Search Results for author:
Found 76 papers, 36 papers with code
Enforcing Conditional Independence for Fair Representation Learning and Causal Image Generation
We are able to enforce conditional independence of the diffusion autoencoder latent representation with respect to any protected attribute under the equalized odds constraint and show that this approach enables causal image generation with controllable latent spaces.
Towards Robust 3D Pose Transfer with Adversarial Learning
This work is driven by the intuition that the robustness of the model can be enhanced by introducing adversarial samples into the training, leading to a more invulnerable model to the noisy inputs, which even can be further extended to directly handling the real-world data like raw point clouds/scans without intermediate processing.
An Interactive Agent Foundation Model
We propose an Interactive Agent Foundation Model that uses a novel multi-task agent training paradigm for training AI agents across a wide range of domains, datasets, and tasks.
Wild2Avatar: Rendering Humans Behind Occlusions
In this work, we present Wild2Avatar, a neural rendering approach catered for occluded in-the-wild monocular videos.
Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection
In this study, we introduce a novel component segmentation model for LA detection that leverages a few labeled samples and unlabeled images sharing logical constraints.
PRISM: Progressive Restoration for Scene Graph-based Image Manipulation
We take advantage of the outer part of the masked area as they have a direct correlation with the context of the scene.
3D TransUNet: Advancing Medical Image Segmentation through Vision Transformers
In this paper, we extend the 2D TransUNet architecture to a 3D network by building upon the state-of-the-art nnU-Net architecture, and fully exploring Transformers' potential in both the encoder and decoder design.
Metadata-Conditioned Generative Models to Synthesize Anatomically-Plausible 3D Brain MRIs
Generative AI models hold great potential in creating synthetic brain MRIs that advance neuroimaging studies by, for example, enriching data diversity.
LSOR: Longitudinally-Consistent Self-Organized Representation Learning
Interpretability is a key issue when applying deep learning models to longitudinal brain MRIs.
Rendering Humans from Object-Occluded Monocular Videos
3D understanding and rendering of moving humans from monocular videos is a challenging task.
An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment
One of the hallmark symptoms of Parkinson's Disease (PD) is the progressive loss of postural reflexes, which eventually leads to gait difficulties and balance problems.
HomE: Homography-Equivariant Video Representation Learning
In this work, we propose a novel method for representation learning of multi-view videos, where we explicitly model the representation space to maintain Homography Equivariance (HomE).
DIAMANT: Dual Image-Attention Map Encoders For Medical Image Segmentation
Although purely transformer-based architectures showed promising performance in many computer vision tasks, many hybrid models consisting of CNN and transformer blocks are introduced to fit more specialized tasks.
SCOPE: Structural Continuity Preservation for Medical Image Segmentation
Although the preservation of shape continuity and physiological anatomy is a natural assumption in the segmentation of medical images, it is often neglected by deep learning methods that mostly aim for the statistical modeling of input data as pixels rather than interconnected structures.
Vision-based Estimation of Fatigue and Engagement in Cognitive Training Sessions
Computerized cognitive training (CCT) is a scalable, well-tolerated intervention that has promise for slowing cognitive decline.
Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model
As acquiring MRIs is expensive, neuroscience studies struggle to attain a sufficient number of them for properly training deep learning models.
Medical Image Segmentation Review: The success of U-Net
U-Net is the most widespread image segmentation architecture due to its flexibility, optimized modular design, and success in all medical image modalities.
Joint Graph Convolution for Analyzing Brain Structural and Functional Connectome
The white-matter (micro-)structural architecture of the brain promotes synchrony among neuronal populations, giving rise to richly patterned functional connections.
SoMoFormer: Multi-Person Pose Forecasting with Transformers
Although there are several previous works targeting the problem of multi-person dynamic pose forecasting, they often model the entire pose sequence as time series (ignoring the underlying relationship between joints) or only output the future pose sequence of one person at a time.
Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding
In this work, we propose a generalized notion of multi-task learning by incorporating both auxiliary tasks that the model should perform well on and adversarial tasks that the model should not perform well on.
Multiple Instance Neuroimage Transformer
As a proof-of-concept, we evaluate the efficacy of our model by training it to identify sex from T1w-MRIs of two public datasets: Adolescent Brain Cognitive Development (ABCD) and the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA).
TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation
Especially, deep neural networks based on seminal architectures such as U-shaped models with skip-connections or atrous convolution with pyramid pooling have been tailored to a wide range of medical image analysis tasks.
Bridging the Gap between Deep Learning and Hypothesis-Driven Analysis via Permutation Testing
A fundamental approach in neuroscience research is to test hypotheses based on neuropsychological and behavioral measures, i. e., whether certain factors (e. g., related to life events) are associated with an outcome (e. g., depression).
A Penalty Approach for Normalizing Feature Distributions to Build Confounder-Free Models
In this paper, we extend the MDN method by applying a Penalty approach (referred to as PDMN).
