Christoph Feichtenhofer
Graph View
Backlinks
- A ConvNet for the 2020s
- Hiera - A Hierarchical Vision Transformer without the Bells-and-Whistles
- MeMViT - Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition
- Perception Encoder - The best visual embeddings are not at the output of the network
- SAM 3 - Segment Anything with Concepts