Abstract Deep Image Manipulation Localization (IML) models suffer from training data
insufficiency and thus heavily rely on pre-training. We argue that contrastive learning is more …

Fall risk assessment needs contemporary approaches based on habitual data. Currently,
inertial measurement unit (IMU)-based wearables are used to inform free-living spatio …

We present the design and creation of a disability-first dataset,“BIV-Priv,” which contains 728
images and 728 videos of 14 private categories captured by 26 blind participants to support …

Unprecedented video collection and sharing have exacerbated privacy concerns and led to
increasing interest in privacy-preserving tools. A satisfactory video de-identification tool …

Visual-language foundation Models (FMs) exhibit remarkable zero-shot generalization
across diverse tasks, largely attributed to extensive pre-training on large-scale datasets …

Videos represent the most prevailing form of digital media for communication, information
dissemination, and monitoring. However, their widespread use has increased the risks of …

Advances in cameras and web technology have made it easy to capture and share large
amounts of face videos over to an unknown audience with uncontrollable purposes. These …

Unprecedented video collection and sharing have exacerbated privacy concerns and led to
increasing interest in privacy-preserving tools. A satisfactory video de-identification tool …

The Privacy-sensitive Object Identification (POI) task allocates bounding boxes for privacy-
sensitive objects in a scene. The key to POI is settling an object's privacy class (privacy …

This paper proposes a global optimization solution that combines different types of
perceptual information to further improve transmission efficiency. First, a new rate-distortion …