1 code implementation • 22 Mar 2024 • Lei Jiang, Weixin Yang, Xin Zhang, Hao Ni
Skeleton-based action recognition (SAR) in videos is an important but challenging task in computer vision.
1 code implementation • ICCV 2023 • Hao Ni, Yuke Li, Lianli Gao, Heng Tao Shen, Jingkuan Song
Based on the local similarity obtained in CSL, a Part-guided Self-Distillation (PSD) is proposed to further improve the generalization of global features.
Domain Generalization Generalizable Person Re-identification
no code implementations • 4 Aug 2023 • Andraž Jelinčič, Jiajie Tao, William F. Turner, Thomas Cass, James Foster, Hao Ni
In this paper, we propose L\'{e}vyGAN, a deep-learning-based model for generating approximate samples of L\'{e}vy area conditional on a Brownian increment.
no code implementations • 28 Jul 2023 • Chunyu Qiang, Hao Li, Hao Ni, He Qu, Ruibo Fu, Tao Wang, Longbiao Wang, Jianwu Dang
However, existing methods suffer from three problems: the high dimensionality and waveform distortion of discrete speech representations, the prosodic averaging problem caused by the duration prediction model in non-autoregressive frameworks, and the information redundancy and dimension explosion problems of existing semantic encoding methods.
no code implementations • 1 Jun 2023 • Bowen Fang, Hao Ni, Yue Wu
The concept of the path-dependent partial differential equation (PPDE) was first introduced in the context of path-dependent derivatives in financial markets.
1 code implementation • NeurIPS 2023 • Hang Lou, Siran Li, Hao Ni
Generating high-fidelity time series data using generative adversarial networks (GANs) remains a challenging task, as it is difficult to capture the temporal dependence of joint probability distributions induced by time-series data.
1 code implementation • 18 May 2023 • Xinheng Xie, Yue Wu, Hao Ni, Cuiyu He
Inspired by the traditional partial differential equation (PDE) approach for image denoising, we propose a novel neural network architecture, referred as NODE-ImgNet, that combines neural ordinary differential equations (NODEs) with convolutional neural network (CNN) blocks.
no code implementations • 18 Jan 2023 • Abbi Abdel-Rehim, Oghenejokpeme Orhobor, Hang Lou, Hao Ni, Ross D. King
We developed the ARStack PSP method by stacking AlphaFold2 and RoseTTAFold.
no code implementations • 17 Sep 2022 • Ye Bai, Jie Li, Wenjing Han, Hao Ni, Kaituo Xu, Zhuo Zhang, Cheng Yi, Xiaorui Wang
Experimental results show that the proposed model achieves competitive performance with 1/3 of the parameters of the encoder, compared with the full-parameter model.
1 code implementation • 2 Apr 2022 • Hang Lou, Siran Li, Hao Ni
To tackle this problem, we propose a novel, trainable path development layer, which exploits representations of sequential data with the help of finite-dimensional matrix Lie groups.
1 code implementation • CVPR 2022 • Hao Ni, Jingkuan Song, Xiaopeng Luo, Feng Zheng, Wen Li, Heng Tao Shen
Domain Generalizable (DG) person ReID is a challenging task which trains a model on source domains yet generalizes well on target domains.
Domain Generalization Generalizable Person Re-identification +1
no code implementations • 2 Dec 2021 • Shujian Liao, Jian Chen, Hao Ni
In this paper, we investigate the problem of predicting the future volatility of Forex currency pairs using the deep learning techniques.
1 code implementation • 1 Nov 2021 • Hao Ni, Lukasz Szpruch, Marc Sabate-Vidales, Baoren Xiao, Magnus Wiese, Shujian Liao
Synthetic data is an emerging technology that can significantly accelerate the development and deployment of AI machine learning pipelines.
1 code implementation • 25 Oct 2021 • Shujian Liao, Terry Lyons, Weixin Yang, Kevin Schlegel, Hao Ni
In this paper, we propose a novel module, namely Logsig-RNN, which is the combination of the log-signature layer and recurrent type neural networks (RNNs).
Action Recognition In Videos Skeleton Based Action Recognition +3
no code implementations • EMNLP (Louhi) 2020 • Andrey Kormilitzin, Nemanja Vaci, Qiang Liu, Hao Ni, Goran Nenadic, Alejo Nevado-Holgado
In this work we addressed the problem of capturing sequential information contained in longitudinal electronic health records (EHRs).
2 code implementations • 9 Jun 2020 • Shujian Liao, Hao Ni, Lukasz Szpruch, Magnus Wiese, Marc Sabate-Vidales, Baoren Xiao
The signature of a path is a graded sequence of statistics that provides a universal description for a stream of data, and its expected value characterises the law of the time-series model.
no code implementations • 8 Apr 2020 • Yue Wu, Hao Ni, Terence J. Lyons, Robin L. Hudson
In this paper we put the visibility transformation on a clear theoretical footing and show that this transform is able to embed the effect of the absolute position of the data stream into signature features in a unified and efficient way.
no code implementations • 2 Feb 2020 • Guang Yang, Jun Chen, Zhifan Gao, Shuo Li, Hao Ni, Elsa Angelini, Tom Wong, Raad Mohiaddin, Eva Nyktari, Ricardo Wage, Lei Xu, Yanping Zhang, Xiuquan Du, Heye Zhang, David Firmin, Jennifer Keegan
Using our MVTT recursive attention model, both the LA anatomy and scar can be segmented accurately (mean Dice score of 93% for the LA anatomy and 87% for the scar segmentations) and efficiently (~0. 27 seconds to simultaneously segment the LA anatomy and scars directly from the 3D LGE CMR dataset with 60-68 2D slices).
no code implementations • 22 Aug 2019 • Shujian Liao, Terry Lyons, Weixin Yang, Hao Ni
We illustrate the approach by approximating the unknown functional as a controlled differential equation.
Ranked #54 on Skeleton Based Action Recognition on NTU RGB+D 120
no code implementations • 12 Jun 2018 • Jun Chen, Guang Yang, Zhifan Gao, Hao Ni, Elsa Angelini, Raad Mohiaddin, Tom Wong, Yanping Zhang, Xiuquan Du, Heye Zhang, Jennifer Keegan, David Firmin
Late Gadolinium Enhanced Cardiac MRI (LGE-CMRI) for detecting atrial scars in atrial fibrillation (AF) patients has recently emerged as a promising technique to stratify patients, guide ablation therapy and predict treatment success.
no code implementations • 13 Jul 2017 • Weixin Yang, Terry Lyons, Hao Ni, Cordelia Schmid, Lianwen Jin
To this end, we regard the evolving landmark data as a high-dimensional path and apply non-linear path signature techniques to provide an expressive, robust, non-linear, and interpretable representation for the sequential events.
no code implementations • 9 Oct 2016 • Zecheng Xie, Zenghui Sun, Lianwen Jin, Hao Ni, Terry Lyons
Online handwritten Chinese text recognition (OHCTR) is a challenging problem as it involves a large-scale character set, ambiguous segmentation, and variable-length input sequences.
1 code implementation • 17 Mar 2016 • Shi Zong, Hao Ni, Kenny Sung, Nan Rosemary Ke, Zheng Wen, Branislav Kveton
In this work, we study cascading bandits, an online learning variant of the cascade model where the goal is to recommend $K$ most attractive items from a large set of $L$ candidate items.
2 code implementations • 1 Sep 2013 • Daniel Levin, Terry Lyons, Hao Ni
We bring the theory of rough paths to the study of non-parametric statistics on streamed data.