GaitForeMer: Self-Supervised Pre-Training of Transformers via Human Motion Forecasting for Few-Shot Gait Impairment Severity Estimation
Because of this clinical data scarcity and inspired by the recent advances in self-supervised large-scale language models like GPT-3, we use human motion forecasting as an effective self-supervised pre-training task for the estimation of motor impairment severity.
Combining Counterfactuals With Shapley Values To Explain Image Models
With the widespread use of sophisticated machine learning models in sensitive applications, understanding their decision-making has become an essential task.
Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces
Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases.
PrivHAR: Recognizing Human Actions From Privacy-preserving Lens
The accelerated use of digital cameras prompts an increasing concern about privacy and security, particularly in applications such as action recognition.
Affective Medical Estimation and Decision Making via Visualized Learning and Deep Learning
With the advent of sophisticated machine learning (ML) techniques and the promising results they yield, especially in medical applications, where they have been investigated for different tasks to enhance the decision-making process.
An advanced spatio-temporal convolutional recurrent neural network for storm surge predictions
This study presents a neural network model that can predict storm surge, informed by a database of synthetic storm simulations.
Intervertebral Disc Labeling With Learning Shape Information, A Look Once Approach
Accurate and automatic segmentation of intervertebral discs from medical images is a critical task for the assessment of spine-related diseases such as osteoporosis, vertebral fractures, and intervertebral disc herniation.
MOMA: Multi-Object Multi-Actor Activity Parsing
This paper introduces Activity Parsing as the overarching task of temporal segmentation and classification of activities, sub-activities, atomic actions, along with an instance-level understanding of actors, objects, and their relationships in videos.
Convolutional generative adversarial imputation networks for spatio-temporal missing data in storm surge simulations
The proposed method's performance by considering the improvements and adaptations required for the storm surge data is assessed and compared to the original GAIN and a few other techniques.
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
Longitudinal Correlation Analysis for Decoding Multi-Modal Brain Development
Characterizing such complex brain development requires effective analysis of longitudinal and multi-modal neuroimaging data.
Scalable Differential Privacy With Sparse Network Finetuning
We propose a novel method for privacy-preserving training of deep neural networks leveraging public, out-domain data.
Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning
Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution.
Home Action Genome: Cooperative Compositional Action Understanding
However, there remains a lack of studies that extend action composition and leverage multiple viewpoints and multiple modalities of data for representation learning.
Ranked #1 on
Video Classification
on Home Action Genome
Metadata Normalization
Batch Normalization (BN) and its variants have delivered tremendous success in combating the covariate shift induced by the training step of deep learning methods.
TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild
Joint forecasting of human trajectory and pose dynamics is a fundamental building block of various applications ranging from robotics and autonomous driving to surveillance systems.
Self-Supervised Longitudinal Neighbourhood Embedding
Longitudinal MRIs are often used to capture the gradual deterioration of brain structure and function caused by aging or neurological diseases.
Representation Disentanglement for Multi-modal brain MR Analysis
To address this issue, we propose a margin loss that regularizes the similarity in relationships of the representations across subjects and modalities.
Going Beyond Saliency Maps: Training Deep Models to Interpret Deep Models
Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies.
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
Medical image segmentation is an essential prerequisite for developing healthcare systems, especially for disease diagnosis and treatment planning.
Ranked #4 on
Medical Image Segmentation
on ACDC
Generative Adversarial U-Net for Domain-free Medical Image Augmentation
The shortage of annotated medical images is one of the biggest challenges in the field of medical image computing.
3D CNNs with Adaptive Temporal Feature Resolutions
While the GFLOPs of a 3D CNN can be decreased by reducing the temporal feature resolution within the network, there is no setting that is optimal for all input clips.
Vision-based Estimation of MDS-UPDRS Gait Scores for Assessing Parkinson's Disease Motor Severity
This is the first benchmark for classifying PD patients based on MDS-UPDRS gait severity and could be an objective biomarker for disease severity.
Socially and Contextually Aware Human Motion and Pose Forecasting
In this paper, we propose a novel framework to tackle both tasks of human motion (or trajectory) and body skeleton pose forecasting in a unified end-to-end pipeline.
Longitudinal Self-Supervised Learning
Machine learning analysis of longitudinal neuroimaging data is typically based on supervised learning, which requires a large number of ground-truth labels to be informative.
MetricUNet: Synergistic Image- and Voxel-Level Learning for Precise CT Prostate Segmentation via Online Sampling
Therefore, the proposed network has a dual-branch architecture that tackles two tasks: 1) a segmentation sub-network aiming to generate the prostate segmentation, and 2) a voxel-metric learning sub-network aiming to improve the quality of the learned feature space supervised by a metric loss.
It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
In this work, we present Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory prediction.
Ranked #1 on
Multi Future Trajectory Prediction
on ETH/UCY
Longitudinal Pooling & Consistency Regularization to Model Disease Progression from MRIs
Many neurological diseases are characterized by gradual deterioration of brain structure and function.
