TFVision MoViNet VAR
TFVision MoViNet VAR is Google's image to text model. A TFVision MoViNet variant using Visual AutoRegressive architecture for efficient video understanding and action recognition.
google-tfvision-movinet-var |
| Image to Text |
| Active |
| Google |
| Image |
| Text |
Capabilities
Input1/5
·
✓
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| TFVision MoViNet VAR | — | — | — | — | Current |
| TFVision MoViNet VCN | — | — | — | — | Available |
| TFVision YOLOv7 | — | — | — | — | Available |