Related papers: Privacy-Preserving Human Activity Recognition from…
Future activity anticipation is a challenging problem in egocentric vision. As a standard future activity anticipation paradigm, recursive sequence prediction suffers from the accumulation of errors. To address this problem, we propose a…
We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information. Rather than simply inhibiting a given fixed pre-trained…
Inverse reinforcement learning (IRL) methods assume that the expert data is generated by an agent optimizing some reward function. However, in many settings, the agent may optimize a reward function subject to some constraints, where the…
Many computer vision systems require users to upload image features to the cloud for processing and storage. These features can be exploited to recover sensitive information about the scene or subjects, e.g., by reconstructing the…
Along with the improvement of radar technologies, Automatic Target Recognition (ATR) using Synthetic Aperture Radar (SAR) and Inverse SAR (ISAR) has come to be an active research area. SAR/ISAR are radar techniques to generate a…
Human action recognition (HAR) in videos is one of the core tasks of video understanding. Based on video sequences, the goal is to recognize actions performed by humans. While HAR has received much attention in the visible spectrum, action…
Human action recognition is an important problem in computer vision. It has a wide range of applications in surveillance, human-computer interaction, augmented reality, video indexing, and retrieval. The varying pattern of spatio-temporal…
Inverse reinforcement learning (IRL) is a common technique for inferring human preferences from data. Standard IRL techniques tend to assume that the human demonstrator is stationary, that is that their policy $\pi$ doesn't change over…
Learning an egocentric action recognition model from video data is challenging due to distractors (e.g., irrelevant objects) in the background. Further integrating object information into an action model is hence beneficial. Existing…
Face Recognition systems are widely deployed in real-world applications, but they also raise privacy concerns due to unauthorized collection and misuse of facial data. Existing adversarial privacy protection methods rely on input-space…
The advanced RDH work focuses on both data encryption and image encryption which makes it more secure and free of errors. All previous methods embed data without encrypting the data which may subject to errors on the data extraction or…
Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos. However, less attention has been paid to recognition performance at…
Inverse rendering seeks to recover 3D geometry, surface material, and lighting from captured images, enabling advanced applications such as novel-view synthesis, relighting, and virtual object insertion. However, most existing techniques…
Single Image Super-Resolution (SISR) aims to recover a high-resolution image from a given low-resolution version of it. Video Super Resolution (VSR) targets series of given images, aiming to fuse them to create a higher resolution outcome.…
Given an image, we wish to produce an image of larger size with significantly more pixels and higher image quality. This is generally known as the Single Image Super-Resolution (SISR) problem. The idea is that with sufficient training data…
Most recent work on vision-based human activity recognition (HAR) focuses on designing complex deep learning models for the task. In so doing, there is a requirement for large datasets to be collected. As acquiring and processing large…
Many augmented reality (AR) applications rely on omnidirectional environment lighting to render photorealistic virtual objects. When the virtual objects consist of reflective materials, such as a metallic sphere, the required lighting…
This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It roots from the observation that visual systems of human beings can easily identify video incoherence based on…
Vision-based activity recognition is essential for security, monitoring and surveillance applications. Further, real-time analysis having low-quality video and contain less information about surrounding due to poor illumination, and…
When a very fast dynamic event is recorded with a low-framerate camera, the resulting video suffers from severe motion blur (due to exposure time) and motion aliasing (due to low sampling rate in time). True Temporal Super-Resolution (TSR)…