Search Results for author: Ehsan Adeli

Found 45 papers, 22 papers with code

MOMA: Multi-Object Multi-Actor Activity Parsing

no code implementations NeurIPS 2021 Zelun Luo, Wanze Xie, Siddharth Kapoor, Yiyun Liang, Michael Cooper, Juan Carlos Niebles, Ehsan Adeli, Fei-Fei Li

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

no code implementations3 Nov 2021 Ehsan Adeli, Jize Zhang, Alexandros A. Taflanidis

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.

Imputation Time Series

On the Opportunities and Risks of Foundation Models

1 code implementation16 Aug 2021 Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch, Dallas Card, Rodrigo Castellon, Niladri Chatterji, Annie Chen, Kathleen Creel, Jared Quincy Davis, Dora Demszky, Chris Donahue, Moussa Doumbouya, Esin Durmus, Stefano Ermon, John Etchemendy, Kawin Ethayarajh, Li Fei-Fei, Chelsea Finn, Trevor Gale, Lauren Gillespie, Karan Goel, Noah Goodman, Shelby Grossman, Neel Guha, Tatsunori Hashimoto, Peter Henderson, John Hewitt, Daniel E. Ho, Jenny Hong, Kyle Hsu, Jing Huang, Thomas Icard, Saahil Jain, Dan Jurafsky, Pratyusha Kalluri, Siddharth Karamcheti, Geoff Keeling, Fereshte Khani, Omar Khattab, Pang Wei Kohd, Mark Krass, Ranjay Krishna, Rohith Kuditipudi, Ananya Kumar, Faisal Ladhak, Mina Lee, Tony Lee, Jure Leskovec, Isabelle Levent, Xiang Lisa Li, Xuechen Li, Tengyu Ma, Ali Malik, Christopher D. Manning, Suvir Mirchandani, Eric Mitchell, Zanele Munyikwa, Suraj Nair, Avanika Narayan, Deepak Narayanan, Ben Newman, Allen Nie, Juan Carlos Niebles, Hamed Nilforoshan, Julian Nyarko, Giray Ogut, Laurel Orr, Isabel Papadimitriou, Joon Sung Park, Chris Piech, Eva Portelance, Christopher Potts, aditi raghunathan, Rob Reich, Hongyu Ren, Frieda Rong, Yusuf Roohani, Camilo Ruiz, Jack Ryan, Christopher Ré, Dorsa Sadigh, Shiori Sagawa, Keshav Santhanam, Andy Shih, Krishnan Srinivasan, Alex Tamkin, Rohan Taori, Armin W. Thomas, Florian Tramèr, Rose E. Wang, William Wang, Bohan Wu, Jiajun Wu, Yuhuai Wu, Sang Michael Xie, Michihiro Yasunaga, Jiaxuan You, Matei Zaharia, Michael Zhang, Tianyi Zhang, Xikun Zhang, Yuhui Zhang, Lucia Zheng, Kaitlyn Zhou, Percy Liang

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.

Transfer Learning

Longitudinal Correlation Analysis for Decoding Multi-Modal Brain Development

1 code implementation10 Jul 2021 Qingyu Zhao, Ehsan Adeli, Kilian M. Pohl

Characterizing such complex brain development requires effective analysis of longitudinal and multi-modal neuroimaging data.

Scalable Differential Privacy With Sparse Network Finetuning

no code implementations CVPR 2021 Zelun Luo, Daniel J. Wu, Ehsan Adeli, Li Fei-Fei

We propose a novel method for privacy-preserving training of deep neural networks leveraging public, out-domain data.

Transfer Learning

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

2 code implementations10 Jun 2021 Liangqiong Qu, Yuyin Zhou, Paul Pu Liang, Yingda Xia, Feifei Wang, Li Fei-Fei, Ehsan Adeli, Daniel Rubin

Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution.

Federated Learning

Metadata Normalization

1 code implementation CVPR 2021 Mandy Lu, Qingyu Zhao, Jiequan Zhang, Kilian M. Pohl, Li Fei-Fei, Juan Carlos Niebles, Ehsan Adeli

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

no code implementations ICCV 2021 Vida Adeli, Mahsa Ehsanpour, Ian Reid, Juan Carlos Niebles, Silvio Savarese, Ehsan Adeli, Hamid Rezatofighi

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.

