Unsupervised intuitive physics from visual observations
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 sidest...
Glavni autori: | Ehrhardt, S, Monszpart, A, Mitra, N, Vedaldi, A |
---|---|
Format: | Conference item |
Izdano: |
Springer, Cham
2019
|
Slični predmeti
-
Taking visual motion prediction to new heightfields
od: Ehrhardt, S, i dr.
Izdano: (2019) -
Taking visual motion prediction to new heightfields
od: Ehrhardt, S, i dr.
Izdano: (2019) -
RELATE: physically plausible multi-object scene synthesis using structured latent spaces
od: Ehrhardt, S, i dr.
Izdano: (2020) -
Scrutinizing and de-biasing intuitive physics with neural stethoscopes
od: Fuchs, FB, i dr.
Izdano: (2019) -
Dissociating intuitive physics from intuitive psychology: Evidence from Williams syndrome
od: Kamps, Frederik S, i dr.
Izdano: (2021)