Related papers: Learnable Privacy-Preserving Anonymization for Ped…
Unsupervised person re-identification (re-ID) has attracted increasing research interests because of its scalability and possibility for real-world applications. State-of-the-art unsupervised re-ID methods usually follow a clustering-based…
With billions of personal images being generated from social media and cameras of all sorts on a daily basis, security and privacy are unprecedentedly challenged. Although extensive attempts have been made, existing face image…
Medical data employed in research frequently comprises sensitive patient health information (PHI), which is subject to rigorous legal frameworks such as the General Data Protection Regulation (GDPR) or the Health Insurance Portability and…
Machine unlearning aims to erase data from a model as if the latter never saw them during training. While existing approaches unlearn information from complete or partial access to the training data, this access can be limited over time due…
Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions. Their difference consists in the granularity. Most existing re-ID methods only take identity labels of pedestrians into…
Data privacy is an increasingly important aspect of many real-world Data sources that contain sensitive information may have immense potential which could be unlocked using the right privacy enhancing transformations, but current methods…
Drawing on recent advancements in diffusion models for text-to-image generation, identity-preserved personalization has made significant progress in accurately capturing specific identities with just a single reference image. However,…
Multi-shot pedestrian re-identification problem is at the core of surveillance video analysis. It matches two tracks of pedestrians from different cameras. In contrary to existing works that aggregate single frames features by time series…
Face anonymization aims to conceal identity information while preserving non-identity attributes. Mainstream diffusion models rely on inference-time interventions such as negative guidance or energy-based optimization, which are applied…
Gait recognition is the process of identifying humans from their bipedal locomotion such as walking or running. As such, gait data is privacy sensitive information and should be anonymized where possible. With the rise of higher quality…
De-identification is the task of detecting protected health information (PHI) in medical text. It is a critical step in sanitizing electronic health records (EHRs) to be shared for research. Automatic de-identification classifierscan…
While metric learning is important for Person re-identification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires…
Artificial Intelligence (AI) models are vulnerable to information leakage of their training data, which can be highly sensitive, for example in medical imaging. Privacy Enhancing Technologies (PETs), such as Differential Privacy (DP), aim…
Normalizing flow models have risen as a popular solution to the problem of density estimation, enabling high-quality synthetic data generation as well as exact probability density evaluation. However, in contexts where individuals are…
We present a novel large-scale dataset and comprehensive baselines for end-to-end pedestrian detection and person recognition in raw video frames. Our baselines address three issues: the performance of various combinations of detectors and…
In this paper, we aim to tackle the one-shot person re-identification problem where only one image is labelled for each person, while other images are unlabelled. This task is challenging due to the lack of sufficient labelled training…
Person re-identification (re-ID) aims to tackle the problem of matching identities across non-overlapping cameras. Supervised approaches require identity information that may be difficult to obtain and are inherently biased towards the…
As cameras become ubiquitous in our living environment, invasion of privacy is becoming a growing concern. A common approach to privacy preservation is to remove personally identifiable information from a captured image, but there is a risk…
Learning to recognize pedestrian attributes at far distance is a challenging problem in visual surveillance since face and body close-shots are hardly available; instead, only far-view image frames of pedestrian are given. In this study, we…
Skeleton-based action recognition attracts practitioners and researchers due to the lightweight, compact nature of datasets. Compared with RGB-video-based action recognition, skeleton-based action recognition is a safer way to protect the…