Journal article
Taking visual motion prediction to new heightfields
- Abstract:
-
While the basic laws of Newtonian mechanics are well understood, explaining a physical scenario still requires manually modeling the problem with suitable equations and estimating the associated parameters. In order to be able to leverage the approximation capabilities of artificial intelligence techniques in such physics related contexts, researchers have handcrafted relevant states, and then used neural networks to learn the state transitions using simulation runs as training data. Unfortun...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Bibliographic Details
- Publisher:
- Elsevier Publisher's website
- Journal:
- Computer Vision and Image Understanding Journal website
- Volume:
- 181
- Pages:
- 14-25
- Publication date:
- 2019-02-26
- Acceptance date:
- 2019-02-18
- DOI:
- EISSN:
-
1090-235X
- ISSN:
-
1077-3142
Item Description
- Pubs id:
-
pubs:981679
- UUID:
-
uuid:13db6497-b6bc-4da1-8805-e9b9bc800638
- Local pid:
- pubs:981679
- Source identifiers:
-
981679
- Deposit date:
- 2019-04-16
Terms of use
- Copyright holder:
- Ehrhardt et al
- Copyright date:
- 2019
- Notes:
- © 2019 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record