Picture for Dongmei Fu

Dongmei Fu

Bridging the Semantic-Numerical Gap: A Numerical Reasoning Method of Cross-modal Knowledge Graph for Material Property Prediction

Dec 15, 2023
Viaarxiv icon

PixelLM: Pixel Reasoning with Large Multimodal Model

Add code
Dec 04, 2023
Figure 1 for PixelLM: Pixel Reasoning with Large Multimodal Model
Figure 2 for PixelLM: Pixel Reasoning with Large Multimodal Model
Figure 3 for PixelLM: Pixel Reasoning with Large Multimodal Model
Figure 4 for PixelLM: Pixel Reasoning with Large Multimodal Model
Viaarxiv icon

MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field

Add code
Sep 24, 2023
Figure 1 for MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field
Figure 2 for MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field
Figure 3 for MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field
Figure 4 for MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field
Viaarxiv icon

Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation

Jun 29, 2023
Figure 1 for Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation
Figure 2 for Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation
Figure 3 for Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation
Figure 4 for Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation
Viaarxiv icon

VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending

May 22, 2023
Figure 1 for VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending
Figure 2 for VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending
Figure 3 for VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending
Figure 4 for VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending
Viaarxiv icon

PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers

Mar 16, 2023
Figure 1 for PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers
Figure 2 for PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers
Figure 3 for PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers
Figure 4 for PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers
Viaarxiv icon

Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution

Add code
Dec 27, 2022
Figure 1 for Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution
Figure 2 for Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution
Figure 3 for Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution
Figure 4 for Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution
Viaarxiv icon

Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge

Nov 22, 2022
Figure 1 for Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge
Figure 2 for Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge
Figure 3 for Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge
Figure 4 for Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge
Viaarxiv icon

Dynamic Graph Reasoning for Multi-person 3D Pose Estimation

Aug 06, 2022
Figure 1 for Dynamic Graph Reasoning for Multi-person 3D Pose Estimation
Figure 2 for Dynamic Graph Reasoning for Multi-person 3D Pose Estimation
Figure 3 for Dynamic Graph Reasoning for Multi-person 3D Pose Estimation
Figure 4 for Dynamic Graph Reasoning for Multi-person 3D Pose Estimation
Viaarxiv icon

IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation

Aug 06, 2022
Figure 1 for IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation
Figure 2 for IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation
Figure 3 for IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation
Figure 4 for IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation
Viaarxiv icon