Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

SoMoFormer: Multi-Person Pose Forecasting with Transformers


Aug 30, 2022
Edward Vendrow, Satyajit Kumar, Ehsan Adeli, Hamid Rezatofighi

* 10 pages, 6 figures. Submitted to WACV 2023. Our method was submitted to the SoMoF benchmark leaderboard dated March 2022. See https://somof.stanford.edu/result/217/ 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding


Aug 22, 2022
Stephen Su, Samuel Kwong, Qingyu Zhao, De-An Huang, Juan Carlos Niebles, Ehsan Adeli


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multiple Instance Neuroimage Transformer


Aug 19, 2022
Ayush Singla, Qingyu Zhao, Daniel K. Do, Yuyin Zhou, Kilian M. Pohl, Ehsan Adeli


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation


Aug 01, 2022
Reza Azad, Moein Heidari, Moein Shariatnia, Ehsan Khodapanah Aghdam, Sanaz Karimijafarbigloo, Ehsan Adeli, Dorit Merhof


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Bridging the Gap between Deep Learning and Hypothesis-Driven Analysis via Permutation Testing


Jul 28, 2022
Magdalini Paschali, Qingyu Zhao, Ehsan Adeli, Kilian M. Pohl

* Accepted at the 5th workshop on PRedictive Intelligence in Medicine (PRIME 2022) - MICCAI 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Penalty Approach for Normalizing Feature Distributions to Build Confounder-Free Models


Jul 11, 2022
Anthony Vento, Qingyu Zhao, Robert Paul, Kilian M. Pohl, Ehsan Adeli


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

GaitForeMer: Self-Supervised Pre-Training of Transformers via Human Motion Forecasting for Few-Shot Gait Impairment Severity Estimation


Jun 30, 2022
Mark Endo, Kathleen L. Poston, Edith V. Sullivan, Li Fei-Fei, Kilian M. Pohl, Ehsan Adeli

* Accepted as a conference paper at MICCAI (Medical Image Computing and Computer Assisted Intervention) 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Combining Counterfactuals With Shapley Values To Explain Image Models


Jun 14, 2022
Aditya Lahiri, Kamran Alipour, Ehsan Adeli, Babak Salimi

* ICML 2022 Workshop on Responsible Decision Making in Dynamic Environments 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces


Jun 10, 2022
Kamran Alipour, Aditya Lahiri, Ehsan Adeli, Babak Salimi, Michael Pazzani


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

PrivHAR: Recognizing Human Actions From Privacy-preserving Lens


Jun 08, 2022
Carlos Hinojosa, Miguel Marquez, Henry Arguello, Ehsan Adeli, Li Fei-Fei, Juan Carlos Niebles


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
6
7
>>