Visual Understanding without Naming:Bypassing the “Language Bottleneck”
Event details
| Date | 19.06.2015 |
| Hour | 10:00 › 11:00 |
| Speaker | Alexei (Alyosha) Efros, UC Berkeley (USA) |
| Location | |
| Category | Conferences - Seminars |
Most modern visual understanding approaches rely on supervision by
word labels to achieve their impressive performance. But there are
many more things in our visual world than we have words to describe
them with.
Using language is supervisory signal risks missing out on much of the
visual subtlety. In this talk, I will describe some of our recent
efforts to bypass the "language bottleneck" and instead use
information that is already in the data, such as spatial context and
visual consistency, to help in visual understanding, visual
correspondence, and image retrieval.
word labels to achieve their impressive performance. But there are
many more things in our visual world than we have words to describe
them with.
Using language is supervisory signal risks missing out on much of the
visual subtlety. In this talk, I will describe some of our recent
efforts to bypass the "language bottleneck" and instead use
information that is already in the data, such as spatial context and
visual consistency, to help in visual understanding, visual
correspondence, and image retrieval.
Links
Practical information
- General public
- Free
Organizer
- Sabine Susstrunk
Contact
- Sylvie Thomet