Mingqiao Ye

Hi, thanks for watching our work! Here we treat each image/object/mask equally instead of each pixel. For example, if we have two images with one big elephant mask and one...

Thanks! We also provide a [notebook](https://colab.research.google.com/drive/1dhRq4eR6Fbl-yl1vbQvU9hqyyeOidQaU?usp=sharing) now.

Yes, your description of matching is correct. For the first problem, Hungarian matching already considers localization quality, but this matching has no gradient. Loss is calculated based on the matching...

Of course, I've been a little busy recently, it's expected to be released in early November.

Hi, thanks for watching our work! We use the EgoHands dataset with 11k images from this [Roboflow Link](https://universe.roboflow.com/brad-dwyer/egohands-public/dataset/9) and the provided default train/val split. Roboflow has different versions for this...

We use UVO v0.5 with its default [train/val split](https://drive.google.com/drive/folders/1dz2aSAy50tT95I3oWYjVsiJhDwdEE40s).

Hi, sorry for the late reply. We use the same augmentation as DN-DETR with a multi-scale training strategy. The code of cascade_dn_detr is released now and you can find the...

Hi, thanks for watching our work! The json files we provide are examples of different editing. For example, if you want to remove some object(s) in figurines, you can find...

Hi, thanks for watching our work. 256 is the max number of identities here. We set it to 256 since it can be easily stored in one gray image with...

Hi, our implementation of 3D regularization loss would take up more memory (we use 48G memory GPU in our paper). And we are optimizing this issue. For reducing memory, I...