Picture for Xiangdong Zhou

Xiangdong Zhou

PanoSwin: a Pano-style Swin Transformer for Panorama Understanding

Aug 28, 2023
Figure 1 for PanoSwin: a Pano-style Swin Transformer for Panorama Understanding
Figure 2 for PanoSwin: a Pano-style Swin Transformer for Panorama Understanding
Figure 3 for PanoSwin: a Pano-style Swin Transformer for Panorama Understanding
Figure 4 for PanoSwin: a Pano-style Swin Transformer for Panorama Understanding
Viaarxiv icon

Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction

Add code
Jun 20, 2023
Figure 1 for Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction
Figure 2 for Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction
Figure 3 for Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction
Figure 4 for Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction
Viaarxiv icon

Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network

Jul 30, 2022
Figure 1 for Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network
Figure 2 for Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network
Figure 3 for Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network
Figure 4 for Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network
Viaarxiv icon

3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation

Jun 02, 2022
Figure 1 for 3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation
Figure 2 for 3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation
Figure 3 for 3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation
Figure 4 for 3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation
Viaarxiv icon

CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification

Mar 08, 2022
Figure 1 for CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification
Figure 2 for CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification
Figure 3 for CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification
Figure 4 for CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification
Viaarxiv icon

Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos

May 15, 2021
Figure 1 for Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos
Figure 2 for Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos
Figure 3 for Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos
Figure 4 for Aerial-PASS: Panoramic Annular Scene Segmentation in Drone Videos
Viaarxiv icon