In this paper, we propose a framework for predicting the performance of a vision algorithm given the input image or video so as to maximize the algorithm's ability to provide...
We address the character identification problem in
movies and television videos: assigning names to faces on
the screen. Most prior work on person recognition in video
assumes s...
Timothee Cour, Benjamin Sapp, Akash Nagle, Ben Tas...
With our interest to improve our education in computer science, an understanding of how students learn about CS concepts, how different concepts are understood, as well as the con...
Mordechai Ben-Ari, Anders Berglund, Shirley Booth,...
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human...
Abhinav Gupta, Trista Chen, Francine Chen, Don Kim...
As massive repositories of real-time human commentary, social media platforms have arguably evolved far beyond passive facilitation of online social interactions. Rapid analysis o...