Picture for Junzhe Zhang

Junzhe Zhang

MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency

Add code
Jun 19, 2024
Viaarxiv icon

Evaluating and Mitigating Number Hallucinations in Large Vision-Language Models: A Consistency Perspective

Add code
Mar 03, 2024
Figure 1 for Evaluating and Mitigating Number Hallucinations in Large Vision-Language Models: A Consistency Perspective
Figure 2 for Evaluating and Mitigating Number Hallucinations in Large Vision-Language Models: A Consistency Perspective
Figure 3 for Evaluating and Mitigating Number Hallucinations in Large Vision-Language Models: A Consistency Perspective
Figure 4 for Evaluating and Mitigating Number Hallucinations in Large Vision-Language Models: A Consistency Perspective
Viaarxiv icon

Entity-Aware Multimodal Alignment Framework for News Image Captioning

Add code
Feb 29, 2024
Figure 1 for Entity-Aware Multimodal Alignment Framework for News Image Captioning
Figure 2 for Entity-Aware Multimodal Alignment Framework for News Image Captioning
Figure 3 for Entity-Aware Multimodal Alignment Framework for News Image Captioning
Figure 4 for Entity-Aware Multimodal Alignment Framework for News Image Captioning
Viaarxiv icon

DeformToon3D: Deformable 3D Toonification from Neural Radiance Fields

Add code
Sep 08, 2023
Viaarxiv icon

Variational Relational Point Completion Network for Robust 3D Classification

Add code
Apr 18, 2023
Viaarxiv icon

Generative Diffusion Prior for Unified Image Restoration and Enhancement

Add code
Apr 03, 2023
Figure 1 for Generative Diffusion Prior for Unified Image Restoration and Enhancement
Figure 2 for Generative Diffusion Prior for Unified Image Restoration and Enhancement
Figure 3 for Generative Diffusion Prior for Unified Image Restoration and Enhancement
Figure 4 for Generative Diffusion Prior for Unified Image Restoration and Enhancement
Viaarxiv icon

ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing

Add code
Sep 30, 2022
Figure 1 for ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing
Figure 2 for ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing
Figure 3 for ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing
Figure 4 for ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing
Viaarxiv icon

CARNet:Compression Artifact Reduction for Point Cloud Attribute

Add code
Sep 17, 2022
Figure 1 for CARNet:Compression Artifact Reduction for Point Cloud Attribute
Figure 2 for CARNet:Compression Artifact Reduction for Point Cloud Attribute
Figure 3 for CARNet:Compression Artifact Reduction for Point Cloud Attribute
Figure 4 for CARNet:Compression Artifact Reduction for Point Cloud Attribute
Viaarxiv icon

Sequential Causal Imitation Learning with Unobserved Confounders

Add code
Aug 12, 2022
Figure 1 for Sequential Causal Imitation Learning with Unobserved Confounders
Figure 2 for Sequential Causal Imitation Learning with Unobserved Confounders
Figure 3 for Sequential Causal Imitation Learning with Unobserved Confounders
Figure 4 for Sequential Causal Imitation Learning with Unobserved Confounders
Viaarxiv icon

Causal Imitation Learning with Unobserved Confounders

Add code
Aug 12, 2022
Figure 1 for Causal Imitation Learning with Unobserved Confounders
Figure 2 for Causal Imitation Learning with Unobserved Confounders
Figure 3 for Causal Imitation Learning with Unobserved Confounders
Figure 4 for Causal Imitation Learning with Unobserved Confounders
Viaarxiv icon