Oliver Groth

@omgroth

PhD student & computer scientist training robots.

Vrijeme pridruživanja: srpanj 2018.

Tweetovi

Blokirali ste korisnika/cu @omgroth

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

  1. Prikvačeni tweet
    15. sij 2019.

    My new blog post is online! 😀 Check it out, if you’re curious what the project is all about and how we’re trying to give robots a physical intuition.

    Poništi
  2. proslijedio/la je Tweet
    4. velj

    camera-ready version of GENESIS is now online: We would like to sincerely thank the reviewers for their thoughtful comments and useful suggestions :)

    Poništi
  3. proslijedio/la je Tweet
    30. sij

    Feynman Lessons for Learning: 🧠 1) Understanding is more important than memorization! 2) Learn principles, not formulas. 3) Ask questions! 4) Read Books every day. 5) Teaching is a powerful tool to learning.

    Poništi
  4. proslijedio/la je Tweet
    28. sij

    +, Σ, and ∫ are just different evolutions of the same Pokémon

    Prikaži ovu nit
    Poništi
  5. 26. sij

    An insightful article making an interesting connection between and the philosophical concepts of nativism and empiricism on the example of the language generation network . True intelligence needs to go beyond statistical prediction.

    Poništi
  6. proslijedio/la je Tweet
    25. sij

    Fall in love with some activity, and do it! Nobody ever figures out what life is all about, and it doesn't matter. Explore the world. Nearly everything is really interesting if you go into it deeply enough!

    Poništi
  7. 18. sij

    Thread on learning of decision boundaries with differnt classifier types - a nice visual recap of ML 101. 🙂

    Poništi
  8. 14. sij

    If you’re looking for an ambitious environment to conduct cutting-edge research, consider applying to and his team - a great place to be, not just for . 😃

    Poništi
  9. 7. sij

    Action Genome, the latest offspring of the , features 10K videos annotated with 0.4M objects and 1.7M visual relationships. Scene graphs have also received a spatio-temporal extension. Great work by the team .

    Poništi
  10. 26. stu 2019.

    I was quite amazed by how much 3D information can be inferred from a *single* RGB image! Cool work by my colleagues , and Andrea Vedaldi. Also shows that is not just all but smart ideas about feature extraction remain important!

    Poništi
  11. proslijedio/la je Tweet
    Poništi
  12. proslijedio/la je Tweet
    15. stu 2019.
    Poništi
  13. proslijedio/la je Tweet
    29. lis 2019.

    “fiercely competitive environment leads to a haste to publish and a larger number of less rigorous papers results.”

    Poništi
  14. 24. lis 2019.

    Scene graphs are a great way of combining recent methods with established to endow systems with more explicit semantics. Great workshop by my friend and former collaborator ! Check it out, if you’re at .

    Poništi
  15. 24. lis 2019.

    I agree. The AI-hype will come back to bite us in the long run, if we’re not careful about how we communicate our field’s successes, i.e. putting them in realistic perspectives and avoiding overclaiming.

    Poništi
  16. proslijedio/la je Tweet
    19. lis 2019.

    Keeping up with the literature

    Poništi
  17. 20. lis 2019.

    A very nice codebase released by my colleague . It has been a pleasure to play with GENESIS so far! 🙂

    Poništi
  18. 20. lis 2019.

    Congratulations ! Very well deserved! "She is also an incredible mentor and supporter of younger students." - I couldn't agree more. I'm still very thankful that she convinced me of pursuing a PhD when I was a clueless Master's student visiting her lab 4 years ago. 🙂

    Poništi
  19. proslijedio/la je Tweet
    17. lis 2019.

    Moonshot demos that ignore the economics (e.g. by needing ridiculously-costly compute) don't tell you that much about the real world. The real world is *all about* the economics. After we brought back a moonrock in the real moonshot, we didn't start moon mining.

    Poništi
  20. proslijedio/la je Tweet
    11. lis 2019.

    Machine learning now has an over-agitated culture that IMHO is bad for researcher wellbeing. You're not a loser if hype, firehose arXiv, FOMO, feuds, overwork & random reviews cause you unhealthily-sustained stress, anxiety & gloom. We didn't & don't have to have this culture.

    Poništi
  21. proslijedio/la je Tweet
    9. lis 2019.

    Correcting small typos in Google Docs you are asked to review is the business equivalent of killing wild boars to level up in World of Warcraft

    Poništi

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:

    ·