Related papers: STPrivacy: Spatio-Temporal Privacy-Preserving Acti…
Panoramic Activity Recognition (PAR) seeks to identify diverse human activities across different scales, from individual actions to social group and global activities in crowded panoramic scenes. PAR presents two major challenges: 1)…
Privacy is a crucial concern in collaborative machine vision where a part of a Deep Neural network (DNN) model runs on the edge, and the rest is executed on the cloud. In such applications, the machine vision model does not need the exact…
Virtual reality (VR) and "metaverse" systems have recently seen a resurgence in interest and investment as major technology companies continue to enter the space. However, recent studies have demonstrated that the motion tracking…
Several companies (e.g., Meta, Google) have initiated "data-for-good" projects where aggregate location data are first sanitized and released publicly, which is useful to many applications in transportation, public health (e.g., COVID-19…
Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action…
With rising technologies, the protection of privacy-sensitive information is becoming increasingly important. In industry and production facilities, image or video recordings are beneficial for documentation, tracing production errors or…
Pedestrian Attribute Recognition is a foundational computer vision task that provides essential support for downstream applications, including person retrieval in video surveillance and intelligent retail analytics. However, existing…
The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video. While vision Transformers have driven the recent advances in video…
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…
Face analysis has been studied from different angles to infer emotion, poses, shapes, and landmarks. Traditionally RGB cameras are used, yet for fine-grained tasks standard sensors might not be up to the task due to their latency, making it…
Computer-vision hospital systems can greatly assist healthcare workers and improve medical facility treatment, but often face patient resistance due to the perceived intrusiveness and violation of privacy associated with visual…
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…
Video Anomaly Detection (VAD) presents a significant challenge in computer vision, particularly due to the unpredictable and infrequent nature of anomalous events, coupled with the diverse and dynamic environments in which they occur.…
The widespread deployment of high-resolution visual sensing systems, coupled with the rise of foundation models, has amplified privacy risks in video-based applications. Differentially private pixelization offers mathematically guaranteed…
Face presentation attack detection (fPAD) plays a critical role in the modern face recognition pipeline. The generalization ability of face presentation attack detection models to unseen attacks has become a key issue for real-world…
Pedestrian Attribute Recognition (PAR) is an indispensable task in human-centered research and has made great progress in recent years with the development of deep neural networks. However, the potential vulnerability and anti-interference…
Pedestrian attribute recognition (PAR) has received increasing attention because of its wide application in video surveillance and pedestrian analysis. Extracting robust feature representation is one of the key challenges in this task. The…
We propose a data-driven framework for optimizing privacy-preserving data release mechanisms to attain the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing specific sensitive…
Video-based person re-identification (reID) aims to retrieve person videos with the same identity as a query person across multiple cameras. Spatial and temporal distractors in person videos, such as background clutter and partial…
Preserving privacy of continuous and/or high-dimensional data such as images, videos and audios, can be challenging with syntactic anonymization methods which are designed for discrete attributes. Differential privacy, which provides a more…