| id |
acadia23_v3_173 |
| authors |
Doyle, Shelby; C Niquille, Simone; Cornelius, Chris; Kanngieser, AM |
| year |
2023 |
| title |
Operational Transitions: Panel Discussion |
| source |
ACADIA 2023: Habits of the Anthropocene: Scarcity and Abundance in a Post-Material Economy [Volume 3: Proceedings of the 43rd Annual Conference for the Association for Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9891764-1-0]. Denver. 26-28 October 2023. edited by A. Crawford, N. Diniz, R. Beckett, J. Vanucchi, M. Swackhamer 24-32. |
| summary |
Hi. I have three questions for Simone. They are kind of built on top of each other. I will try to be as brief as I can. The first is about language. You talked about how object recognition algorithms have these kinds of different categories, such as the difference between iPod and media player. So how much of the kind of errors we are seeing in the case of the chairs are contributed by the limits of the language? And the second question is kind of built on top of that. It's like the matter of context. When those chairs, as shown without background, they are kind of floating objects. So how would multi-modal inputs, such as image to image, or video to 3D, will contribute or improve the algorithm's understanding of the context? And the third one is something that you haven't talked about as much as the matter of user agency. I was thinking about the diagram between the cup and the bowl. And something similar, such as a glass used for drinking water when it's tall enough. At some point, it can be used as a vase. What kind of situation would enable users to make different decisions about what the object is used for? |
| series |
ACADIA |
| type |
keynote |
| email |
|
| full text |
 file.pdf (282,466 bytes) |
| references |
Content-type: text/plain
|
| last changed |
2024/04/17 14:00 |
|
