Sookwan Han

**Hi, thanks for open-sourcing the OpenCLIP.** **I'm trying to use your OpenCLIP ViT-H/14, but am facing problems when I follow the exact instructions provided in Huggingface repo (_https://huggingface.co/laion/CLIP-ViT-H-14-frozen-xlm-roberta-large-laion5B-s13B-b90k_).** **Specifically, I...

**Request for adding 2 papers** **[Oral Paper]** **Title**: CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images **ArXiv**: https://arxiv.org/abs/2308.12288 **Project Page**: https://jellyheadandrew.github.io/projects/chorus **Related area**: Human-Object Interaction, Self-supervised learning,...

Are there any detailed explanation for the model specification?

3

Hello! Thanks for your nice work on spatial role labeling. I'm using it for my task and it is very useful. I'd like to reference your work, but I found...

Add new community pipeline for 'Adaptive Mask Inpainting', introduced in [ECCV2024] ComA

8

Add new community pipeline for 'Adaptive Mask Inpainting' introduced in **[ECCV2024] Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models**. # What does this PR...