I am a graduate student at the University of Michigan doing computer vision research under the supervision of Jia Deng. My interest is in human pose and motion understanding with recent work tackling multi-person keypoint localization and instance segmentation.

Publications

Alejandro Newell and Jia Deng. "Associative Embedding: End-to-end Learning for Joint Detection and Grouping" arXiv preprint arXiv:1611.05424, 2016. [pdf]

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

Research

Associative Embedding: End-to-end Learning for Joint Detection and Grouping (New!)

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. Check it out on arXiv.


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.