MoiréVision: A Generalized Moiré-based Mechanism for 6-DoF Motion Sensing

J Ning, L Xie, Z Yan, Y Bu, J Luo - Proceedings of the 30th Annual …, 2024 - dl.acm.org
Ultra-high precision motion sensing leveraging computer vision (CV) is a key technology in
many high-precision AR/VR applications such as precise industrial manufacture and image …

CORE-lens: Simultaneous communication and object recognition with disentangled-GAN cameras

Z Liu, T Zheng, C Hu, Y Yang, Y Sun, Y Zhang… - Proceedings of the 28th …, 2022 - dl.acm.org
Optical camera communication (OCC) enabled by LED and embedded cameras has
attracted extensive attention, thanks to its rich spectrum availability and ready deployability …

Moirétag: Angular measurement and tracking with a passive marker

S Qiu, H Amata, W Heidrich - ACM SIGGRAPH 2023 Conference …, 2023 - dl.acm.org
Stable, low-cost, and precise visual measurement of directional information has many
applications in domains such as virtual and augmented reality, visual odometry, or industrial …

Moiré vision: A signal processing technology beyond pixels using the moiré coordinate

K Jo, M Inami - 2023 IEEE International Conference on …, 2023 - ieeexplore.ieee.org
Nowadays, many computer vision (CV) techniques require high-precision feature point
detection in calibration targets. Checkerboards or circle grids are common patterns used to …

MoiréTracker: Continuous Camera-to-Screen 6-DoF Pose Tracking based on Moiré Pattern

J Ning, L Xie, Y Li, Y Chen, Y Bu… - IEEE Journal on …, 2024 - ieeexplore.ieee.org
In the realm of AR applications and particularly camera-to-screen interactions, camera
tracking stands as a crucial technology. However, the ever-increasing demand for tracking …

Image Hiding and Restoration via Deep Moiré Networks

X Cheng, Z Fu - IEEE Signal Processing Letters, 2024 - ieeexplore.ieee.org
Moiré patterns arise when two repetitive textures are superimposed, which often degrade
the image quality when taking photos. However, controllable moiré patterns can be useful in …

Continual Learning with Pre-Trained Models: A Survey

DW Zhou, HL Sun, J Ning, HJ Ye, DC Zhan - arXiv preprint arXiv …, 2024 - arxiv.org
Nowadays, real-world applications often face streaming data, which requires the learning
system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve …

UbiPose: Towards Ubiquitous Outdoor AR Pose Tracking using Aerial Meshes

W Pang, C Xia, B Leong, F Ahmad, J Paek… - Proceedings of the 29th …, 2023 - dl.acm.org
Tracking the position and orientation, or pose, of a viewing device enables AR applications
to accurately embed virtual content in physical spaces. Mobile OSs track pose by matching …

Moiré Backdoor Attack (MBA): A Novel Trigger for Pedestrian Detectors in the Physical World

H Wei, H Yu, K Zhang, Z Wang, J Zhu… - Proceedings of the 31st …, 2023 - dl.acm.org
A backdoor attack is executed by injecting a few poisoned samples into the training dataset
of Deep Neural Networks (DNNs), enabling attackers to implant a hidden manipulation. This …

TV100: a TV series dataset that pre-trained CLIP has not seen

DW Zhou, ZH Qi, HJ Ye, DC Zhan - Frontiers of Computer Science, 2024 - Springer
Conclusion The era of pre-trained models has ushered in a wealth of new insights for the
machine learning community. Among the myriad of questions that arise, one of paramount …