Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling-Reference-Cited by-同舟云学术

Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling

Published:2023-06 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Hu Zhanhao¹,Chu Wenda²,Zhu Xiaopei³,Zhang Hui⁴,Zhang Bo¹,Hu Xiaolin¹

Affiliation:

1. Tsinghua University,Department of Computer Science and Technology,Beijing,China

2. Institute for Interdisciplinary Information Sciences, Tsinghua University,Beijing,China

3. School of Integrated Circuits, Tsinghua University,Beijing,China

4. Beijing Institute of Fashion Technology,Beijing,China

Funder

National Natural Science Foundation of China

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10203037/10203050/10205173.pdf?arnumber=10205173

Reference48 articles.

1. In-triguing properties of neural networks;szegedy;International Con-ference on Learning Representations,2014

2. Learning coated adversarial camouflages for object detec-tors;duan;Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence,2022

3. Physical adversarial examples for object detectors;song;12th USENIX Workshop on Offensive Tech-nologies ( WOOT 18),2018

4. Adversarial Camouflage: Hiding Physical-World Attacks With Natural Styles

5. An Augmentation Strategy for Medical Image Processing Based on Statistical Shape Model and 3D Thin Plate Spline for Deep Learning

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. An Adversarial Patch Attack for Vehicle Detectors in the Physical World;2023 IEEE International Conference on Unmanned Systems (ICUS);2023-10-13

2. Natural Weather-Style Black-Box Adversarial Attacks Against Optical Aerial Detectors;IEEE Transactions on Geoscience and Remote Sensing;2023

3. Physical Adversarial Attacks for Surveillance: A Survey;IEEE Transactions on Neural Networks and Learning Systems;2023