VideoMAE V2
Nanjing UniversityShenzhen Institute of Advanced TechnologyShanghai AI LabAction recognitionOpen weights
The VideoMAE V2 model is an open-weights action recognition model from Nanjing University,Shenzhen Institute of Advanced Technology,Shanghai AI Lab with 1000000000.0 parameters.
About VideoMAE V2
Scale is the primary factor for building a powerful foundation model that could well generalize to a variety of downstream tasks. However, it is still challenging to train video foundation models with billions of parameters. This paper shows that vid
Details
- Provider
- Nanjing University,Shenzhen Institute of Advanced Technology,Shanghai AI Lab
- Task
- Action recognition
- Parameters
- 1000000000.0
- Released
- 2023-03-29
- Open weights
- Yes