Latent prediction video models exhibit a distinct robustness profile across corruption, occlusion, fine-grained discrimination, and temporal sensitivity compared to other self-supervised video models when used as world models.
Time is matter: Temporal self-supervision for video transformers.arXiv preprint arXiv:2207.09067, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Latent Video Prediction Learns Better World Models
Latent prediction video models exhibit a distinct robustness profile across corruption, occlusion, fine-grained discrimination, and temporal sensitivity compared to other self-supervised video models when used as world models.