Picture for Wenguan Wang

Wenguan Wang

DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation

Add code
Mar 18, 2025
Viaarxiv icon

Multi-view Reconstruction via SfM-guided Monocular Depth Estimation

Add code
Mar 18, 2025
Viaarxiv icon

Chemical knowledge-informed framework for privacy-aware retrosynthesis learning

Add code
Feb 26, 2025
Viaarxiv icon

Learning Clustering-based Prototypes for Compositional Zero-shot Learning

Add code
Feb 10, 2025
Figure 1 for Learning Clustering-based Prototypes for Compositional Zero-shot Learning
Figure 2 for Learning Clustering-based Prototypes for Compositional Zero-shot Learning
Figure 3 for Learning Clustering-based Prototypes for Compositional Zero-shot Learning
Figure 4 for Learning Clustering-based Prototypes for Compositional Zero-shot Learning
Viaarxiv icon

A Survey of World Models for Autonomous Driving

Add code
Jan 20, 2025
Viaarxiv icon

Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models

Add code
Oct 26, 2024
Figure 1 for Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models
Figure 2 for Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models
Figure 3 for Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models
Figure 4 for Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models
Viaarxiv icon

Scene Graph Generation with Role-Playing Large Language Models

Add code
Oct 20, 2024
Figure 1 for Scene Graph Generation with Role-Playing Large Language Models
Figure 2 for Scene Graph Generation with Role-Playing Large Language Models
Figure 3 for Scene Graph Generation with Role-Playing Large Language Models
Figure 4 for Scene Graph Generation with Role-Playing Large Language Models
Viaarxiv icon

Vision-Language Navigation with Energy-Based Policy

Add code
Oct 18, 2024
Figure 1 for Vision-Language Navigation with Energy-Based Policy
Figure 2 for Vision-Language Navigation with Energy-Based Policy
Figure 3 for Vision-Language Navigation with Energy-Based Policy
Figure 4 for Vision-Language Navigation with Energy-Based Policy
Viaarxiv icon

Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation

Add code
Sep 16, 2024
Figure 1 for Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation
Figure 2 for Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation
Figure 3 for Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation
Figure 4 for Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation
Viaarxiv icon

Image Segmentation in Foundation Model Era: A Survey

Add code
Aug 23, 2024
Figure 1 for Image Segmentation in Foundation Model Era: A Survey
Figure 2 for Image Segmentation in Foundation Model Era: A Survey
Figure 3 for Image Segmentation in Foundation Model Era: A Survey
Viaarxiv icon