Conference item
Unsupervised intuitive physics from visual observations
- Abstract:
-
While learning models of intuitive physics is an active area of research, current approaches fall short of natural intelligences in one important regard: they require external supervision, such as explicit access to physical states, at training and sometimes even at test time. Some approaches sidestep these requirements by building models on top of handcrafted physical simulators. In both cases, however, methods cannot learn automatically new physical environments and their laws as humans do....
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Accepted manuscript, pdf, 6.2MB)
-
- Publisher copy:
- 10.1007/978-3-030-20893-6_44
Authors
Bibliographic Details
- Publisher:
- Springer, Cham Publisher's website
- Journal:
- Asian Conference on Computer Vision (ACCV), 2018 Journal website
- Volume:
- 11363
- Pages:
- 700-716
- Series:
- Lecture Notes in Computer Science
- Host title:
- ACCV 2018: Computer Vision – ACCV 2018
- Publication date:
- 2019-05-29
- Acceptance date:
- 2018-11-08
- DOI:
- ISSN:
-
0302-9743
- Source identifiers:
-
942831
- ISBN:
- 9783030208936
Item Description
- Pubs id:
-
pubs:942831
- UUID:
-
uuid:db3a04e0-7748-4e43-87f7-42c465961245
- Local pid:
- pubs:942831
- Deposit date:
- 2018-11-16
Terms of use
- Copyright holder:
- Springer Nature Switzerland AG
- Copyright date:
- 2019
- Notes:
-
Copyright © 2019 Springer Nature Switzerland AG. This is the accepted manuscript version of the article. The final version is available online from Springer at: DOI
https://doi.org/10.1007/978-3-030-20893-6_44
If you are the owner of this record, you can report an update to it here: Report update to this record