Sa2VA
Public? Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
Creat:2025-01-06T23:03:53
Update:2025-03-27T05:34:08
https://arxiv.org/abs/2501.04001
1.2K
Stars
3
Stars Increase
? Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos