DreamFusion has recently demonstrated the utility of a pre-trained
text-...
Denoising diffusion models (DDMs) have shown promising results in 3D poi...
Existing transformer-based image backbones typically propagate feature
i...
In this paper, we present a non-parametric structured latent variable mo...
Manually labeling video datasets for segmentation tasks is extremely tim...
In this paper, we propose the differentiable mask-matching network (DMM-...
In this paper, we study the problem of parsing structured knowledge grap...
Generating adversarial examples is an intriguing problem and an importan...