Picture for Zhiheng Ma

Zhiheng Ma

ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing

Add code
Dec 17, 2024
Figure 1 for ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing
Figure 2 for ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing
Figure 3 for ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing
Figure 4 for ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing
Viaarxiv icon

FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training

Add code
Nov 18, 2024
Viaarxiv icon

Multi-modal Crowd Counting via Modal Emulation

Add code
Jul 28, 2024
Figure 1 for Multi-modal Crowd Counting via Modal Emulation
Figure 2 for Multi-modal Crowd Counting via Modal Emulation
Figure 3 for Multi-modal Crowd Counting via Modal Emulation
Figure 4 for Multi-modal Crowd Counting via Modal Emulation
Viaarxiv icon

Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation

Add code
Jul 12, 2024
Viaarxiv icon

Curriculum Dataset Distillation

Add code
May 15, 2024
Figure 1 for Curriculum Dataset Distillation
Figure 2 for Curriculum Dataset Distillation
Figure 3 for Curriculum Dataset Distillation
Figure 4 for Curriculum Dataset Distillation
Viaarxiv icon

Prompt Customization for Continual Learning

Add code
Apr 28, 2024
Figure 1 for Prompt Customization for Continual Learning
Figure 2 for Prompt Customization for Continual Learning
Figure 3 for Prompt Customization for Continual Learning
Figure 4 for Prompt Customization for Continual Learning
Viaarxiv icon

Few-shot Online Anomaly Detection and Segmentation

Add code
Mar 27, 2024
Viaarxiv icon

Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling

Add code
Feb 23, 2024
Figure 1 for Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling
Figure 2 for Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling
Figure 3 for Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling
Figure 4 for Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling
Viaarxiv icon

Gramformer: Learning Crowd Counting via Graph-Modulated Transformer

Add code
Jan 08, 2024
Viaarxiv icon

Linguistic Profiling of Deepfakes: An Open Database for Next-Generation Deepfake Detection

Add code
Jan 04, 2024
Viaarxiv icon