Maneesh Agrawala

@magrawala

Forest Baskett Professor of Computer Science and Director of the Brown Institute for Media Innovation at Stanford.

graphics.stanford.edu/~maneesh
Vrijeme pridruživanja: studeni 2009.
32 fotografije ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @magrawala

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @magrawala

  1. 29. sij

    New work on Visual QA on charts and graphs, with natural language Explanations. Code and dataset available!

    6 proslijeđenih tweetova 22 korisnika označavaju da im se sviđa
    Poništi
  2. proslijedio/la je Tweet
    20. sij

    1/ This time I just have a single image here. It was taken in 1900 in New York City, and it's of course colorized by my latest and greatest and unreleased DeOldify model. I've done this one before but it's great to test the model on high resolution renders.

    3.889 proslijeđenih tweetova 27.012 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    1. sij

    A+ Sparkline-relevant paper on choosing aspect ratios in data graphics,essential in all time-series plots, by “Multi-Scale Banking to 45º” IEEE Tranactions on Visualization and Computer Graphics, 2006. Stat inference textbooks should bank their graphics!

    13 proslijeđenih tweetova 38 korisnika označava da im se sviđa
    Poništi
  4. proslijedio/la je Tweet
    28. pro 2019.

    StyleGAN2 projection + VisBeat = The Lazy Person's Cursed Music Video

    1 reply 2 proslijeđena tweeta 28 korisnika označava da im se sviđa
    Poništi
  5. proslijedio/la je Tweet
    25. pro 2019.

    Maneesh Agrawala & his students nail what is wrong in video editing tools and how AI can help.

    2 proslijeđena tweeta 2 korisnika označavaju da im se sviđa
    Poništi
  6. 11. pro 2019.

    Very nice writeup of a shot type detector!

    Trained a ResNet-50 that can recognise shot scale in images (Close Up, Long, Medium, etc) with a custom dataset. Fascinating heatmaps! Thanks to and for the fastai library Project: Code:
    Prikaži ovu nit
    1 reply 4 korisnika označavaju da im se sviđa
    Poništi
  7. 9. pro 2019.

    Why are there so many different graphic novelizations of the Mueller report?

    1 korisnik označava da mu se sviđa
    Poništi
  8. proslijedio/la je Tweet
    9. pro 2019.

    Less than 24 hours away from Symposium in SF at RSVP today to hear Jon Miller, Hany Farid, Roger MacDonald, Jason Gonzalez, & Leila Zia discuss solutions to

    3 proslijeđena tweeta 8 korisnika označava da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    3. pro 2019.

    Honored to have been invited to final class presentations for by and others. Amazing stuff. And good to see continue to grow.

    3 proslijeđena tweeta 11 korisnika označava da im se sviđa
    Poništi
  10. proslijedio/la je Tweet
    3. pro 2019.

    VisBeat is a really cool project by that allows you to sync visual rhythm with audio. Make em dance to the beat of a different drum. This Missy Elliot and Thays Monaro mashup is just plain fun.

    2 proslijeđena tweeta 2 korisnika označavaju da im se sviđa
    Poništi
  11. 3. pro 2019.

    Cool example of ’s Visual Beat!

    2:01
    I didn't intend to use the same song but the walk cadence here is a mood. Visbeat has a simple Colab notebook, just add a '!pip install visbeat' on top:
    Prikaži ovu nit
    3 korisnika označavaju da im se sviđa
    Poništi
  12. 23. stu 2019.

    Can’t wait to talk more about this project!

    17-year-old Trayvon Martin was killed for looking “suspicious.” Did we perpetuate a -ve perception of this child by using images of him wearing a hoodie? What if there was an automated way to analyze editorial decisions? That’s why my team is building a TV news analyzer
    11 korisnika označava da im se sviđa
    Poništi
  13. 21. lis 2019.

    And presenting her work view dependent video texture for 360 video.

    7 korisnika označava da im se sviđa
    Poništi
  14. 21. lis 2019.

    This is getting ready to present her work on optimizing Portrait Lighting at capture time at .

    1 reply 2 proslijeđena tweeta 15 korisnika označava da im se sviđa
    Poništi
  15. proslijedio/la je Tweet
    17. lis 2019.

    TONIGHT! The Brown Institute Showcase! It will take place on the ground floor of Pulitzer Hall in . RSVP at . Tonight we celebrate the work of talented engineers and journalists...

    7 proslijeđenih tweetova 10 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    9. lis 2019.

    Why Train What You Can Code? Excited to share Rekall - using programmatic composition to find new events in video! Paper on arXiv, and code available on Github! Blog:

    1 reply 21 proslijeđeni tweet 36 korisnika označava da im se sviđa
    Poništi
  17. 8. lis 2019.

    Very excited to host , editor in chief of at the for a conversation tonight. 5pm in Allen 101X on the Stanford Campus.

    1 reply 1 proslijeđeni tweet 4 korisnika označavaju da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    29. kol 2019.

    Worried about missing important narrative events when watching 360° video? Check out our upcoming paper! With: , Steven DiVerdi, and

    1 reply 3 proslijeđena tweeta 10 korisnika označava da im se sviđa
    Poništi
  19. 28. kol 2019.

    A new tool to help photographers find good lighting when capturing portraits (w/ ).

    If you are interested in camera interfaces, portrait lighting, or just want to see what I’ve been up to for the past few years, check out our upcoming paper:
    7 korisnika označava da im se sviđa
    Poništi
  20. 5. kol 2019.

    Looking forward to seeing what people do with it!

    We've released the recipe dataset with action/ingredient annotation generated from our RecipeScape project! Yes, it's way overdue, but as some say, better late than never. Thanks for the help!
    4 korisnika označavaju da im se sviđa
    Poništi

@magrawala još nije objavio nijedan Tweet.

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·