About

I am a reseach scientist at Meta (Reality Labs). I obtained my Ph.D. in Computer Engineering from University of Wisconsin-Madison in 2023 (Advisor: Prof. Umit Y. Ogras). I also work closely with Prof. Yin Li. Prior to UW, I received my B.S. from University of Electronic Science and Technology of China (UESTC). During my Ph.D. study, I work as a research intern on computer vision field at Meta (Reality Labs), TikTok and Ambarella.

My research interests include ML/CV, human activity recognition (HAR), 3D human pose estimation (HPE), multi-modal sensing, NeRF, generative models, and smart healthcare algorithms.

Shoot me an email to sizhe.an@wisc.edu if you are interested in talking to me!

News

  • September 2023: Joined Meta (Reality Labs) as a research scientist!
  • August 2023: Defended my Ph.D.! What an exciting journey!
  • February 2022: Two papers accepted to CVPR 2023 (PanoHead stars and Panic-3D stars ) and one paper accepted to DAC 2023!
  • December 2022: Started research internship in Meta Reality Labs working on NeRF for device generalization!
  • September 2022: mRI (multi-modal human pose estimation dataset) got accepted in NeurIPS 2022! Dataset and code are partially released, give it a try!!
  • August 2022: Passed my prelim exam!
  • June 2022: Started research internship in TikTok working on 3D-aware full-head GAN!
  • February 2022: Paper accepted for publication in Design Automation Conference (DAC) 2022. See y’all in SF! (Acceptance rate: 23%) [paper]
  • September 2021: Paper accepted for publication in ACM Transactions on Internet of Things (TIOT), and journal-track paper presentation in ACM SenSys 2021 (Acceptance rate: 8/49 ≈ 16%) [arXiv]
  • July 2021: MARS got nominated for best paper award! [github]
  • June 2021: Joined Ambarella as a computer vision intern.
  • November 2020: Passed my qual exam!
  • June 2020: Transferred to UW-Madison from Arizona State
  • October 2019: Best paper award at EMBEDDED SYSTEMS WEEK 2019! (1/75)

Research Highlights

PanoHead

PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360°

Sizhe An, Hongyi Xu, Yichun Shi, Guoxian Song, Umit Ogras, and Linjie Luo. Accepted in CVPR 2023 [Paper][Page][Code]


mRI

mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors

Sizhe An, Yin Li, and Umit Ogras. Accepted in NeurIPS 2022 Datasets & Benchmarks Track [Dataset][code][Openreview]


MARS MARS: mmWave-based Assistive Rehabilitation System for Smart Healthcare

Sizhe An and Umit Ogras. CODES, ESWEEK 2021, oral presentation [Paper][Code and data]


MGait

MGait: Model-Based Gait Analysis Using Wearable Bend and Inertial Sensors

S An, Y Tuncel, T Basaklar, GK Krishnakumar, G Bhat, U Ogras. ACM Transactions on Internet of Things (TIOT) [arXiv][Paper]


Transfer Learning for Human Activity Recognition using Representational Analysis of Neural Networks

S An, G Bhat, S Gumussoy, U Ogras. ACM Transactions on Computing for Healthcare.[arXiv][code]


HAR

An ultra-low energy human activity recognition accelerator for wearable health applications

G Bhat, Y Tuncel, S An, HG Lee, UY Ogras. Best paper award at ESWEEK 2019!


Trends

A Systematic Survey of Research Trends in Technology Usage for Parkinson’s Disease

R Deb, G Bhat, S An, U Ogras, H Shill. [Paper][Code and data]

Visitors