no code implementations • 25 May 2017 • Aiden Nibali, Zhen He, Stuart Morgan, Daniel Greenwood
Due to recent advances in technology, the recording and analysis of video data has become an increasingly common component of athlete training programmes.
no code implementations • 28 May 2017 • Brandon Victor, Zhen He, Stuart Morgan, Dino Miniutti
Most research has been focused on action recognition and using it to classify many clips in continuous video for action localisation.
no code implementations • NeurIPS 2017 • Zhen He, Shao-Bing Gao, Liang Xiao, Daxue Liu, Hangen He, David Barber
The capacity of an LSTM network can be increased by widening and adding layers.
2 code implementations • 23 Jan 2018 • Aiden Nibali, Zhen He, Stuart Morgan, Luke Prendergast
We study deep learning approaches to inferring numerical coordinates for points of interest in an input image.
Ranked #29 on Pose Estimation on MPII Human Pose
1 code implementation • 5 Jun 2018 • Aiden Nibali, Zhen He, Stuart Morgan, Luke Prendergast
Automatically determining three-dimensional human pose from monocular RGB image data is a challenging problem.
Ranked #46 on 3D Human Pose Estimation on MPI-INF-3DHP
1 code implementation • CVPR 2019 • Zhen He, Jian Li, Daxue Liu, Hangen He, David Barber
To achieve both label-free and end-to-end learning of MOT, we propose a Tracking-by-Animation framework, where a differentiable neural model first tracks objects from input frames and then animates these objects into reconstructed frames.
no code implementations • 8 Jul 2020 • Matthias Langer, Zhen He, Wenny Rahayu, Yanbo Xue
Distributed deep learning systems (DDLS) train deep neural network models by utilizing the distributed resources of a cluster.
no code implementations • 25 Aug 2020 • Xidong Wang, Zhan Li, Zhen He, Huijun Gao
This paper presents a novel adaptive fast smooth second-order sliding mode control for the attitude tracking of the three degree-of-freedom (3-DOF) helicopter system with lumped disturbances.
Systems and Control Systems and Control
no code implementations • 1 Jun 2021 • Brandon Victor, Aiden Nibali, Zhen He, David L. Carey
Sophisticated trajectory prediction models that effectively mimic team dynamics have many potential uses for sports coaches, broadcasters and spectators.
no code implementations • 11 Jun 2021 • Kristen Moore, Shenjun Zhong, Zhen He, Torsten Rudolf, Nils Fisher, Brandon Victor, Neha Jindal
In this paper we present the results of our experiments in training and deploying a self-supervised retrieval-based chatbot trained with contrastive learning for assisting customer support agents.
no code implementations • 26 Jun 2021 • Xu Yuan, Hongshen Chen, Yonghao Song, Xiaofang Zhao, Zhuoye Ding, Zhen He, Bo Long
In this paper, we propose a model, SSI, to improve sequential recommendation consistency with Self-Supervised Imitation.
no code implementations • 26 Jun 2021 • Xidong Wang, Zhan Li, Xinghu Yu, Zhen He
In this paper, a novel adaptive smooth disturbance observer-based fast finite-time adaptive backstepping control scheme is presented for the attitude tracking of the 3-DOF helicopter system subject to compound disturbances.
no code implementations • 9 Aug 2021 • Haritha Thilakarathne, Aiden Nibali, Zhen He, Stuart Morgan
We introduce a novel deep learning based group activity recognition approach called the Pose Only Group Activity Recognition System (POGARS), designed to use only tracked poses of people to predict the performed group activity.
Ranked #6 on Group Activity Recognition on Volleyball
no code implementations • 20 Aug 2021 • Tri Huynh, Aiden Nibali, Zhen He
Medical image classification is often challenging for two reasons: a lack of labelled examples due to expensive and time-consuming annotation protocols, and imbalanced class labels due to the relative scarcity of disease-positive individuals in the wider population.
