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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

SAGE: Saliency-Guided Mixup with Optimal Rearrangements


Oct 31, 2022
Avery Ma, Nikita Dvornik, Ran Zhang, Leila Pishdad, Konstantinos G. Derpanis, Afsaneh Fazly

Add code

* Accepted at British Machine Vision Conference (BMVC) 2022. Code: https://github.com/SamsungLabs/SAGE 

   Access Paper or Ask Questions

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

SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models


Oct 12, 2022
Ziyi Wu, Nikita Dvornik, Klaus Greff, Thomas Kipf, Animesh Garg

Add code

* Project page: https://slotformer.github.io/ 

   Access Paper or Ask Questions

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

Graph2Vid: Flow graph to Video Grounding forWeakly-supervised Multi-Step Localization


Oct 10, 2022
Nikita Dvornik, Isma Hadji, Hai Pham, Dhaivat Bhatt, Brais Martinez, Afsaneh Fazly, Allan D. Jepson

Add code

* ECCV 2022 
* ECCV'22, oral 

   Access Paper or Ask Questions

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

P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision


May 04, 2022
He Zhao, Isma Hadji, Nikita Dvornik, Konstantinos G. Derpanis, Richard P. Wildes, Allan D. Jepson

Add code

* Accepted as an oral paper at CVPR 2022 

   Access Paper or Ask Questions

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

Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers


Aug 26, 2021
Nikita Dvornik, Isma Hadji, Konstantinos G. Derpanis, Animesh Garg, Allan D. Jepson

Add code


   Access Paper or Ask Questions

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

Selecting Relevant Features from a Universal Representation for Few-shot Classification


Mar 20, 2020
Nikita Dvornik, Cordelia Schmid, Julien Mairal

Add code


   Access Paper or Ask Questions

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

Diversity with Cooperation: Ensemble Methods for Few-Shot Classification


Mar 27, 2019
Nikita Dvornik, Cordelia Schmid, Julien Mairal

Add code


   Access Paper or Ask Questions

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

On the Importance of Visual Context for Data Augmentation in Scene Understanding


Sep 06, 2018
Nikita Dvornik, Julien Mairal, Cordelia Schmid

Add code

* arXiv admin note: substantial text overlap with arXiv:1807.07428 

   Access Paper or Ask Questions

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

Modeling Visual Context is Key to Augmenting Object Detection Datasets


Jul 19, 2018
Nikita Dvornik, Julien Mairal, Cordelia Schmid

Add code

* ECCV2018, Sep 2018, Munich, Germany. 2018 

   Access Paper or Ask Questions

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

BlitzNet: A Real-Time Deep Network for Scene Understanding


Aug 09, 2017
Nikita Dvornik, Konstantin Shmelkov, Julien Mairal, Cordelia Schmid

Add code


   Access Paper or Ask Questions

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