Related papers: EdgeSync: Accelerating Edge-Model Updates for Data…
The real-time query of massive surveillance video data plays a fundamental role in various smart urban applications such as public safety and intelligent transportation. Traditional cloud-based approaches are not applicable because of high…
Training competitive deep video models is an order of magnitude slower than training their counterpart image models. Slow training causes long research cycles, which hinders progress in video understanding research. Following standard…
One of the most important factors that contribute to the success of a machine learning model is a good training objective. Training objective crucially influences the model's performance and generalization capabilities. This paper…
Affordable 3D scanners often produce sparse and non-uniform point clouds that negatively impact downstream applications in robotic systems. While existing point cloud upsampling architectures have demonstrated promising results on standard…
High definition (HD) map needs to be updated frequently to capture road changes, which is constrained by limited specialized collection vehicles. To maintain an up-to-date map, we explore crowdsourcing data from connected vehicles. Updating…
Deep learning models are increasingly deployed to edge devices for real-time applications. To ensure stable service quality across diverse edge environments, it is highly desirable to generate tailored model architectures for different…
Image diffusion models are trained on independently sampled static images. While this is the bedrock task protocol in generative modeling, capturing the temporal world through the lens of static snapshots is information-deficient by design.…
Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft models for every target model, which is costly and…
There is a growing need for low latency for many devices and users. The traditional cloud computing paradigm can not meet this requirement, legitimizing the need for a new paradigm. Edge computing proposes to move computing capacities to…
Single-object tracking (SOT) on edge devices is a critical computer vision task, requiring accurate and continuous target localization across video frames under occlusion, distractor interference, and fast motion. However, recent…
Video transmission applications (e.g., conferencing) are gaining momentum, especially in times of global health pandemic. Video signals are transmitted over lossy channels, resulting in low-quality received signals. To restore videos on…
In this work, we introduce Adapt & Align, a method for continual learning of neural networks by aligning latent representations in generative models. Neural Networks suffer from abrupt loss in performance when retrained with additional…
Video deraining is an important task in computer vision as the unwanted rain hampers the visibility of videos and deteriorates the robustness of most outdoor vision systems. Despite the significant success which has been achieved for video…
As a key technology of enabling Artificial Intelligence (AI) applications in 5G era, Deep Neural Networks (DNNs) have quickly attracted widespread attention. However, it is challenging to run computation-intensive DNN-based tasks on mobile…
The edge-cloud continuum has emerged as a transformative paradigm that meets the growing demand for low-latency, scalable, end-to-end service delivery by integrating decentralized edge resources with centralized cloud infrastructures.…
Video analytics pipelines have steadily shifted to edge deployments to reduce bandwidth overheads and privacy violations, but in doing so, face an ever-growing resource tension. Most notably, edge-box GPUs lack the memory needed to…
Mobile deep vision systems play a vital role in numerous scenarios. However, deep learning applications in mobile vision scenarios face problems such as tight computing resources. With the development of edge computing, the architecture of…
Recently developed deep neural models like NetGAN, CELL, and Variational Graph Autoencoders have made progress but face limitations in replicating key graph statistics on generating large graphs. Diffusion-based methods have emerged as…
We develop an edge-assisted object recognition system with the aim of studying the system-level trade-offs between end-to-end latency and object recognition accuracy. We focus on developing techniques that optimize the transmission delay of…
Diffusion-based image synthesis has attracted extensive attention recently. In particular, ControlNet that uses image-based prompts exhibits powerful capability in image tasks such as canny edge detection and generates images well aligned…