中文
相关论文

相关论文: Privacy Beyond Pixels: Latent Anonymization for Pr…

200 篇论文

Anonymizing textual documents is a highly context-sensitive problem: the appropriate balance between privacy protection and utility preservation varies with the data domain, privacy objectives, and downstream application. However, existing…

计算与语言 · 计算机科学 2026-04-21 Gabriel Loiseau , Damien Sileo , Damien Riquet , Maxime Meyer , Marc Tommasi

Latent Action Models (LAMs) enable learning from actionless data for applications ranging from robotic control to interactive world models. However, existing LAMs typically focus on short-horizon frame transitions and capture low-level…

机器人学 · 计算机科学 2026-03-09 Hanjung Kim , Lerrel Pinto , Seon Joo Kim

In this paper, we introduce a learning model able to conceals personal information (e.g. gender, age, ethnicity, etc.) from an image, while maintaining any additional information present in the image (e.g. smile, hair-style, brightness).…

机器学习 · 计算机科学 2019-09-23 Moshe Hanukoglu , Nissan Goldberg , Aviv Rovshitz , Amos Azaria

The ubiquitous use of face recognition has sparked increasing privacy concerns, as unauthorized access to sensitive face images could compromise the information of individuals. This paper presents an in-depth study of the privacy protection…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Yuxi Mi , Yuge Huang , Jiazhen Ji , Minyi Zhao , Jiaxiang Wu , Xingkun Xu , Shouhong Ding , Shuigeng Zhou

Editing natural images using textual descriptions in text-to-image diffusion models remains a significant challenge, particularly in achieving consistent generation and handling complex, non-rigid objects. Existing methods often struggle to…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Dinh-Khoi Vo , Thanh-Toan Do , Tam V. Nguyen , Minh-Triet Tran , Trung-Nghia Le

The automatic understanding of video content is advancing rapidly. Empowered by deeper neural networks and large datasets, machines are increasingly capable of understanding what is concretely visible in video frames, whether it be objects,…

计算机视觉与模式识别 · 计算机科学 2026-04-09 Gowreesh Mago , Pascal Mettes , Stevan Rudinac

Existing research on privacy-preserving Human Activity Recognition (HAR) typically evaluates methods against a binary paradigm: clear video versus a single privacy transformation. This limits cross-method comparability and obscures the…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Samar Ansari

Large Language Models (LLMs) are gaining increasing attention due to their exceptional performance across numerous tasks. As a result, the general public utilize them as an influential tool for boosting their productivity while natural…

密码学与安全 · 计算机科学 2023-06-16 Zhigang Kan , Linbo Qiao , Hao Yu , Liwen Peng , Yifu Gao , Dongsheng Li

Ensuring the ethical use of video data involving human subjects, particularly infants, requires robust anonymization methods. We propose BLANKET (Baby-face Landmark-preserving ANonymization with Keypoint dEtection consisTency), a novel…

计算机视觉与模式识别 · 计算机科学 2026-01-13 Ditmar Hadera , Jan Cech , Miroslav Purkrabek , Matej Hoffmann

In modern intelligent video surveillance systems, automatic anomaly detection through computer vision analytics plays a pivotal role which not only significantly increases monitoring efficiency but also reduces the burden on live…

计算机视觉与模式识别 · 计算机科学 2020-04-14 Sijie Zhu , Chen Chen , Waqas Sultani

As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognize and appropriately handle privacy-sensitive content is essential. We conduct a comprehensive evaluation of ten…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Laurens Samson , Nimrod Barazani , Sennay Ghebreab , Yuki M. Asano

Text-to-image diffusion models, such as Stable Diffusion, generate highly realistic images from text descriptions. However, the generation of certain content at such high quality raises concerns. A prominent issue is the accurate depiction…

计算机视觉与模式识别 · 计算机科学 2026-02-09 Liang Shi , Jie Zhang , Shiguang Shan

The unprecedented increase in the usage of computer vision technology in society goes hand in hand with an increased concern in data privacy. In many real-world scenarios like people tracking or action recognition, it is important to be…

计算机视觉与模式识别 · 计算机科学 2020-12-01 Maxim Maximov , Ismail Elezi , Laura Leal-Taixé

Privacy preservation is a prerequisite for using video data in Operating Room (OR) research. Effective anonymization relies on the exhaustive localization of every individual; even a single missed detection necessitates extensive manual…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Keqi Chen , Vinkle Srivastav , Armine Vardazaryan , Cindy Rolland , Didier Mutter , Nicolas Padoy

The increasing capabilities of deep neural networks for re-identification, combined with the rise in public surveillance in recent years, pose a substantial threat to individual privacy. Event cameras were initially considered as a…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Katharina Bendig , René Schuster , Nicole Thiemer , Karen Joisten , Didier Stricker

Latent action models (LAMs) aim to learn action-relevant changes from unlabeled videos by compressing changes between frames as latents. However, differences between video frames can be caused by controllable changes as well as exogenous…

机器学习 · 计算机科学 2025-11-13 Chuheng Zhang , Tim Pearce , Pushi Zhang , Kaixin Wang , Xiaoyu Chen , Wei Shen , Li Zhao , Jiang Bian

As the privacy risks posed by camera surveillance and facial recognition have grown, so has the research into privacy preservation algorithms. Among these, visual privacy preservation algorithms attempt to impart bodily privacy to subjects…

计算机视觉与模式识别 · 计算机科学 2023-01-13 Sophie Noiret , Siddharth Ravi , Martin Kampel , Francisco Florez-Revuelta

We introduce Latent Action Pretraining for general Action models (LAPA), an unsupervised method for pretraining Vision-Language-Action (VLA) models without ground-truth robot action labels. Existing Vision-Language-Action models require…

Recent advances in diffusion models have enabled high-quality synthesis of specific subjects, such as identities or objects. This capability, while unlocking new possibilities in content creation, also introduces significant privacy risks,…

计算机视觉与模式识别 · 计算机科学 2025-11-04 Tae-Young Lee , Juwon Seo , Jong Hwan Ko , Gyeong-Moon Park

Existing pedestrian attribute recognition (PAR) algorithms are mainly developed based on a static image, however, the performance is unreliable in challenging scenarios, such as heavy occlusion, motion blur, etc. In this work, we propose to…

计算机视觉与模式识别 · 计算机科学 2024-04-30 Xiao Wang , Qian Zhu , Jiandong Jin , Jun Zhu , Futian Wang , Bo Jiang , Yaowei Wang , Yonghong Tian