Autonomous Driving Human-Object Interaction Detection

Self-Supervised Longitudinal Neighbourhood Embedding

1 code implementation5 Mar 2021 Jiahong Ouyang, Qingyu Zhao, Ehsan Adeli, Edith V Sullivan, Adolf Pfefferbaum, Greg Zaharchuk, Kilian M Pohl

Longitudinal MRIs are often used to capture the gradual deterioration of brain structure and function caused by aging or neurological diseases.

Contrastive Learning Representation Learning

Representation Disentanglement for Multi-modal brain MR Analysis

1 code implementation23 Feb 2021 Jiahong Ouyang, Ehsan Adeli, Kilian M. Pohl, Qingyu Zhao, Greg Zaharchuk

To address this issue, we propose a margin loss that regularizes the similarity in relationships of the representations across subjects and modalities.

Brain Tumor Segmentation Tumor Segmentation

Going Beyond Saliency Maps: Training Deep Models to Interpret Deep Models

no code implementations16 Feb 2021 Zixuan Liu, Ehsan Adeli, Kilian M. Pohl, Qingyu Zhao

Interpretability is a critical factor in applying complex deep learning models to advance the understanding of brain disorders in neuroimaging studies.

Image-to-Image Translation

Generative Adversarial U-Net for Domain-free Medical Image Augmentation

no code implementations12 Jan 2021 Xiaocong Chen, Yun Li, Lina Yao, Ehsan Adeli, Yu Zhang

The shortage of annotated medical images is one of the biggest challenges in the field of medical image computing.

Computed Tomography (CT) Image Augmentation +1

3D CNNs with Adaptive Temporal Feature Resolutions

1 code implementation CVPR 2021 Mohsen Fayyaz, Emad Bahrami, Ali Diba, Mehdi Noroozi, Ehsan Adeli, Luc van Gool, Juergen Gall

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.

Action Recognition

Vision-based Estimation of MDS-UPDRS Gait Scores for Assessing Parkinson's Disease Motor Severity

no code implementations17 Jul 2020 Mandy Lu, Kathleen Poston, Adolf Pfefferbaum, Edith V. Sullivan, Li Fei-Fei, Kilian M. Pohl, Juan Carlos Niebles, Ehsan Adeli

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

no code implementations14 Jul 2020 Vida Adeli, Ehsan Adeli, Ian Reid, Juan Carlos Niebles, Hamid Rezatofighi

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.

Human Dynamics Robot Navigation

Longitudinal Self-Supervised Learning

no code implementations12 Jun 2020 Qingyu Zhao, Zixuan Liu, Ehsan Adeli, Kilian M. Pohl

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.

Representation Learning Self-Supervised Learning

MetricUNet: Synergistic Image- and Voxel-Level Learning for Precise CT Prostate Segmentation via Online Sampling

no code implementations15 May 2020 Kelei He, Chunfeng Lian, Ehsan Adeli, Jing Huo, Yang Gao, Bing Zhang, Junfeng Zhang, Dinggang Shen

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.

Metric Learning Multi-Task Learning +1

Spatio-Temporal Graph Convolution for Resting-State fMRI Analysis

2 code implementations24 Mar 2020 Soham Gadgil, Qingyu Zhao, Adolf Pfefferbaum, Edith V. Sullivan, Ehsan Adeli, Kilian M. Pohl

The Blood-Oxygen-Level-Dependent (BOLD) signal of resting-state fMRI (rs-fMRI) records the temporal dynamics of intrinsic functional networks in the brain.

Time Series

Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction

1 code implementation20 Feb 2020 Bingbin Liu, Ehsan Adeli, Zhangjie Cao, Kuan-Hui Lee, Abhijeet Shenoi, Adrien Gaidon, Juan Carlos Niebles

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.

Autonomous Driving

Adversarial Cross-Domain Action Recognition with Co-Attention

no code implementations22 Dec 2019 Boxiao Pan, Zhangjie Cao, Ehsan Adeli, Juan Carlos Niebles

Action recognition has been a widely studied topic with a heavy focus on supervised learning involving sufficient labeled videos.

Action Recognition

Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision

no code implementations4 Nov 2019 Karttikeya Mangalam, Ehsan Adeli, Kuan-Hui Lee, Adrien Gaidon, Juan Carlos Niebles

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.

