhiji Yang, Wanyi Chen, huan zhang, Yitian Xu, Lei Shi, Jianhua Zhao
Support vector machine (SVM) has achieved many successes in machine learning, especially for a small sample problem.
no code implementations • 3 Mar 2024 • Huijie Guo, Ying Ba, Jie Hu, Lingyu Si, Wenwen Qiang, Lei Shi
Specifically, we update our proposed model through a bi-level optimization mechanism, enabling it to capture comprehensive features.
1 code implementation • 25 Feb 2024 • Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Long Xia, Dawei Yin, Chao Huang
However, existing frameworks for heterogeneous graph learning have limitations in generalizing across diverse heterogeneous graph datasets.
1 code implementation • 25 Feb 2024 • Zhonghang Li, Lianghao Xia, Jiabin Tang, Yong Xu, Lei Shi, Long Xia, Dawei Yin, Chao Huang
These findings highlight the potential of building large language models for spatio-temporal learning, particularly in zero-shot scenarios where labeled data is scarce.
no code implementations • 7 Feb 2024 • Lei Shi, Jia-Qi Yang
This study investigates leveraging stochastic gradient descent (SGD) to learn operators between general Hilbert spaces.
no code implementations • 25 Dec 2023 • Haoyu Wei, Runzhe Wan, Lei Shi, Rui Song
Many real-world bandit applications are characterized by sparse rewards, which can significantly hinder learning efficiency.
no code implementations • 19 Dec 2023 • Susanne Hindennach, Lei Shi, Filip Miletić, Andreas Bulling
When users perceive AI systems as mindful, independent agents, they hold them responsible instead of the AI experts who created and designed these systems.
1 code implementation • 15 Dec 2023 • Shiwei Lyu, Chenfei Chi, Hongbo Cai, Lei Shi, Xiaoyan Yang, Lei Liu, Xiang Chen, Deng Zhao, Zhiqiang Zhang, Xianguo Lyu, Ming Zhang, Fangzhou Li, Xiaowei Ma, Yue Shen, Jinjie Gu, Wei Xue, Yiran Huang
We introduce RJUA-QA, a novel medical dataset for question answering (QA) and reasoning with clinical evidence, contributing to bridge the gap between general large language models (LLMs) and medical-specific LLM applications.
no code implementations • 12 Dec 2023 • Matteo Bortoletto, Lei Shi, Andreas Bulling
We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations.
1 code implementation • NeurIPS 2023 • Yuankai Luo, Lei Shi, Veronika Thost
Self-supervised learning (SSL) has great potential for molecular representation learning given the complexity of molecular graphs, the large amounts of unlabelled data available, the considerable cost of obtaining labels experimentally, and the hence often only small training datasets.
no code implementations • 14 Nov 2023 • Jia Luo, Daiyun Peng, Lei Shi, Didier El Baz, Xinran Liu
This paper presents a comparative analysis of the COVID-19 infodemic in the English and Chinese languages, utilizing textual data extracted from social media platforms.
no code implementations • 25 Oct 2023 • Adnen Abdessaied, Lei Shi, Andreas Bulling
We propose $\mathbb{VD}$-$\mathbb{GR}$ - a novel visual dialog model that combines pre-trained language models (LMs) with graph neural networks (GNNs).
1 code implementation • 19 Oct 2023 • Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Lixin Su, Suqi Cheng, Dawei Yin, Chao Huang
The open-sourced model implementation of our GraphGPT is available at https://github. com/HKUDS/GraphGPT.
1 code implementation • 8 Oct 2023 • Fan He, Mingzhen He, Lei Shi, Xiaolin Huang, Johan A. K. Suykens
To enhance kernel flexibility, this paper introduces the concept of Locally-Adaptive-Bandwidths (LAB) as trainable parameters to enhance the Radial Basis Function (RBF) kernel, giving rise to the LAB RBF kernel.
1 code implementation • 22 Aug 2023 • Yuankai Luo, Hongkang Li, Lei Shi, Xiao-Ming Wu
Empirically, we demonstrate that graph transformers with HDSE excel in graph classification, regression on 7 graph-level datasets, and node classification on 11 large-scale graphs, including those with up to a billion nodes.
