Minimal JS interface to an image classifer

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

OneFormer: One Transformer to Rule Universal Image Segmentation, arxiv 2022 / CVPR 2023

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

ImageBind One Embedding Space to Bind Them All

Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification

3D ResNets for Action Recognition (CVPR 2018)

Supplementary code for the paper "Hyperbolic Image Embeddings".