Alert button
Picture for Fan Wang

Fan Wang

Alert button

RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension

Aug 03, 2023
Qiang Zhou, Chaohui Yu, Shaofeng Zhang, Sitong Wu, Zhibing Wang, Fan Wang

Figure 1 for RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension
Figure 2 for RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension
Figure 3 for RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension
Figure 4 for RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension
Viaarxiv icon

Dynamic Token-Pass Transformers for Semantic Segmentation

Aug 03, 2023
Yuang Liu, Qiang Zhou, Jing Wang, Fan Wang, Jun Wang, Wei Zhang

Figure 1 for Dynamic Token-Pass Transformers for Semantic Segmentation
Figure 2 for Dynamic Token-Pass Transformers for Semantic Segmentation
Figure 3 for Dynamic Token-Pass Transformers for Semantic Segmentation
Figure 4 for Dynamic Token-Pass Transformers for Semantic Segmentation
Viaarxiv icon

Improved Neural Radiance Fields Using Pseudo-depth and Fusion

Jul 27, 2023
Jingliang Li, Qiang Zhou, Chaohui Yu, Zhengda Lu, Jun Xiao, Zhibin Wang, Fan Wang

Figure 1 for Improved Neural Radiance Fields Using Pseudo-depth and Fusion
Figure 2 for Improved Neural Radiance Fields Using Pseudo-depth and Fusion
Figure 3 for Improved Neural Radiance Fields Using Pseudo-depth and Fusion
Figure 4 for Improved Neural Radiance Fields Using Pseudo-depth and Fusion
Viaarxiv icon

Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation

Jul 26, 2023
Chaohui Yu, Qiang Zhou, Jingliang Li, Zhe Zhang, Zhibin Wang, Fan Wang

Figure 1 for Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation
Figure 2 for Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation
Figure 3 for Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation
Figure 4 for Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation
Viaarxiv icon

Graph Convolution Based Efficient Re-Ranking for Visual Retrieval

Jun 15, 2023
Yuqi Zhang, Qi Qian, Hongsong Wang, Chong Liu, Weihua Chen, Fan Wang

Figure 1 for Graph Convolution Based Efficient Re-Ranking for Visual Retrieval
Figure 2 for Graph Convolution Based Efficient Re-Ranking for Visual Retrieval
Figure 3 for Graph Convolution Based Efficient Re-Ranking for Visual Retrieval
Figure 4 for Graph Convolution Based Efficient Re-Ranking for Visual Retrieval
Viaarxiv icon

Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training

Jun 15, 2023
Chong Liu, Yuqi Zhang, Hongsong Wang, Weihua Chen, Fan Wang, Yan Huang, Yi-Dong Shen, Liang Wang

Figure 1 for Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training
Figure 2 for Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training
Figure 3 for Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training
Figure 4 for Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training
Viaarxiv icon

SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting

Jun 05, 2023
Lei Chen, Fei Du, Yuan Hu, Fan Wang, Zhibin Wang

Figure 1 for SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting
Figure 2 for SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting
Figure 3 for SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting
Figure 4 for SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting
Viaarxiv icon

MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks

May 17, 2023
Wenfang Sun, Yingjun Du, Xiantong Zhen, Fan Wang, Ling Wang, Cees G. M. Snoek

Figure 1 for MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks
Figure 2 for MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks
Figure 3 for MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks
Figure 4 for MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks
Viaarxiv icon

NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation

May 15, 2023
Jiefeng Li, Siyuan Bian, Qi Liu, Jiasheng Tang, Fan Wang, Cewu Lu

Figure 1 for NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation
Figure 2 for NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation
Figure 3 for NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation
Figure 4 for NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation
Viaarxiv icon

UniNeXt: Exploring A Unified Architecture for Vision Recognition

May 01, 2023
Fangjian Lin, Jianlong Yuan, Sitong Wu, Fan Wang, Zhibin Wang

Figure 1 for UniNeXt: Exploring A Unified Architecture for Vision Recognition
Figure 2 for UniNeXt: Exploring A Unified Architecture for Vision Recognition
Figure 3 for UniNeXt: Exploring A Unified Architecture for Vision Recognition
Figure 4 for UniNeXt: Exploring A Unified Architecture for Vision Recognition
Viaarxiv icon