SCENT, a single-stage transformer-based conditioned neural field, jointly handles reconstruction, interpolation, and forecasting on sparse and noisy scientific data, reporting state-of-the-art results on Navier-Stokes and AirDelhi benchmarks.
Is space-time attention all you need for video understanding? In International Conference on Machine Learning (ICML), 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields
SCENT, a single-stage transformer-based conditioned neural field, jointly handles reconstruction, interpolation, and forecasting on sparse and noisy scientific data, reporting state-of-the-art results on Navier-Stokes and AirDelhi benchmarks.