1 code implementation • NeurIPS 2021 • Shen Kai, Lingfei Wu, Siliang Tang, Yueting Zhuang, Zhen He, Zhuoye Ding, Yun Xiao, Bo Long
The task of visual question generation (VQG) aims to generate human-like neural questions from an image and potentially other side information (e. g., answer type or the answer itself).
no code implementations • 15 Dec 2021 • Xueying Zhang, Yanyan Zou, Hainan Zhang, Jing Zhou, Shiliang Diao, Jiajia Chen, Zhuoye Ding, Zhen He, Xueqi He, Yun Xiao, Bo Long, Han Yu, Lingfei Wu
It consists of two main components: 1) natural language generation, which is built from a transformer-pointer network and a pre-trained sequence-to-sequence model based on millions of training data from our in-house platform; and 2) copywriting quality control, which is based on both automatic evaluation and human screening.
no code implementations • 16 Dec 2021 • Xiaojie Guo, Shugen Wang, Hanqing Zhao, Shiliang Diao, Jiajia Chen, Zhuoye Ding, Zhen He, Yun Xiao, Bo Long, Han Yu, Lingfei Wu
In addition, this kind of product description should be eye-catching to the readers.
no code implementations • 13 Feb 2022 • Jiayang Bai, Jie Guo, Chenchen Wan, Zhenyu Chen, Zhen He, Shan Yang, Piaopiao Yu, Yan Zhang, Yanwen Guo
At its core is a new lighting model (dubbed DSGLight) based on depth-augmented Spherical Gaussians (SG) and a Graph Convolutional Network (GCN) that infers the new lighting representation from a single LDR image of limited field-of-view.
no code implementations • 21 May 2022 • Xueying Zhang, Kai Shen, Chi Zhang, Xiaochuan Fan, Yun Xiao, Zhen He, Bo Long, Lingfei Wu
In this paper, we proposed an automatic Scenario-based Multi-product Advertising Copywriting Generation system (SMPACG) for E-Commerce, which has been deployed on a leading Chinese e-commerce platform.
1 code implementation • 26 Jun 2022 • Xiaochuan Fan, Chi Zhang, Yong Yang, Yue Shang, Xueying Zhang, Zhen He, Yun Xiao, Bo Long, Lingfei Wu
For a platform with billions of products, it is extremely time-costly and labor-expensive to manually pick and organize qualified images.
no code implementations • 30 Jun 2022 • Lin Yuan, Zhen He, Qiang Wang, Leiyang Xu, Xiang Ma
Human action recognition is a quite hugely investigated area where most remarkable action recognition networks usually use large-scale coarse-grained action datasets of daily human actions as inputs to state the superiority of their networks.
no code implementations • 3 Oct 2022 • Brandon Victor, Zhen He, Aiden Nibali
Agricultural research is essential for increasing food production to meet the requirements of an increasing population in the coming decades.
no code implementations • 18 Mar 2023 • Jiayang Bai, Zhen He, Shan Yang, Jie Guo, Zhenyu Chen, Yan Zhang, Yanwen Guo
Recent methods mostly rely on convolutional neural networks (CNNs) to fill the missing contents in the warped panorama.
no code implementations • 15 Apr 2023 • Xidong Wang, Zhan Li, Zhen He
This brief aims at the issue of globally composite-learning-based neural fast finite-time (F-FnT) tracking control for a class of uncertain systems in strict-feedback form subject to nonlinearly periodic disturbances.
no code implementations • 5 Oct 2023 • Long Nguyen, Aiden Nibali, Joshua Millward, Zhen He
Recently there have been many algorithms proposed for the classification of very high resolution whole slide images (WSIs).
no code implementations • 6 Jan 2024 • Haritha Thilakarathne, Aiden Nibali, Zhen He, Stuart Morgan
Group activity recognition in video is a complex task due to the need for a model to recognise the actions of all individuals in the video and their complex interactions.
1 code implementation • EMNLP 2021 • Xianming Li, Xiaotian Luo, Chenghao Dong, Daichuan Yang, Beidi Luan, Zhen He
To address such a problem, this paper proposes a novel efficient entities and relations extraction model called TDEER, which stands for Translating Decoding Schema for Joint Extraction of Entities and Relations.
Ranked #1 on Joint Entity and Relation Extraction on NYT