Log inSign up
user avatar
Carl Vondrick
@cvondrick
Associate Professor at @Columbia.
New York, NY
cs.columbia.edu/~vondrick/
Joined October 2012
569
Following
6,689
Followers
  • user avatar
    Carl Vondrick
    @cvondrick
    Jun 27, 2018
    Our latest work shows that learning to colorize videos causes visual tracking to emerge automatically! Blog: ai.googleblog.com/2018/06/self-s… Paper: arxiv.org/abs/1806.09594 @alirezafathi @kevskibombom @sguada @abhi2610
    00:00
  • user avatar
    Carl Vondrick
    @cvondrick
    Nov 22, 2016
    Fantastic conditional GAN results by Isola et al phillipi.github.io/pix2pix/
  • user avatar
    Carl Vondrick
    @cvondrick
    Mar 2, 2021
    The future is hard to anticipate! In our latest #CVPR2021 paper, we introduce a framework for learning *what* is predictable in the future. Rather than committing up front to categories to predict, our approach learns how to hedge the bet. hyperfuture.cs.columbia.edu
    00:00
  • user avatar
    Carl Vondrick
    @cvondrick
    Dec 15, 2016
    Finding Tiny Faces -- had to zoom in quite a bit to parse how cool the results are! arxiv.org/pdf/1612.04402…
  • user avatar
    Carl Vondrick
    @cvondrick
    Dec 19, 2020
    Learning unsupervised machine translation is easier if you open your eyes! Image distributions create transitive relations between languages. This creates incidental supervision for learning multilingual representations on 50 unpaired languages arxiv.org/pdf/2012.04631… @Surisdi
    00:00
  • user avatar
    Carl Vondrick
    @cvondrick
    Nov 29, 2018
    Neural networks fooled by unusual poses arxiv.org/pdf/1811.11553…
  • user avatar
    Carl Vondrick
    @cvondrick
    Dec 20, 2016
    Learning Features by Watching Objects Move by Pathak et al arxiv.org/pdf/1612.06370…
  • user avatar
    Carl Vondrick
    @cvondrick
    Apr 20, 2017
    amazing generations of the video future! Red border means output, green is input. sites.google.com/a/umich.edu/ru…
    GIF
  • user avatar
    Carl Vondrick
    @cvondrick
    Oct 28, 2016
    SoundNet: Learning natural sound representations with convnets and 2 million unlabeled videos. web.mit.edu/vondrick/sound…
  • user avatar
    Carl Vondrick
    @cvondrick
    Dec 2, 2016
    Recognizing objects and scenes from sound only. Turn on your speakers! More visualizations: projects.csail.mit.edu/soundnet/
    00:00
  • user avatar
    Carl Vondrick
    @cvondrick
    Apr 19, 2017
    Unsupervised Learning by Predicting Noise by Bojanowski and Joulin. Cool yet simple idea that works quite well!! arxiv.org/pdf/1704.05310…
  • user avatar
    Carl Vondrick
    @cvondrick
    Jul 15, 2020
    What causes adversarial examples? Latest #ECCV2020 paper from @ChengzhiM and Amogh shows that deep networks are vulnerable partly because they are trained on too few tasks. Just by increasing tasks, we strengthen robustness for each task individually. arxiv.org/pdf/2007.07236…
  • user avatar
    Carl Vondrick
    @cvondrick
    Jun 15, 2020
    Oops! Dave+Bo introduce a dataset of unconstrained videos showing unintentional action. We study self-supervised approaches for learning video representations of intentionality. #CVPR2020 Poster 93, Tue 10am PST Website: oops.cs.columbia.edu Paper: arxiv.org/abs/1911.11206
    00:00
  • user avatar
    Carl Vondrick
    @cvondrick
    Jun 20, 2021
    Learning from Unlabeled Video (#LUV❤️‍🔥) starts today at 1:50pm EDT / 10:50am PDT! sites.google.com/view/luv2021 You will LUV the speaker lineup and the curated papers! 😍 featuring @pathak2206 @akanazawa @SongShuran and more #CVPR2021 #CVPR21 #CVPR