Search Results for author: Shuzhi Sam Ge

Found 13 papers, 3 papers with code

Low-resolution Human Pose Estimation

no code implementations19 Sep 2021 Chen Wang, Feng Zhang, Xiatian Zhu, Shuzhi Sam Ge

Human pose estimation has achieved significant progress on images with high imaging resolution.

Pose Estimation

Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation

1 code implementation27 Jul 2021 Song Tang, Yan Yang, Zhiyuan Ma, Norman Hendrich, Fanyu Zeng, Shuzhi Sam Ge, ChangShui Zhang, Jianwei Zhang

To reach this goal, we construct the nearest neighborhood for every target data and take it as the fundamental clustering unit by building our objective on the geometry.

Deep Clustering Unsupervised Domain Adaptation

Person image generation with semantic attention network for person re-identification

no code implementations18 Aug 2020 Meichen Liu, Kejun Wang, Juihang Ji, Shuzhi Sam Ge

To address this issue, we propose a novel person pose-guided image generation method, which is called the semantic attention network.

Person Re-Identification Pose-Guided Image Generation +1

Adaptive Feedforward Neural Network Control with an Optimized Hidden Node Distribution

no code implementations23 May 2020 Qiong Liu, Dongyu Li, Shuzhi Sam Ge, Zhong Ouyang

Composite adaptive radial basis function neural network (RBFNN) control with a lattice distribution of hidden nodes has three inherent demerits: 1) the approximation domain of adaptive RBFNNs is difficult to be determined a priori; 2) only a partial persistence of excitation (PE) condition can be guaranteed; and 3) in general, the required number of hidden nodes of RBFNNs is enormous.

Learning Theory

Adaptive Control for Marine Vessels Against Harsh Environmental Variation

no code implementations29 Sep 2019 Fangwen Tu, Shuzhi Sam Ge, Yoo Sang Choo, Chang Chieh Hang

In this paper, robust control with sea state observer and dynamic thrust allocation is proposed for the Dynamic Positioning (DP) of an accommodation vessel in the presence of unknown hydrodynamic force variation and the input time delay.

Small traffic sign detection from large image

no code implementations journal 2019 ZhiGang Liu, Dongyu Li, Shuzhi Sam Ge, Feng Tian

It concatenates the features of the different layers into a fused feature map to provide sufficient information for small traffic sign detection.

Region Proposal Small Object Detection +1

Saliency Guided Hierarchical Robust Visual Tracking

no code implementations21 Dec 2018 Fangwen Tu, Shuzhi Sam Ge, Yazhe Tang, Chang Chieh Hang

A saliency guided hierarchical visual tracking (SHT) algorithm containing global and local search phases is proposed in this paper.

Visual Tracking

Shallow Cue Guided Deep Visual Tracking via Mixed Models

no code implementations19 Dec 2018 Fangwen Tu, Shuzhi Sam Ge, Chang Chieh Hang

The generated four local heat maps will facilitate to rectify the holistic map by eliminating the distracters to avoid drifting.

Visual Tracking

Temporal Convolutional Memory Networks for Remaining Useful Life Estimation of Industrial Machinery

1 code implementation12 Oct 2018 Lahiru Jayasinghe, Tharaka Samarasinghe, Chau Yuen, Jenny Chen Ni Low, Shuzhi Sam Ge

This paper, introduces a system model that incorporates temporal convolutions with both long term and short term time dependencies.

Data Augmentation

Object Activity Scene Description, Construction and Recognition

no code implementations1 May 2018 Hui Feng, Shan-Shan Wang, Shuzhi Sam Ge

Although, the existing approaches are good at action recognition, it is a great challenge to recognize a group of actions in an activity scene.

Action Recognition General Classification +2

Role Playing Learning for Socially Concomitant Mobile Robot Navigation

no code implementations29 May 2017 Mingming Li, Rui Jiang, Shuzhi Sam Ge, Tong Heng Lee

In this paper, we present the Role Playing Learning (RPL) scheme for a mobile robot to navigate socially with its human companion in populated environments.

Robot Navigation

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