Video-MAE-Quantized
Sports and human action recognition in videos.
Video MAE (Masked Auto Encoder) is a network for doing video classification that uses the ViT (Vision Transformer) backbone.
Technical Details
Model checkpoint:Kinectics-400
Input resolution:224x224
Number of parameters:87.7M
Model size:87.7 MB
Applicable Scenarios
- Camera
- Action Recognition
Licenses
Source Model:CC-BY-4.0
Deployable Model:AI Model Hub License
Tags
- backbone
- quantized
Supported IoT Devices
- QCS8275 (Proxy)
- QCS8550 (Proxy)
- QCS9075 (Proxy)
Supported IoT Chipsets
- Qualcomm® QCS8275 (Proxy)
- Qualcomm® QCS8550 (Proxy)
- Qualcomm® QCS9075 (Proxy)
Related Models
See all models
Looking for more? See models created by industry leaders.
Discover Model Makers