Related papers: Minimizing the Motion-to-Photon-delay (MPD) in Vir…
Distributed Virtual Reality systems enable globally dispersed users to interact with each other in a shared virtual environment. In such systems, different types of latencies occur. For a good VR experience, they need to be controlled. The…
In this paper, we introduce Attention Prompt Tuning (APT) - a computationally efficient variant of prompt tuning for video-based applications such as action recognition. Prompt tuning approaches involve injecting a set of learnable prompts…
Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an efficient temporal action detector (ETAD) that can train…
Modern applications such as voice recognition rely on the ability to compare signals to pre-recorded ones to classify them. However, this comparison typically needs to ignore differences due to signal noise, temporal offset, signal…
Advances in deep neural networks have considerably improved the art of animating a still image without operating in 3D domain. Whereas, prior arts can only animate small images (typically no larger than 512x512) due to memory limitations,…
A significant challenge for future virtual reality (VR) applications is to deliver high quality-of-experience, both in terms of video quality and responsiveness, over wireless networks with limited bandwidth. This paper proposes to address…
The ability to predict motion in real time is fundamental to many maneuvering activities in animals, particularly those critical for survival, such as attack and escape responses. Given its significance, it is no surprise that motion…
In this paper, a novel proactive computing and mmWave communication for ultra-reliable and low latency wireless virtual reality (VR is proposed. By leveraging information about users' poses, proactive computing and caching are used to…
Autonomous driving systems require real-time environmental perception to ensure user safety and experience. Streaming perception is a task of reporting the current state of the world, which is used to evaluate the delay and accuracy of…
Video depth estimation is essential for providing 3D scene structure in applications ranging from autonomous driving to mixed reality. Current end-to-end video depth models have established state-of-the-art performance. Although current…
In order to serve better VR experiences to users, existing predictive methods of Redirected Walking (RDW) exploit future information to reduce the number of reset occurrences. However, such methods often impose a precondition during…
In this proof of concept, we use Computer Vision (CV) methods to extract pose information out of exercise videos. We then employ a modified version of Dynamic Time Warping (DTW) to calculate the deviation from a gold standard execution of…
Local motion blur commonly occurs in real-world photography due to the mixing between moving objects and stationary backgrounds during exposure. Existing image deblurring methods predominantly focus on global deblurring, inadvertently…
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their…
Current virtual reality (VR) headsets encounter a trade-off between high processing power and affordability. Consequently, offloading 3D rendering to remote servers helps reduce costs, battery usage, and headset weight. Maintaining network…
Video comprises the vast majority of bits that are generated daily, and is the primary signal driving current innovations in robotics, remote sensing, and wearable technology. Yet, the most powerful video understanding models are too…
Visual object tracking is essential to intelligent robots. Most existing approaches have ignored the online latency that can cause severe performance degradation during real-world processing. Especially for unmanned aerial vehicles (UAVs),…
SGD and AdamW are the two most used optimizers for fine-tuning large neural networks in computer vision. When the two methods perform the same, SGD is preferable because it uses less memory (12 bytes/parameter with momentum and 8…
The immersive nature of the metaverse presents significant challenges for wireless multi-user interactive virtual reality (VR), such as ultra-low latency, high throughput and intensive computing, which place substantial demands on the…
Efficiency and robustness are the essential criteria for the visual-inertial odometry (VIO) system. To process massive visual data, the high cost on CPU resources and computation latency limits VIO's possibility in integration with other…