Search Results for author: Mingjun Li

Found 6 papers, 2 papers with code

Using Motion Forecasting for Behavior-Based Virtual Reality (VR) Authentication

1 code implementation30 Jan 2024 Mingjun Li, Natasha Kholgade Banerjee, Sean Banerjee

In this work, we present the first approach that predicts future user behavior using Transformer-based forecasting and using the forecasted trajectory to perform user authentication.

Motion Forecasting

Evaluating Deep Networks for Detecting User Familiarity with VR from Hand Interactions

no code implementations27 Jan 2024 Mingjun Li, Numan Zafar, Natasha Kholgade Banerjee, Sean Banerjee

As VR devices become more prevalent in the consumer space, VR applications are likely to be increasingly used by users unfamiliar with VR.

End-to-End Latency Optimization of Multi-view 3D Reconstruction for Disaster Response

no code implementations4 Apr 2023 Xiaojie Zhang, Mingjun Li, Andrew Hilton, Amitangshu Pal, Soumyabrata Dey, Saptarshi Debroy

In order to plan rapid response during disasters, first responder agencies often adopt `bring your own device' (BYOD) model with inexpensive mobile edge devices (e. g., drones, robots, tablets) for complex video analytics applications, e. g., 3D reconstruction of a disaster scene.

3D Reconstruction Disaster Response +1

FedRight: An Effective Model Copyright Protection for Federated Learning

no code implementations18 Mar 2023 Jinyin Chen, Mingjun Li, Haibin Zheng

For the first time, we formalize the problem of copyright protection for FL, and propose FedRight to protect model copyright based on model fingerprints, i. e., extracting model features by generating adversarial examples as model fingerprints.

Federated Learning

Rethinking the Defense Against Free-rider Attack From the Perspective of Model Weight Evolving Frequency

1 code implementation11 Jun 2022 Jinyin Chen, Mingjun Li, Tao Liu, Haibin Zheng, Yao Cheng, Changting Lin

To address these challenges, we reconsider the defense from a novel perspective, i. e., model weight evolving frequency. Empirically, we gain a novel insight that during the FL's training, the model weight evolving frequency of free-riders and that of benign clients are significantly different.

Federated Learning Privacy Preserving

Eventor: An Efficient Event-Based Monocular Multi-View Stereo Accelerator on FPGA Platform

no code implementations29 Mar 2022 Mingjun Li, Jianlei Yang, Yingjie Qi, Meng Dong, Yuhao Yang, Runze Liu, Weitao Pan, Bei Yu, Weisheng Zhao

In this paper, Eventor is proposed as a fast and efficient EMVS accelerator by realizing the most critical and time-consuming stages including event back-projection and volumetric ray-counting on FPGA.

Quantization

Cannot find the paper you are looking for? You can Submit a new open access paper.