Ranked #5 on
Graph Regression
on ZINC-500k
no code implementations • 18 Aug 2023 • Guanhang Lei, Zhen Lei, Lei Shi, Chenyu Zeng, Ding-Xuan Zhou
In this paper, we establish rigorous analysis of the physics-informed convolutional neural network (PICNN) for solving PDEs on the sphere.
no code implementations • 31 Jul 2023 • Zihan Zhang, Lei Shi, Ding-Xuan Zhou
In this paper, we aim to fill this gap by establishing a novel and elegant oracle-type inequality, which enables us to deal with the boundedness restriction of the target function, and using it to derive sharp convergence rates for fully connected ReLU DNN classifiers trained with logistic loss.
no code implementations • 29 Jun 2023 • Zixuan Chen, Lei Shi, Xuandong Liu, Jiahui Li, Sen Liu, Yang Xu
However, these two types of methods can result in accuracy loss due to discarded gradients and have limited enhancement on the throughput of model synchronization, respectively.
no code implementations • 21 Jun 2023 • Zimeng Li, Sa Xiao, Cheng Wang, Haidong Li, Xiuchao Zhao, Caohui Duan, Qian Zhou, Qiuchen Rao, Yuan Fang, Junshuai Xie, Lei Shi, Fumin Guo, Chaohui Ye, Xin Zhou
Magnetic resonance imaging (MRI) using hyperpolarized noble gases provides a way to visualize the structure and function of human lung, but the long imaging time limits its broad research and clinical applications.
no code implementations • 25 Apr 2023 • Lei Shi, Tianyu Gao, Zheng Zhang, Junxing Zhang
Deep learning based models for medical image segmentation have made great progress in recent years.
1 code implementation • 24 Apr 2023 • Yuankai Luo, Lei Shi, Mufan Xu, Yuwen Ji, Fengli Xiao, Chunming Hu, Zhiguang Shan
Experiment outcomes show that the F1 score of best GF profile significantly outperforms alternative methods of impact indicators and bibliometric networks in all the 6 computer science fields considered.
no code implementations • 20 Apr 2023 • Zheng-Chu Guo, Andreas Christmann, Lei Shi
In this paper, we study an online learning algorithm with a robust loss function $\mathcal{L}_{\sigma}$ for regression over a reproducing kernel Hilbert space (RKHS).
no code implementations • 6 Apr 2023 • Guanhang Lei, Lei Shi
Regularized pairwise ranking with Gaussian kernels is one of the cutting-edge learning algorithms.
1 code implementation • journal 2023 • Junxiao Xue, Hao Zhou, Huawei Song, Bin Wu, Lei Shi
Researchers have proposed many methods to defend against these attacks, but in the existing methods, researchers just focus on speech features.
Ranked #1 on
Voice Anti-spoofing
on ASVspoof 2019 - PA
no code implementations • 12 Jan 2023 • Chen Shen, Zhao Song, Lei Shi, Jun Tanimoto, Zhen Wang
Altruistic punishment, where individuals incur personal costs to punish others who have harmed third parties, presents an evolutionary conundrum as it undermines individual fitness.
1 code implementation • 5 Jan 2023 • Jialin Yu, Alexandra I. Cristea, Anoushka Harit, Zhongtian Sun, Olanrewaju Tahir Aduragba, Lei Shi, Noura Al Moubayed
To leverage information from text pairs, we additionally introduce a novel supervised model we call dual directional learning (DDL), which is designed to integrate with our proposed VSAR model.
no code implementations • 20 Nov 2022 • Jiading Liu, Lei Shi
Previous analysis of regularized functional linear regression in a reproducing kernel Hilbert space (RKHS) typically requires the target function to be contained in this kernel space.
