A5019329248- Dementia and Cognitive Impairment Research
- Advanced Neural Network Applications
- Alzheimer's disease research and treatments
- Domain Adaptation and Few-Shot Learning
- Advanced Image and Video Retrieval Techniques
- Advanced Neuroimaging Techniques and Applications
- Functional Brain Connectivity Studies
- Generative Adversarial Networks and Image Synthesis
- Medical Image Segmentation Techniques
- Face recognition and analysis
- Brain Tumor Detection and Classification
- Human Pose and Action Recognition
- Hand Gesture Recognition Systems
- Machine Learning and Data Classification
- Video Surveillance and Tracking Methods
- Cannabis and Cannabinoid Research
- Forensic Toxicology and Drug Analysis
- Natural Language Processing Techniques
- Multimodal Machine Learning Applications
- Anomaly Detection Techniques and Applications
- Video Analysis and Summarization
- Gaze Tracking and Assistive Technology
- Neurological and metabolic disorders
- Image Retrieval and Classification Techniques
- MRI in cancer diagnosis
Boston University
2005-2025
Massachusetts General Hospital
2017-2023
Harvard University
2019-2023
Framingham Heart Study
2023
Athinoula A. Martinos Center for Biomedical Imaging
2019-2022
Banner Alzheimer’s Institute
2022
University of Toronto
2022
Sunnybrook Research Institute
2022
Florey Institute of Neuroscience and Mental Health
2022
The University of Melbourne
2022
A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad solutions for deep metric learning. In this pa-per, we general weighting framework under-standing recent functions. Our contributions are three-fold: (1) establish General Pair Weighting (GPW) framework, casts sampling problem learning into unified view pair through gradient analysis, providing powerful tool understanding functions; (2) show that with GPW, various existing...
One-stage object detection is commonly implemented by optimizing two sub-tasks: classification and localization, using heads with parallel branches, which might lead to a certain level of spatial misalignment in predictions between the tasks. In this work, we propose Task-aligned Object Detection (TOOD) that explicitly aligns tasks learning-based manner. First, design novel Head (T-Head) offers better balance learning task-interactive task-specific features, as well greater flexibility learn...
Siamese-based trackers have achieved excellent performance on visual object tracking. However, the target template is not updated online, and features of search image are computed independently in a Siamese architecture. In this paper, we propose Deformable Attention Networks, referred to as SiamAttn, by introducing new attention mechanism that computes deformable self-attention cross-attention. The learns strong context information via spatial attention, selectively emphasizes...
<h3>Importance</h3> Mounting evidence suggests that sex differences exist in the pathologic trajectory of Alzheimer disease. Previous literature shows elevated levels cerebrospinal fluid tau women compared with men as a function apolipoprotein E (APOE) ε4 status and β-amyloid (Aβ). What remains unclear is association regional deposition clinically normal individuals. <h3>Objective</h3> To examine cross-sectional between Aβ measured positron emission tomography (PET). <h3>Design, Setting...
Mining informative negative instances are of central importance to deep metric learning (DML). However, the hard-mining ability existing DML methods is intrinsically limited by mini-batch training, where only a accessible at each iteration. In this paper, we identify “slow drift” phenomena observing that embedding features drift exceptionally slow even as model parameters updating throughout training process. It suggests computed preceding iterations can considerably approximate their...
We present ClothFlow, an appearance-flow-based generative model to synthesize clothed person for posed-guided image generation and virtual try-on. By estimating a dense flow between source target clothing regions, ClothFlow effectively models the geometric changes naturally transfers appearance novel images as shown in Figure 1. achieve this with three-stage framework: 1) Conditioned on pose, we first estimate semantic layout provide richer guidance process. 2) Built two feature pyramid...
Recent progress has been made on developing a unified framework for joint text detection and recognition in natural images, but existing models were mostly built two-stage by involving ROI pooling, which can degrade the performance task. In this work, we propose convolutional character networks, referred as CharNet, is an one-stage model that process two tasks simultaneously one pass. CharNet directly outputs bounding boxes of words characters, with corresponding labels. We utilize basic...
Fine-grained image categorization is challenging due to the subtle inter-class differences. We posit that exploiting rich relationships between channels can help capture such differences since different correspond semantics. In this paper, we propose a channel interaction network (CIN), which models channel-wise interplay both within an and across images. For single image, self-channel (SCI) module proposed explore correlation image. This allows model learn complementary features from...
