Gunnar Sigurdsson

PyVideoResearch. A repository of common methods, datasets, and tasks for video research

charades-algorithms. Activity Recognition Algorithms for the Charades Dataset

actions-for-actions. Diagnostic tools and additional visualizations from "What Actions are Needed for Understanding Human Actions in Videos?" ICCV 2017

actor-observer. ActorObserverNet code in PyTorch from "Actor and Observer: Joint Modeling of First and Third-Person Videos", CVPR 2018

temporal-fields. Code for training temporal fully-connected CRF models in Torch

visual-grounding. Project page for "Visual Grounding in Video for Unsupervised Word Translation" CVPR 2020

charades-webcam. Real-time smart webcam in TensorFlow trained on the Charades dataset

srnn. Skipping Recurrent Neural Networks

java-chess-ai. Parallel implementation of Minimax with alpha beta pruning for chess playing

ActivityNet. This repository is intended to host tools and demos for ActivityNet

exemplar-shape. MATLAB implementation of "Interpretable Exemplar-Based Shape Classification Using Constrainted Sparse Linear Models" by Sigurdsson, Yang, Tran, and Prince.

world-features. Framework for extending neural networks layers with arbitrary transforms.

sound-features. Implementations of a few features for analyzing sound data.