1 code implementation • 14 Oct 2022 • Zhuoqing Song, Weijian Li, Kexin Jin, Lei Shi, Ming Yan, Wotao Yin, Kun Yuan
In the proposed family, EquiStatic has a degree of $\Theta(\ln(n))$, where $n$ is the network size, and a series of time-dependent one-peer topologies, EquiDyn, has a constant degree of 1.
no code implementations • 25 Sep 2022 • Xin Guo, Zheng-Chu Guo, Lei Shi
This article provides convergence analysis of online stochastic gradient descent algorithms for functional linear models.
no code implementations • 2 Sep 2022 • Jialin Yu, Alexandra I. Cristea, Anoushka Harit, Zhongtian Sun, Olanrewaju Tahir Aduragba, Lei Shi, Noura Al Moubayed
XAI with natural language processing aims to produce human-readable explanations as evidence for AI decision-making, which addresses explainability and transparency.
no code implementations • 26 Aug 2022 • Yuan Mao, Lei Shi, Zheng-Chu Guo
Compared with the kernel methods for distribution regression in the literature, the algorithm under consideration does not require the kernel to be symmetric and positive semi-definite and hence provides a simple paradigm for designing indefinite kernel methods, which enriches the theme of the distribution regression.
1 code implementation • 19 Apr 2022 • Zaiyun Lin, Shiqiu Yin, Lei Shi, Wenbiao Zhou, YingSheng Zhang
Retrosynthesis prediction is one of the fundamental challenges in organic chemistry and related fields.
Ranked #17 on
Single-step retrosynthesis
on USPTO-50k
no code implementations • 14 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.
no code implementations • 3 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.
no code implementations • 24 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.
no code implementations • 24 Sep 2021 • Lei Shi, Bin Wang, Junxing Zhang
Diabetic retinopathy (DR) is one of the major blindness-causing diseases currently known.
no code implementations • 26 Jul 2021 • Zhuoqing Song, Lei Shi, Shi Pu, Ming Yan
We consider the decentralized optimization problem, where a network of $n$ agents aims to collaboratively minimize the average of their individual smooth and convex objective functions through peer-to-peer communication in a directed graph.
no code implementations • 14 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.
no code implementations • 13 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.
no code implementations • 26 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.
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.
no code implementations • 31 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.
Optics
1 code implementation • 18 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.
no code implementations • 12 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.
no code implementations • 12 Aug 2020 • Lei Shi, Alexandra I. Cristea, Armando M. Toda, Wilk Oliveira
Massive Open Online Courses (MOOCs) exhibit a remarkable heterogeneity of students.
no code implementations • 10 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?"
no code implementations • 26 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.
no code implementations • 19 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.
1 code implementation • 7 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.
Ranked #38 on
Skeleton Based Action Recognition
on NTU RGB+D
no code implementations • 1 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).
no code implementations • 7 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.
no code implementations • 4 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.
no code implementations • 21 Jan 2020 • Lei Shi
How can we infer such a mobility model from the single trajectory information?
no code implementations • 3 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.
2 code implementations • 15 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.
no code implementations • 28 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.
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.
Ranked #69 on
Skeleton Based Action Recognition
on NTU RGB+D
no code implementations • 2 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.
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.
Ranked #9 on
Skeleton Based Action Recognition
on UAV-Human
1 code implementation • 23 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.
1 code implementation • 15 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.
no code implementations • 1 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.
no code implementations • 26 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.
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.
Ranked #7 on
3D Action Recognition
on Assembly101
no code implementations • 10 Oct 2017 • Zheng-Chu Guo, Lei Shi
In this paper, we study the online learning algorithm without explicit regularization terms.
no code implementations • 9 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.
no code implementations • 7 Aug 2017 • Zheng-Chu Guo, Lei Shi, Qiang Wu
Regularization kernel network is an effective and widely used method for nonlinear regression analysis.
no code implementations • 15 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).
no code implementations • 3 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.
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.
1 code implementation • 1 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.
no code implementations • 20 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.
no code implementations • 22 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.
no code implementations • 12 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.
no code implementations • 14 May 2015 • Xiaolin Huang, Lei Shi, Ming Yan, Johan A. K. Suykens
The one-sided $\ell_1$ loss and the linear loss are two popular loss functions for 1bit-CS.
no code implementations • 27 Aug 2014 • Yuyu Zhang, Liang Pang, Lei Shi, Bin Wang
This paper describes the solution of Bazinga Team for Tmall Recommendation Prize 2014.
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.
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.
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.