Picture for Xiaoshan Yang

Xiaoshan Yang

CLIP-VG: Self-paced Curriculum Adapting of CLIP via Exploiting Pseudo-Language Labels for Visual Grounding

May 15, 2023
Linhui Xiao, Xiaoshan Yang, Fang Peng, Ming Yan, Yaowei Wang, Changsheng Xu

Figure 1 for CLIP-VG: Self-paced Curriculum Adapting of CLIP via Exploiting Pseudo-Language Labels for Visual Grounding

Figure 2 for CLIP-VG: Self-paced Curriculum Adapting of CLIP via Exploiting Pseudo-Language Labels for Visual Grounding

Figure 3 for CLIP-VG: Self-paced Curriculum Adapting of CLIP via Exploiting Pseudo-Language Labels for Visual Grounding

Figure 4 for CLIP-VG: Self-paced Curriculum Adapting of CLIP via Exploiting Pseudo-Language Labels for Visual Grounding

* 16 pages, 12 figures. Code will be released at https://github.com/linhuixiao/CLIP-VG

Access Paper or Ask Questions

Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition

Dec 20, 2021
Jinfeng Wei, Yunxin Wang, Mengli Guo, Pei Lv, Xiaoshan Yang, Mingliang Xu

Figure 1 for Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition

Figure 2 for Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition

Figure 3 for Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition

Figure 4 for Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition

* 12 pages, 6 figures

Access Paper or Ask Questions

ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning

Jun 16, 2021
Chaofan Chen, Xiaoshan Yang, Changsheng Xu, Xuhui Huang, Zhe Ma

Figure 1 for ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning

Figure 2 for ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning

Figure 3 for ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning

Figure 4 for ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning

* Accepted by CVPR2021

Access Paper or Ask Questions

Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets

Nov 07, 2020
Peng Jia, Ruiyu Ning, Ruiqi Sun, Xiaoshan Yang, Dongmei Cai

Figure 1 for Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets

Figure 2 for Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets

Figure 3 for Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets

Figure 4 for Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets

* 11 pages. Submitted to MNRAS with minor revision

Access Paper or Ask Questions

Exploring Feature Representation and Training strategies in Temporal Action Localization

May 29, 2019
Tingting Xie, Xiaoshan Yang, Tianzhu Zhang, Changsheng Xu, Ioannis Patras

Figure 1 for Exploring Feature Representation and Training strategies in Temporal Action Localization

Figure 2 for Exploring Feature Representation and Training strategies in Temporal Action Localization

Figure 3 for Exploring Feature Representation and Training strategies in Temporal Action Localization

Figure 4 for Exploring Feature Representation and Training strategies in Temporal Action Localization

* ICIP19 Camera Ready

Access Paper or Ask Questions