ViT-Lens

paper
Tencent
Towards omni-modal representations by extending ViT to additional modalities (3D, audio, etc.) via lightweight lens modules. Published at CVPR 2024.
Paper v1 (arXiv)Paper v2 (arXiv)GitHubProject Page

Paper

Venue CVPR 2024
arXiv HTML
multimodalvisionresearch