Stars
Scenic: A Jax Library for Computer Vision Research and Beyond
Code for paper, "TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency" ECCV 2022
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval [ICCV'21]
Utterance-level Aggregation For Speaker Recognition In The Wild
Understanding Deep Networks via Extremal Perturbations and Smooth Masks
Video embeddings for retrieval with natural language queries
Cross-platform, customizable ML solutions for live and streaming media.
(Hopefully) Up-to-date curriculum vitae based on https://github.com/posquit0/Awesome-CV
Speaker identification with VGGVox network
Reliably download millions of images efficiently
Out of time: automated lip sync in the wild
Mixture-of-Embeddings-Experts
Latex code for making neural networks diagrams
Command-line productivity booster, offers quick access to files and directories, inspired by autojump, z and v.
Directory of tutorials and open-source code repositories for working with Keras, the Python deep learning library
Study of frame rate effects on MSR-VTT dataset
Supporting code for "Emotion Recognition in Speech using Cross-Modal Transfer in the Wild"
Memory consumption and FLOP count estimates for convnets
A matconvnet implementation of the Single Shot Detector