Posts by Collection

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles

ACM Conference on Embedded Networked Sensor Systems (SenSys 2020)

Ran Xu, Chen-lin Zhang, Pengcheng Wang, Jayoung Lee, Subrata Mitra, Somali Chaterji Yin Li, Saurabh Bagchi,

ApproxDet is an adaptive video object detection framework for mobile devices that dynamically balances accuracy and latency under changing content and resource conditions.

ApproxNet: Content and Contention-Aware Video Object Classification System for Embedded Clients

ACM Transactions on Sensor Networks (TOSN 2022)

Ran Xu, Rakesh Kumar, Pengcheng Wang, Peter Bai, Ganga Meghanath, Somali Chaterji Subrata Mitra, Saurabh Bagchi,

ApproxNet dynamically adapts a single DNN for video classification on embedded devices, outperforming prior models in latency and accuracy.

LiteReconfig: Cost and Content Aware Reconfiguration of Video Object Detection Systems for Mobile GPUs

The European Conference on Computer Systems (EuroSys 2022)

Ran Xu, Jayoung Lee, Pengcheng Wang, Saurabh Bagchi, Yin Li, Somali Chaterji

LiteReconfig features a cost-benefit analyzer to decide which features to use, and which execution branch to run, at inference time.

Virtuoso: Energy- and Latency-Aware Streamlining of Streaming Videos on SOCs

ACM Transactions on Design Automation of Electronic Systems (TODAES 2023)

Jayoung Lee, Pengcheng Wang, Ran Xu, Sarthak Jain, Venkat Dasari, Noah Weston, Yin Li, Saurabh Bagchi, Somali Chaterji

Virtuoso is an efficient and adaptive video object detection system that jointly optimizes accuracy, energy, and latency, outperforming 15 SOTA models on NVIDIA Jetson mobile GPUs.

Agile3D: Adaptive Contention- and Content-Aware 3D Object Detection for Embedded GPUs

ACM International Conference on Mobile Systems, Applications, and Services (MobiSys 2025)

Pengcheng Wang, Zhuoming Liu, Shayok Bagchi, Ran Xu, Saurabh Bagchi, Yin Li, Somali Chaterji

Agile3d is a novel approach for efficient 3D object detection on embedded GPUs with adaptive contention and content awareness.

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015