# AI Learns Visual Common Sense With New Dataset | Two Minute Papers #169

## Метаданные

- **Канал:** Two Minute Papers
- **YouTube:** https://www.youtube.com/watch?v=XgB3Xg5st2U
- **Дата:** 09.07.2017
- **Длительность:** 2:32
- **Просмотры:** 22,273
- **Источник:** https://ekstraktznaniy.ru/video/14629

## Описание

The paper "The "something something" video database for learning and evaluating visual common sense" is available here:
https://arxiv.org/abs/1706.04261

Source for the video results:
https://medium.com/@raghavgoyal14/7383596f58df

Recommended for you:
Recurrent Neural Network Writes Sentences About Images - https://www.youtube.com/watch?v=e-WB4lfg30M

Two Minute Papers Merch:
US: http://twominutepapers.com/
EU/Worldwide: https://shop.spreadshirt.net/TwoMinutePapers/

WE WOULD LIKE TO THANK OUR GENEROUS PATREON SUPPORTERS WHO MAKE TWO MINUTE PAPERS POSSIBLE:
Andrew Melnychuk, Christian Lawson, Dave Rushton-Smith, Dennis Abts, e, Esa Turkulainen, Kaben Gabriel Nanlohy, Michael Albrecht, Michael Orenstein, Sunil Kim, VR Wizard.
https://www.patreon.com/TwoMinutePapers

Music: Antarctica by Audionautix is licensed under a Creative Commons Attribution license (https://creativecommons.org/licenses/by/4.0/)
Artist: http://audionautix.com/ 

Thumbnail background image credit: https://pixabay.c

## Транскрипт

### Segment 1 (00:00 - 02:00) []

Dear fellow scholars This is two minut papers with kly zsolnay fehér Today We are going to talk about a new endeavor to teach some More Common Sense to Learning algorithms If You Remember in an earlier episode we talked about an Excellent work by Andre carpy Who Built an algorithm that looked at an input image and described in a full well formed sentence What is depicted There By the way he recently became director of Ai at Tesla Before that he worked at open a freshly gradu phd Now that is a scholarly career If ever seen reading about earlier work Was One Of Those moments When I really had To Hold On To My papers not to fall out of the chair but of course As it Should Be With Every new breakthrough The failure cases were thoroughly discussed One Of The motivations for this new work is that We Could improve The results creating a video database thats AON of commonly occurring Events that Would Be useful to learn These Events include Moving and picking up or Holding poking Throwing pouring or plugging in Different things and much More The goal is that These neural algorithms would get tons of training data for These and Would Be able to distinguish whether a human is showing Them Something or Just Moving things about the already existing video databases are surprisingly sparse in this sort of information and in this new freshly published data set we can learn label videos accelerate Research in I love How many of Works are intertwined And how followup Research Works try to address The weaknesses of previous techniques some initial results with Learning on this dataset are also reported to Kick things off and They seem quite Good If You Look at the results Here but since this was not the Focus of the paper we shouldn't Expect superhuman Performance however as Almost All papers in Research are Stepping excited for that Thanks foring And For gener see you next [Muziek] time y