PFGNet introduces a frequency-guided peripheral gating block in a pure convolutional architecture to enable adaptive receptive fields for efficient spatiotemporal prediction with fewer parameters than prior methods.
Scaling up your kernels: Large kernel design in convnets towards uni- versal representations.IEEE Transactions on Pattern Analy- sis and Machine Intelligence, 2025
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
-
PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learning
PFGNet introduces a frequency-guided peripheral gating block in a pure convolutional architecture to enable adaptive receptive fields for efficient spatiotemporal prediction with fewer parameters than prior methods.