Related papers: Utility-Aware Load Shedding for Real-time Video An…
Edge detection serves as a critical foundation for numerous computer vision applications, including object detection, semantic segmentation, and image editing, by extracting essential structural cues that define object boundaries and…
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…
Today's distributed tracing frameworks are ill-equipped to troubleshoot rare edge-case requests. The crux of the problem is a trade-off between specificity and overhead. On the one hand, frameworks can indiscriminately select requests to…
Human Activity Recognition (HAR) using wearable and mobile sensors has gained momentum in last few years, in various fields, such as, healthcare, surveillance, education, entertainment. Nowadays, Edge Computing has emerged to reduce…
It is challenging for artificial intelligence systems to achieve accurate video recognition under the scenario of low computation costs. Adaptive inference based efficient video recognition methods typically preview videos and focus on…
Vision-language models (VLMs) have demonstrated impressive multimodal comprehension capabilities and are being deployed in an increasing number of online video understanding applications. While recent efforts extensively explore advancing…
Virtual reality (VR) is becoming prevalent with a plethora of applications in education, healthcare, entertainment, etc. To increase the user mobility, and to reduce the energy consumption and production cost of VR head mounted displays…
In this paper, we consider a task offloading problem in a multi-access edge computing (MEC) network, in which edge users can either use their local processing unit to compute their tasks or offload their tasks to a nearby edge server…
Edge camera-based systems are continuously expanding, facing ever-evolving environments that require regular model updates. In practice, complex teacher models are run on a central server to annotate data, which is then used to train…
Object tracking is an important functionality of edge video analytic systems and services. Multi-object tracking (MOT) detects the moving objects and tracks their locations frame by frame as real scenes are being captured into a video.…
Enterprises are increasingly deploying large camera networks for video analytics. Many target applications entail a common problem template: searching for and tracking an object or activity of interest (e.g. a speeding vehicle, a break-in)…
Edge applications generate a large influx of sensor data on massive scales, and these massive data streams must be processed shortly to derive actionable intelligence. However, traditional data processing systems are not well-suited for…
Short video streaming has become a dominant paradigm in digital media, characterized by rapid swiping interactions and diverse media content. A key technical challenge is designing an effective preloading strategy that dynamically selects…
The ubiquity of camera-embedded devices and the advances in deep learning have stimulated various intelligent mobile video applications. These applications often demand on-device processing of video streams to deliver real-time,…
Video streaming analytics is a crucial workload for vision-language model serving, but the high cost of multimodal inference limits scalability. Prior systems reduce inference cost by exploiting temporal and spatial redundancy in video…
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…
Motivated by the proliferation of Internet-of-Thing (IoT) devices and the rapid advances in the field of deep learning, there is a growing interest in pushing deep learning computations, conventionally handled by the cloud, to the edge of…
Multi-access edge computing (MEC) enables placing video content at the edge of the network aiming to improve the quality of experience (QoE) of the mobile clients. Video content caching at edge servers also reduces traffic in the backhaul…
A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially…
Deep Neural Network (DNN) trained object detectors are widely deployed in many mission-critical systems for real time video analytics at the edge, such as autonomous driving and video surveillance. A common performance requirement in these…