Picture for Dongnan Liu

Dongnan Liu

RWKV-CLIP: A Robust Vision-Language Representation Learner

Add code
Jun 11, 2024
Viaarxiv icon

Dance Any Beat: Blending Beats with Visuals in Dance Video Generation

Add code
May 15, 2024
Viaarxiv icon

LaPA: Latent Prompt Assist Model For Medical Visual Question Answering

Add code
Apr 19, 2024
Viaarxiv icon

Cross-domain Fiber Cluster Shape Analysis for Language Performance Cognitive Score Prediction

Mar 30, 2024
Figure 1 for Cross-domain Fiber Cluster Shape Analysis for Language Performance Cognitive Score Prediction
Figure 2 for Cross-domain Fiber Cluster Shape Analysis for Language Performance Cognitive Score Prediction
Figure 3 for Cross-domain Fiber Cluster Shape Analysis for Language Performance Cognitive Score Prediction
Figure 4 for Cross-domain Fiber Cluster Shape Analysis for Language Performance Cognitive Score Prediction
Viaarxiv icon

Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling

Mar 05, 2024
Figure 1 for Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling
Figure 2 for Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling
Figure 3 for Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling
Figure 4 for Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling
Viaarxiv icon

Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive Distillation

Feb 09, 2024
Viaarxiv icon

Learning to Generalize over Subpartitions for Heterogeneity-aware Domain Adaptive Nuclei Segmentation

Jan 21, 2024
Figure 1 for Learning to Generalize over Subpartitions for Heterogeneity-aware Domain Adaptive Nuclei Segmentation
Figure 2 for Learning to Generalize over Subpartitions for Heterogeneity-aware Domain Adaptive Nuclei Segmentation
Figure 3 for Learning to Generalize over Subpartitions for Heterogeneity-aware Domain Adaptive Nuclei Segmentation
Figure 4 for Learning to Generalize over Subpartitions for Heterogeneity-aware Domain Adaptive Nuclei Segmentation
Viaarxiv icon

Complex Organ Mask Guided Radiology Report Generation

Add code
Nov 10, 2023
Viaarxiv icon

ODM3D: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection

Add code
Nov 07, 2023
Figure 1 for ODM3D: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection
Figure 2 for ODM3D: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection
Figure 3 for ODM3D: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection
Figure 4 for ODM3D: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection
Viaarxiv icon

Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training

Aug 31, 2023
Figure 1 for Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training
Figure 2 for Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training
Figure 3 for Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training
Figure 4 for Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training
Viaarxiv icon