no code implementations • 15 Dec 2022 • Wei Peng, Ehsan Adeli, Qingyu Zhao, Kilian M. Pohl
To this end, we train a conditional DPM with attention to generate an MRI sub-volume (a set of slices at arbitrary locations) conditioned on another subset of slices from the same MRI.
1 code implementation • 27 Nov 2022 • Reza Azad, Ehsan Khodapanah Aghdam, Amelie Rauland, Yiwei Jia, Atlas Haddadi Avval, Afshin Bozorgpour, Sanaz Karimijafarbigloo, Joseph Paul Cohen, Ehsan Adeli, Dorit Merhof
U-Net is the most widespread image segmentation architecture due to its flexibility, optimized modular design, and success in all medical image modalities.
no code implementations • 27 Oct 2022 • Yueting Li, Qingyue Wei, Ehsan Adeli, Kilian M. Pohl, Qingyu Zhao
The white-matter (micro-)structural architecture of the brain promotes synchrony among neuronal populations, giving rise to richly patterned functional connections.
1 code implementation • 30 Aug 2022 • Edward Vendrow, Satyajit Kumar, Ehsan Adeli, Hamid Rezatofighi
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.
no code implementations • 22 Aug 2022 • Stephen Su, Samuel Kwong, Qingyu Zhao, De-An Huang, Juan Carlos Niebles, Ehsan Adeli
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.
1 code implementation • 19 Aug 2022 • Ayush Singla, Qingyu Zhao, Daniel K. Do, Yuyin Zhou, Kilian M. Pohl, Ehsan Adeli
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).
1 code implementation • 1 Aug 2022 • Reza Azad, Moein Heidari, Moein Shariatnia, Ehsan Khodapanah Aghdam, Sanaz Karimijafarbigloo, Ehsan Adeli, Dorit Merhof
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.
1 code implementation • 28 Jul 2022 • Magdalini Paschali, Qingyu Zhao, Ehsan Adeli, Kilian M. Pohl
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).
1 code implementation • 11 Jul 2022 • Anthony Vento, Qingyu Zhao, Robert Paul, Kilian M. Pohl, Ehsan Adeli
In this paper, we extend the MDN method by applying a Penalty approach (referred to as PDMN).
1 code implementation • 30 Jun 2022 • Mark Endo, Kathleen L. Poston, Edith V. Sullivan, Li Fei-Fei, Kilian M. Pohl, Ehsan Adeli
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.
no code implementations • 14 Jun 2022 • Aditya Lahiri, Kamran Alipour, Ehsan Adeli, Babak Salimi
With the widespread use of sophisticated machine learning models in sensitive applications, understanding their decision-making has become an essential task.
no code implementations • 10 Jun 2022 • Kamran Alipour, Aditya Lahiri, Ehsan Adeli, Babak Salimi, Michael Pazzani
Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases.
no code implementations • 8 Jun 2022 • Carlos Hinojosa, Miguel Marquez, Henry Arguello, Ehsan Adeli, Li Fei-Fei, Juan Carlos Niebles
The accelerated use of digital cameras prompts an increasing concern about privacy and security, particularly in applications such as action recognition.
1 code implementation • 9 May 2022 • Mohammad Eslami, Solale Tabarestani, Ehsan Adeli, Glyn Elwyn, Tobias Elze, Mengyu Wang, Nazlee Zebardast, Nassir Navab, Malek Adjouadi
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.
no code implementations • 18 Apr 2022 • Ehsan Adeli, Luning Sun, JianXun Wang, Alexandros A. Taflanidis
This study presents a neural network model that can predict storm surge, informed by a database of synthetic storm simulations.
no code implementations • 6 Apr 2022 • Reza Azad, Moein Heidari, Julien Cohen-Adad, Ehsan Adeli, Dorit Merhof
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.
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.
no code implementations • 3 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.
1 code implementation • 16 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 Koh, 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.
1 code implementation • 10 Jul 2021 • Qingyu Zhao, Ehsan Adeli, Kilian M. Pohl
Characterizing such complex brain development requires effective analysis of longitudinal and multi-modal neuroimaging data.
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.
1 code implementation • CVPR 2022 • Liangqiong Qu, Yuyin Zhou, Paul Pu Liang, Yingda Xia, Feifei Wang, Ehsan Adeli, Li Fei-Fei, 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.
1 code implementation • CVPR 2021 • Nishant Rai, Haofeng Chen, Jingwei Ji, Rishi Desai, Kazuki Kozuka, Shun Ishizaka, Ehsan Adeli, Juan Carlos Niebles
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
1 code implementation • 30 Apr 2021 • Nishant Rai, Ehsan Adeli, Kuan-Hui Lee, Adrien Gaidon, Juan Carlos Niebles
Labeling videos at scale is impractical.
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.
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.
1 code implementation • 5 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.
1 code implementation • 23 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.
no code implementations • 16 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.
14 code implementations • 8 Feb 2021 • Jieneng Chen, Yongyi Lu, Qihang Yu, Xiangde Luo, Ehsan Adeli, Yan Wang, Le Lu, Alan L. Yuille, Yuyin Zhou
Medical image segmentation is an essential prerequisite for developing healthcare systems, especially for disease diagnosis and treatment planning.
Ranked #3 on Medical Image Segmentation on ACDC
no code implementations • 12 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.
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.
no code implementations • 17 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.
no code implementations • 14 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.
no code implementations • 12 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.
no code implementations • 15 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.
3 code implementations • ECCV 2020 • Karttikeya Mangalam, Harshayu Girase, Shreyas Agarwal, Kuan-Hui Lee, Ehsan Adeli, Jitendra Malik, Adrien Gaidon
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
no code implementations • 31 Mar 2020 • Jiahong Ouyang, Qingyu Zhao, Edith V. Sullivan, Adolf Pfefferbaum, Susan F. Tapert, Ehsan Adeli, Kilian M. Pohl
Many neurological diseases are characterized by gradual deterioration of brain structure and function.
no code implementations • CVPR 2020 • Boxiao Pan, Haoye Cai, De-An Huang, Kuan-Hui Lee, Adrien Gaidon, Ehsan Adeli, Juan Carlos Niebles
In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time.
2 code implementations • 24 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.
1 code implementation • 20 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.
no code implementations • 22 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.
no code implementations • 4 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.
2 code implementations • 8 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.
no code implementations • 25 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.
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.
Ranked #2 on Human Pose Forecasting on Human3.6M (MAR, walking, 1,000ms metric)
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.
1 code implementation • 30 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.
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.
1 code implementation • 24 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.
no code implementations • 24 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.
2 code implementations • 11 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.
no code implementations • 11 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.
no code implementations • 5 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.
1 code implementation • 23 Oct 2018 • Hsu-kuang Chiu, Ehsan Adeli, Borui Wang, De-An Huang, Juan Carlos Niebles
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)
no code implementations • 1 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.
no code implementations • 13 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).
2 code implementations • 24 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.
5 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.
3 code implementations • 17 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.
Ranked #108 on Image Classification on CIFAR-10
1 code implementation • 13 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.