Understanding where people are looking is an informative social cue. In this work, we present Gaze360, a large-scale gaze-tracking dataset and method for robust 3D gaze estimation in unconstrained images. Our dataset consists of 238 subjects in indoor and outdoor environments with labeled 3D gaze across a wide range of head poses and distances. It is the largest publicly available dataset of its kind by both subject and variety, made possible by a simple and efficient collection method.

Torch implementation for learning a mapping from input images to output images.

This repo covers the implementation for CMC (as well as Momentum Contrast and Instance Discrimination), which learns representations from multiview data in a self-supervised way (by multiview, we mean multiple sensory, multiple modal data, or literally multiple viewpoint data.

Vega is a visualization grammar, a declarative language for creating, saving, and sharing interactive visualization designs. With Vega, you can describe the visual appearance and interactive behavior of a visualization in a JSON format, and generate web-based views using Canvas or SVG.

This repository provides experiments, scripts, and instructions for reproducing the experiments in our paper, Low-Latency Graph Streaming Using Compressed Purely-Functional Trees. Our paper introduces Aspen, a graph-streaming system based on compressed purely-functional trees. Aspen is designed for maintaining a dynamic graph subject to updates by a single writer, while supporting multiple concurrent readers. Due to the fact that the graph is purely-functional, all operations in Aspen are strictly serializable.