Objective The goal of this study was to examine sex differences in tau distribution across the brain older adults, using positron emission tomography (PET), and investigate how these might associate with cognitive trajectories. Methods Participants were 343 clinically normal individuals (women, 58%; 73.8 [8.5] years) 55 mild impairment (MCI; women, 38%; 76.9 [7.3] from Harvard Aging Brain Study Alzheimer's Disease Neuroimaging Initiative. We examined 18 F‐Flortaucipir (FTP)‐positron (PET)...
Visual compatibility is critical for fashion analysis, yet missing in existing image synthesis systems. In this paper, we propose to explicitly model visual through inpainting. We present Fashion Inpainting Networks (FiNet), a two-stage image-to-image generation framework that able perform compatible and diverse Disentangling the of shape appearance ensure photorealistic results, our consists network an network. More importantly, each network, introduce two encoders interacting with one...
Many Large-scale image databases such as ImageNet have significantly advanced classification and other visual recognition tasks. However much of these datasets are constructed only for single-label coarse object-level classification. For real-world applications, multiple labels fine-grained categories often needed, yet very few exist publicly, especially those large-scale high quality. In this work, we contribute to the community a new dataset called iMaterialist Fashion Attribute...
Training an object detector on a data-rich domain and applying it to data-poor one with limited performance drop is highly attractive in industry, because saves huge annotation cost. Recent research unsupervised adaptive detection has verified that aligning data distributions between source target images through adversarial learning very useful. The key when, where how use achieve best practice. We propose Image-Instance Full Alignment Networks (iFAN) tackle this problem by precisely feature...
Abstract Animal and human imaging research reported that the presence of cortical Alzheimer’s Disease’s (AD) neuropathology, beta-amyloid neurofibrillary tau, is associated with altered neuronal activity circuitry failure, together facilitating clinical progression. The locus coeruleus (LC), one initial subcortical regions harboring pretangle hyperphosphorylated has widespread connections to cortex modulating cognition. Here we investigate whether LC’s in-vivo functional connectivity (FC)...
Weakly-supervised instance segmentation aims to detect and segment object instances precisely, given image-level labels only. Unlike previous methods which are composed of multiple offline stages, we propose Sequential Label Propagation Enhancement Networks (referred as Label-PEnet) that progressively transforms pixel-wise in a coarse-to-fine manner. We design four cascaded modules including multi-label classification, detection, refinement segmentation, implemented sequentially by sharing...
Unawareness, or anosognosia, of memory deficits is a challenging manifestation Alzheimer's disease (AD) that adversely affects patient's safety and decision-making. However, there lack consensus regarding the presence, as well evolution, altered awareness function across preclinical prodromal stages AD. Here, we aimed to characterize change in abilities its relationship beta-amyloid (Aβ) burden large cohort (N = 1,070) individuals spectrum.
A family of loss functions built on pair-based computation have been proposed in the literature which provide a myriad solutions for deep metric learning. In this paper, we general weighting framework understanding recent functions. Our contributions are three-fold: (1) establish General Pair Weighting (GPW) framework, casts sampling problem learning into unified view pair through gradient analysis, providing powerful tool functions; (2) show that with GPW, various existing methods can be...
MR images (MRIs) accurate segmentation of brain lesions is important for improving cancer diagnosis, surgical planning, and prediction outcome. However, manual from 3D MRIs highly expensive, time-consuming, prone to user biases. We present an efficient yet conceptually simple network (referred as Brain SegNet), which a residual framework automatic voxel-wise lesion. Our model able directly predict dense voxel tumor or ischemic stroke regions in MRIs. The proposed can run at about 0.5s per -...
Most existing 3D CNNs for video representation learning are clip-based methods, and thus do not consider video-level temporal evolution of spatio-temporal features. In this paper, we propose Video-level 4D Convolutional Neural Networks, referred as V4D, to model the long-range with convolutions, at same time, preserve strong residual connections. Specifically, design a new block able capture inter-clip interactions, which could enhance power original clip-level CNNs. The blocks can be easily...
The ability to synthesize multi-modality data is highly desirable for many computer-aided medical applications, e.g. clinical diagnosis and neuroscience research, since rich imaging cohorts offer diverse complementary information unraveling human tissues. However, collecting acquisitions can be limited by adversary factors such as patient discomfort, expensive cost scanner unavailability. In this paper, we propose a multi-task coherent modality transferable GAN (MCMT-GAN) address issue brain...