Picture for Yulong Shi

Yulong Shi

FViT: A Focal Vision Transformer with Gabor Filter

Add code
Feb 27, 2024
Viaarxiv icon

EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention

Add code
Oct 22, 2023
Figure 1 for EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention
Figure 2 for EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention
Figure 3 for EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention
Figure 4 for EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention
Viaarxiv icon

Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision

Sep 21, 2018
Figure 1 for Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision
Figure 2 for Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision
Figure 3 for Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision
Viaarxiv icon

FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information

Jun 25, 2018
Figure 1 for FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information
Figure 2 for FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information
Figure 3 for FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information
Figure 4 for FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information
Viaarxiv icon