Paleo: A Performance Model for Deep Neural Networks

Joint work with Evan R. Sparks and Ameet Talwalkar

Paleo is an analytical model to estimate the scalability and performance of deep learning systems. It can be used for efficiently exploring the space of scalable deep learning systems and quickly diagnosing their effectiveness for a given problem instances. Paleo is robust to the choice of network architecture, hardware, software, communication schemes, and parallelization strategies.

Runner-up prize for best real-world application at Southern California Machine Learning Symposium 2016.

Paper Web View on Github

Restricted Visual Turing Test

Joint work with Tianfu Wu, Mun-Wai Lee, and Song-Chun Zhu

This project features a restricted visual Turing test (VTT) which evaluates computer vision systems' understanding of scenes and events in videos by story-line based queries. We collected a long-term and multi-camera captured video dataset. To perform the test, we built an integrated system consisting of a well-designed architecture, various vision modules, a knowledge base, and a query engine.

Project Website

Topic Discovery and Story Segmentation for Broadcast News

Joint work with Weixin Li, Jungseock Joo, and Song-Chun Zhu

Topic discovery and story segmentation provides fundamental methods for automatically organizing, analyzing, searching, and visualizing the vast amount of news videos available online. In this project, we present a topic discovery and story segmentation framework based on Swendsen-Wang Cuts, aiming at dividing news videos into stories and generating a topic hierarchy to organize these stories.

Paper