PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learning
Paper • 2602.20537 • Published • 1
PFGNet
PFGNet is a fully convolutional framework for efficient spatiotemporal predictive learning.
This repository provides dataset-specific trained checkpoints of PFGNet on multiple benchmarks.
Code: https://github.com/fhjdqaq/PFGNet
Paper: https://huggingface.co/papers/2602.20537
Provided by: WYK Lab
Project page: https://kaimaoge.github.io
Available checkpoints
| Dataset | Checkpoint |
|---|---|
| Moving MNIST | pfg_mmnist.ckpt |
| Moving Fashion MNIST | pfg_mfmnist.ckpt |
| TaxiBJ | pfg_taxibj.ckpt |
| KTH (10→20) | pfg_kth20.ckpt |
| KTH (10→40) | pfg_kth40.ckpt |
| Human3.6M | pfg_human.ckpt |
Usage
Please refer to the official code repository for training and inference scripts.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support