相关论文: EdgeMA: Model Adaptation System for Real-Time Vide…

Transformer-based models for anomaly detection in multivariate time series can benefit from the self-attention mechanism due to its advantage in modeling long-term dependencies. However, Transformer-based anomaly detection models have…

Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition…

The 6G vision is envisaged to enable agile network expansion and rapid deployment of new on-demand microservices (e.g., visibility services for data traffic management, mobile edge computing services) closer to the network's edge IoT…

Edge learning facilitates ubiquitous intelligence by enabling model training and adaptation directly on data-generating devices, thereby mitigating privacy risks and communication latency. However, the high computational and energy overhead…

Anomalous diffusion occurs in a wide range of systems, including protein transport within cells, animal movement in complex habitats, pollutant dispersion in groundwater, and nanoparticle motion in synthetic materials. Accurately estimating…

Lots of neural network architectures have been proposed to deal with learning tasks on graph-structured data. However, most of these models concentrate on only node features during the learning process. The edge features, which usually play…

Video frame interpolation can up-convert the frame rate and enhance the video quality. In recent years, although the interpolation performance has achieved great success, image blur usually occurs at the object boundaries owing to the large…

Edge Machine Learning (Edge ML), which shifts computational intelligence from cloud-based systems to edge devices, is attracting significant interest due to its evident benefits including reduced latency, enhanced data privacy, and…

We introduce an efficient video segmentation system for resource-limited edge devices leveraging heterogeneous compute. Specifically, we design network models by searching across multiple dimensions of specifications for the neural…

Event-based vision represents a paradigm shift in how vision information is captured and processed. By only responding to dynamic intensity changes in the scene, event-based sensing produces far less data than conventional frame-based…

Structural shifts pose a significant challenge for graph neural networks, as graph topology acts as a covariate that can vary across domains. Existing domain generalization methods rely on fixed structural augmentations or training on…

Real-time video analytics typically require video frames to be processed by a query to identify objects or activities of interest while adhering to an end-to-end frame processing latency constraint. Such applications impose a continuous and…

Efficient anomaly detection and diagnosis in multivariate time-series data is of great importance for modern industrial applications. However, building a system that is able to quickly and accurately pinpoint anomalous observations is a…

Subgraph matching is to find all subgraphs in a data graph that are isomorphic to an existing query graph. Subgraph matching is an NP-hard problem, yet has found its applications in many areas. Many learning-based methods have been proposed…

Processing visual data on mobile devices has many applications, e.g., emergency response and tracking. State-of-the-art computer vision techniques rely on large Deep Neural Networks (DNNs) that are usually too power-hungry to be deployed on…

Conventionally, DNN models are trained once in the cloud and deployed in edge devices such as cars, robots, or unmanned aerial vehicles (UAVs) for real-time inference. However, there are many cases that require the models to adapt to new…

Today's intelligent applications can achieve high performance accuracy using machine learning (ML) techniques, such as deep neural networks (DNNs). Traditionally, in a remote DNN inference problem, an edge device transmits raw data to a…

Unsupervised Graph Domain Adaptation (UGDA) seeks to bridge distribution shifts between domains by transferring knowledge from labeled source graphs to given unlabeled target graphs. Existing UGDA methods primarily focus on aligning…

Edge intelligent applications like VR/AR and language model based chatbots have become widespread with the rapid expansion of IoT and mobile devices. However, constrained edge devices often cannot serve the increasingly large and complex…

Streaming Data-Driven Optimization (SDDO) problems arise in many applications where data arrive continuously and the optimization environment evolves over time. Concept drift produces non-stationary landscapes, making optimization methods…