morgott

感谢您的回复，我觉得这是一个很好的方式，但我认为主要的原因是https://github.com/CVHub520/X-AnyLabeling/blob/5f1357423b9c95c0e703e54ff8314d4b6f07fb4c/anylabeling/services/auto_labeling/segment_anything_2_video.py#L354-L360 我们在外面设置的label会被上面的代码覆盖，label的text只会受到sam2中tracklet顺序的影响，就如你所说的，为什么不复用我们完成目标时设置的label呢

> Hello, @Morgott-The-Omen-King, > > Thank you for your inquiry about SAM2 video annotation. The scenario you've described is indeed a common challenge in object tracking across frames. > >...

> 你好，网址是啥？ https://arxiv.org/pdf/2409.15272

> > Thank you for your suggestion. I also want to evaluate this model using linear probing. I will add this assessment to our plan. > > segmentation too :)...