Spatio-Temporal Graph for Video Captioning with Knowledge Distillation
In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time.
Spatio-Temporal Graph Convolution for Resting-State fMRI Analysis
The Blood-Oxygen-Level-Dependent (BOLD) signal of resting-state fMRI (rs-fMRI) records the temporal dynamics of intrinsic functional networks in the brain.
Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
In addition, we introduce a new dataset designed specifically for autonomous-driving scenarios in areas with dense pedestrian populations: the Stanford-TRI Intent Prediction (STIP) dataset.
Adversarial Cross-Domain Action Recognition with Co-Attention
Action recognition has been a widely studied topic with a heavy focus on supervised learning involving sufficient labeled videos.
Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision
In contrast to the previous work that aims to solve either the task of pose prediction or trajectory forecasting in isolation, we propose a framework to unify the two problems and address the practically useful task of pedestrian locomotion prediction in the wild.
Representation Learning with Statistical Independence to Mitigate Bias
Presence of bias (in datasets or tasks) is inarguably one of the most critical challenges in machine learning applications that has alluded to pivotal debates in recent years.
Bias-Resilient Neural Network
We apply our method to a synthetic, a medical diagnosis, and a gender classification (Gender Shades) dataset.
Imitation Learning for Human Pose Prediction
Modeling and prediction of human motion dynamics has long been a challenging problem in computer vision, and most existing methods rely on the end-to-end supervised training of various architectures of recurrent neural networks.
Ranked #2 on
Human Pose Forecasting
on Human3.6M
(MAR, walking, 1,000ms metric)
Self-Supervised Representation Learning via Neighborhood-Relational Encoding
Conventional unsupervised learning methods only focused on training deep networks to understand the primitive characteristics of the visual data, mainly to be able to reconstruct the data from a latent space.
Confounder-Aware Visualization of ConvNets
With recent advances in deep learning, neuroimaging studies increasingly rely on convolutional networks (ConvNets) to predict diagnosis based on MR images.
Procedure Planning in Instructional Videos
In this paper, we study the problem of procedure planning in instructional videos, which can be seen as a step towards enabling autonomous agents to plan for complex tasks in everyday settings such as cooking.
Image to Images Translation for Multi-Task Organ Segmentation and Bone Suppression in Chest X-Ray Radiography
Chest X-ray radiography is one of the earliest medical imaging technologies and remains one of the most widely-used for diagnosis, screening, and treatment follow up of diseases related to lungs and heart.
Segmenting the Future
While prior work attempts to predict future video pixels, anticipate activities or forecast future scene semantic segments from segmentation of the preceding frames, methods that predict future semantic segmentation solely from the previous frame RGB data in a single end-to-end trainable model do not exist.
Variational AutoEncoder For Regression: Application to Brain Aging Analysis
While unsupervised variational autoencoders (VAE) have become a powerful tool in neuroimage analysis, their application to supervised learning is under-explored.
Truncated Gaussian-Mixture Variational AutoEncoder
In this paper we propose a novel generative process, in which we use a Gaussian-mixture to model a few major clusters in the data, and use a non-informative uniform distribution to capture the remaining data.
Population-Guided Large Margin Classifier for High-Dimension Low -Sample-Size Problems
Various applications in different fields, such as gene expression analysis or computer vision, suffer from data sets with high-dimensional low-sample-size (HDLSS), which has posed significant challenges for standard statistical and modern machine learning methods.
Action-Agnostic Human Pose Forecasting
In this paper, we propose a new action-agnostic method for short- and long-term human pose forecasting.
Ranked #5 on
Human Pose Forecasting
on Human3.6M
(MAR, walking, 1,000ms metric)
End-To-End Alzheimer's Disease Diagnosis and Biomarker Identification
As shown in computer vision, the power of deep learning lies in automatically learning relevant and powerful features for any perdition task, which is made possible through end-to-end architectures.
End-to-End Parkinson Disease Diagnosis using Brain MR-Images by 3D-CNN
In this work, we use a deep learning framework for simultaneous classification and regression of Parkinson disease diagnosis based on MR-Images and personal information (i. e. age, gender).
AVID: Adversarial Visual Irregularity Detection
Real-time detection of irregularities in visual data is very invaluable and useful in many prospective applications including surveillance, patient monitoring systems, etc.
Adversarially Learned One-Class Classifier for Novelty Detection
Our architecture is composed of two deep networks, each of which trained by competing with each other while collaborating to understand the underlying concept in the target class, and then classify the testing samples.
Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet
SimpNet outperforms the deeper and more complex architectures such as VGGNet, ResNet, WideResidualNet \etc, on several well-known benchmarks, while having 2 to 25 times fewer number of parameters and operations.
Ranked #110 on
Image Classification
on CIFAR-10
Deep Relative Attributes
In order to establish a correspondence between images and to be able to compare the strength of each property between images, relative attributes were introduced.
