Search Results for author: Zhen He

Found 11 papers, 3 papers with code

Improving Sequential Recommendation Consistency with Self-Supervised Imitation

no code implementations26 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.

Imitation Learning Sparse Learning

A comprehensive solution to retrieval-based chatbot construction

no code implementations11 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.

Chatbot Contrastive Learning +1

Enhancing Trajectory Prediction using Sparse Outputs: Application to Team Sports

no code implementations1 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.

Trajectory Prediction

Adaptive Fast Smooth Second-Order Sliding Mode Control for Attitude Tracking of a 3-DOF Helicopter

no code implementations25 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

Distributed Training of Deep Learning Models: A Taxonomic Perspective

no code implementations8 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.

Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers

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.

Multi-Object Tracking Online Multi-Object Tracking

3D Human Pose Estimation with 2D Marginal Heatmaps

1 code implementation5 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.

3D Human Pose Estimation

Numerical Coordinate Regression with Convolutional Neural Networks

2 code implementations23 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.

Pose Estimation

Continuous Video to Simple Signals for Swimming Stroke Detection with Convolutional Neural Networks

no code implementations28 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.

Action Recognition

Extraction and Classification of Diving Clips from Continuous Video Footage

no code implementations25 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.

General Classification

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