Search Results for author:
Found 13 papers, 9 papers with code
DiaMond: Dementia Diagnosis with Multi-Modal Vision Transformers Using MRI and PET
DiaMond significantly outperforms existing multi-modal methods across various datasets, achieving a balanced accuracy of 92. 4% in AD diagnosis, 65. 2% for AD-MCI-CN classification, and 76. 5% in differential diagnosis of AD and FTD.
Faster Image2Video Generation: A Closer Look at CLIP Image Embedding's Impact on Spatio-Temporal Cross-Attentions
This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency.
Mamba? Catch The Hype Or Rethink What Really Helps for Image Registration
Our findings indicate that adopting "advanced" computational elements fails to significantly improve registration accuracy.
Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
Controllable text-to-image (T2I) diffusion models have shown impressive performance in generating high-quality visual content through the incorporation of various conditions.
Box It to Bind It: Unified Layout Control and Attribute Binding in T2I Diffusion Models
To address these deficiencies, we introduce the Box-it-to-Bind-it (B2B) module - a novel, training-free approach for improving spatial control and semantic accuracy in text-to-image (T2I) diffusion models.
No-Clean-Reference Image Super-Resolution: Application to Electron Microscopy
The inability to acquire clean high-resolution (HR) electron microscopy (EM) images over a large brain tissue volume hampers many neuroscience studies.
H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration
This paper introduces a novel top-down representation approach for deformable image registration which estimates the deformation field by capturing various short- and long-range flow features at different scale levels.
RegBN: Batch Normalization of Multimodal Data with Regularization
The proposed method demonstrates broad applicability across different architectures such as multilayer perceptrons, convolutional neural networks, and vision transformers, enabling effective normalization of both low- and high-level features in multimodal neural networks.
Self-Supervised Super-Resolution Approach for Isotropic Reconstruction of 3D Electron Microscopy Images from Anisotropic Acquisition
To overcome this limitation, we propose a novel deep-learning (DL)-based self-supervised super-resolution approach that computationally reconstructs isotropic 3DEM from the anisotropic acquisition.
Adversarial Distortion Learning for Medical Image Denoising
The proposed ADL consists of two auto-encoders: a denoiser and a discriminator.
Ranked #1 on
Color Image Denoising
on CBSD68 sigma35
Regional Attention Network (RAN) for Head Pose and Fine-grained Gesture Recognition
Affect is often expressed via non-verbal body language such as actions/gestures, which are vital indicators for human behaviors.
Facial Expression Recognition
Facial Expression Recognition (FER)
+2
FFD: Fast Feature Detector
In this paper, we show that robust and accurate keypoints exist in the specific scale-space domain.
Orderly Disorder in Point Cloud Domain
Our method extracts the deep patterns inside a 3D object via creating a dynamic link to seek the most stable patterns and at once, throws away the unstable ones.
