I am at the University of Michigan doing research in computer vision under the supervision of Jia Deng. My research interests include scene understanding and human pose estimation.

Publications

Pixels to Graphs by Associative Embedding
Alejandro Newell and Jia Deng. Neural Information Processing Systems (NIPS), 2017.
[arXiv] (project page and code coming soon)

Associative Embedding: End-to-end Learning for Joint Detection and Grouping
Alejandro Newell, Zhiao Huang, and Jia Deng. Neural Information Processing Systems (NIPS), 2017.
[arXiv]

Stacked Hourglass Networks for Human Pose Estimation
Alejandro Newell, Kaiyu Yang, and Jia Deng. European Conference for Computer Vision (ECCV), 2016.
[arXiv] [project] [code]

Research

Associative Embedding: End-to-end Learning for Joint Detection and Grouping

We teach a network to simultaneously output detections and group assignments. This technique can be easily integrated into any network architecture that produces pixel-wise predictions. We show how to apply this method to both multi-person pose estimation and instance segmentation, and we present results for both tasks.



Stacked Hourglass Networks for Human Pose Estimation

I worked on a convolutional network architecture for single person pose estimation achieving state-of-the-art performance. For more info check out the project page.