The ubiquitous and demonstrably suboptimal choice of resizing images to ...
Open-vocabulary object detection has benefited greatly from pretrained
v...
The most performant spatio-temporal action localisation models use exter...
We present Imagen Video, a text-conditional video generation system base...
Transfer learning is the predominant paradigm for training deep networks...
Generating temporally coherent high fidelity video is an important miles...
Scenic is an open-source JAX library with a focus on Transformer-based m...