Search Results for author: De-Shuang Huang

Found 6 papers, 1 papers with code

Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation

no code implementations19 May 2024 Zejun Gu, Zhong-Qiu Zhao, Henghui Ding, Hao Shen, Zhao Zhang, De-Shuang Huang

In this framework, we construct a scale-adaptive projector ensemble (SAPE) module to spatially align feature maps between models of varying input resolutions.

Knowledge Distillation Pose Estimation

Attention Deep Model with Multi-Scale Deep Supervision for Person Re-Identification

no code implementations23 Nov 2019 Di Wu, Chao Wang, Yong Wu, De-Shuang Huang

Besides, most of the multi-scale models embedding the multi-scale feature learning block into the feature extraction deep network, which reduces the efficiency of inference network.

Person Re-Identification

Omni-directional Feature Learning for Person Re-identification

no code implementations13 Dec 2018 Di Wu, Hong-Wei Yang, De-Shuang Huang

Most of them focus on learning the part feature representation of person body in horizontal direction.

Person Re-Identification Representation Learning

Random Occlusion-recovery for Person Re-identification

no code implementations26 Sep 2018 Di Wu, Kun Zhang, Fei Cheng, Yang Zhao, Qi Liu, Chang-An Yuan, De-Shuang Huang

As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across different time with a single camera.

Generative Adversarial Network Person Re-Identification

Optimized Projection for Sparse Representation Based Classification

no code implementations31 Jan 2015 Can-Yi Lu, De-Shuang Huang

Dimensionality reduction (DR) methods have been commonly used as a principled way to understand the high-dimensional data such as facial images.

Classification Dimensionality Reduction +3

Robust and Efficient Subspace Segmentation via Least Squares Regression

1 code implementation27 Apr 2014 Can-Yi Lu, Hai Min, Zhong-Qiu Zhao, Lin Zhu, De-Shuang Huang, Shuicheng Yan

If the subspaces from which the data drawn are independent or orthogonal, they are able to obtain a block diagonal affinity matrix, which usually leads to a correct segmentation.

regression Segmentation

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