Human Dynamics Pose Prediction +1

Representation Learning with Statistical Independence to Mitigate Bias

2 code implementations8 Oct 2019 Ehsan Adeli, Qingyu Zhao, Adolf Pfefferbaum, Edith V. Sullivan, Li Fei-Fei, Juan Carlos Niebles, Kilian M. Pohl

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.

Face Recognition Representation Learning

Bias-Resilient Neural Network

no code implementations25 Sep 2019 Ehsan Adeli, Qingyu Zhao, Adolf Pfefferbaum, Edith V. Sullivan, L. Fei-Fei, Juan Carlos Niebles, Kilian M. Pohl

We apply our method to a synthetic, a medical diagnosis, and a gender classification (Gender Shades) dataset.

Face Recognition Medical Diagnosis

Imitation Learning for Human Pose Prediction

no code implementations ICCV 2019 Borui Wang, Ehsan Adeli, Hsu-kuang Chiu, De-An Huang, Juan Carlos Niebles

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.

Human Pose Forecasting Imitation Learning +1

Self-Supervised Representation Learning via Neighborhood-Relational Encoding

no code implementations ICCV 2019 Mohammad Sabokrou, Mohammad Khalooei, Ehsan Adeli

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.

Anomaly Detection Unsupervised Representation Learning

Confounder-Aware Visualization of ConvNets

1 code implementation30 Jul 2019 Qingyu Zhao, Ehsan Adeli, Adolf Pfefferbaum, Edith V. Sullivan, Kilian M. Pohl

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

no code implementations ECCV 2020 Chien-Yi Chang, De-An Huang, Danfei Xu, Ehsan Adeli, Li Fei-Fei, Juan Carlos Niebles

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

1 code implementation24 Jun 2019 Mohammad Eslami, Solale Tabarestani, Shadi Albarqouni, Ehsan Adeli, Nassir Navab, Malek Adjouadi

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.

Decision Making Translation

Segmenting the Future

no code implementations24 Apr 2019 Hsu-kuang Chiu, Ehsan Adeli, Juan Carlos Niebles

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.

Autonomous Driving Decision Making +3

Variational AutoEncoder For Regression: Application to Brain Aging Analysis

1 code implementation11 Apr 2019 Qingyu Zhao, Ehsan Adeli, Nicolas Honnorat, Tuo Leng, Kilian M. Pohl

While unsupervised variational autoencoders (VAE) have become a powerful tool in neuroimage analysis, their application to supervised learning is under-explored.

Variational Inference

Truncated Gaussian-Mixture Variational AutoEncoder

no code implementations11 Feb 2019 Qingyu Zhao, Nicolas Honnorat, Ehsan Adeli, Kilian M. Pohl

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.

Outlier Detection

Population-Guided Large Margin Classifier for High-Dimension Low -Sample-Size Problems

no code implementations5 Jan 2019 Qingbo Yin, Ehsan Adeli, Liran Shen, Dinggang Shen

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.

Face Recognition General Classification

End-To-End Alzheimer's Disease Diagnosis and Biomarker Identification

no code implementations1 Oct 2018 Soheil Esmaeilzadeh, Dimitrios Ioannis Belivanis, Kilian M. Pohl, Ehsan Adeli

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

no code implementations13 Jun 2018 Soheil Esmaeilzadeh, Yao Yang, Ehsan Adeli

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).

General Classification

AVID: Adversarial Visual Irregularity Detection

2 code implementations24 May 2018 Mohammad Sabokrou, Masoud Pourreza, Mohsen Fayyaz, Rahim Entezari, Mahmood Fathy, Jürgen Gall, Ehsan Adeli

Real-time detection of irregularities in visual data is very invaluable and useful in many prospective applications including surveillance, patient monitoring systems, etc.

Anomaly Detection

Adversarially Learned One-Class Classifier for Novelty Detection

7 code implementations CVPR 2018 Mohammad Sabokrou, Mohammad Khalooei, Mahmood Fathy, Ehsan Adeli

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.

Anomaly Detection One-class classifier

Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet

3 code implementations17 Feb 2018 Seyyed Hossein Hasanpour, Mohammad Rouhani, Mohsen Fayyaz, Mohammad Sabokrou, Ehsan Adeli

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.

Image Classification

Deep Relative Attributes

1 code implementation13 Dec 2015 Yaser Souri, Erfan Noury, Ehsan Adeli

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.

Cannot find the paper you are looking for? You can Submit a new open access paper.