Mohammed Innat innat

Pinned Loading

1. [NeurIPS'22] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

   Jupyter Notebook 22 3

2. Keras 3 Implementation of Video Swin Transformers for 3D Video Modeling

   Jupyter Notebook 32 4

3. Play around with Pixel in Python

   Python 45 34

4. AI Toolkit for Healthcare Imaging in Keras 3

   Jupyter Notebook 21 3

5. A Keras implementation of hybrid efficientnet swin transformer model.

   Jupyter Notebook 34 6

6. [ICCV2023] UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer

   Jupyter Notebook 9 3