RVM uses recurrent computation inside a masked autoencoder to learn video representations that match or exceed prior video and image models on classification, tracking, and dense spatial tasks with up to 30x better parameter efficiency.
Unifying (machine) vision via counter- factual world modeling.arXiv preprint arXiv:2306.01828
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A zero-shot visual world model trained on one child's experience achieves broad competence on physical understanding benchmarks while matching developmental behavioral patterns.
A probabilistic graphical model called 3WM unifies 3D vision tasks into one system that performs them zero-shot by selecting different inference pathways through multimodal scene nodes.
citing papers explorer
-
Recurrent Video Masked Autoencoders
RVM uses recurrent computation inside a masked autoencoder to learn video representations that match or exceed prior video and image models on classification, tracking, and dense spatial tasks with up to 30x better parameter efficiency.
-
Zero-shot World Models Are Developmentally Efficient Learners
A zero-shot visual world model trained on one child's experience achieves broad competence on physical understanding benchmarks while matching developmental behavioral patterns.
-
Unified 3D Scene Understanding Through Physical World Modeling
A probabilistic graphical model called 3WM unifies 3D vision tasks into one system that performs them zero-shot by selecting different inference pathways through multimodal scene nodes.