Aritra Roy Gosthipaty    @ariG23498    11/25/2021      

Our work (\w @RisingSayak) on masked image modelling has been published in https://t.co/xurTwXlKUR. The tutorial is the paper implementation of Masked Autoencoders Are Scalable Vision Learners. arxiv: https://t.co/oXrpg3rleY Link: https://t.co/9SsLfZoHVR https://t.co/1WfR0k3suL
  
    9         49




  Hashtags  

   #3DV2021






 
  Related  

François Chollet    @fchollet    11/24/2021      

New paper walkthrough on https://t.co/m6mT8SrKDD: masked image modeling. Applying the principles of masked language modeling to computer vision. https://t.co/M1ftCAzC9t Created by @arig23498 and @RisingSayak
  
    1         3



Sayak Paul    @RisingSayak    11/25/2021      

New work with @ariG23498 on implementing Masked Autoencoders for self-supervised pretraining of images. Thanks to @endernewton for the helpful discussions.
  
          3



AK    @ak92501    11/29/2021      

Global Interaction Modelling in Vision Transformer via Super Tokens abs: https://t.co/oDe5XATTDX In standard image classification on Imagenet1K, STTS25 achieves 83.5% accuracy which is equivalent to Swin transformer (Swin-B) with circa half the number of parameters (49M)
  
    2         10



Lourdes Agapito    @LourdesAgapito    11/29/2021      

The International Conference on 3D Vision #3DV2021 kicks off tomorrow with two excellent tutorials https://t.co/30HXlueRNt on Spectral Geometry and Neural Rendering. Thanks to our tutorial chairs @angelaqdai and @mmbronstein and to the legendary researchers imparting them!
  
    1         4