Related papers: Semantic Zooming and Edge Bundling for Multi-Scale…
Adapting large-scale Vision-Language Models (VLMs) like CLIP to downstream tasks often suffers from a "one-size-fits-all" architectural approach, where visual and textual tokens are processed uniformly by wide, generic adapters. We argue…
Online scene perception and topology reasoning are critical for autonomous vehicles to understand their driving environments, particularly for mapless driving systems that endeavor to reduce reliance on costly High-Definition (HD) maps.…
To bridge the gap between supervised semantic segmentation and real-world applications that acquires one model to recognize arbitrary new concepts, recent zero-shot segmentation attracts a lot of attention by exploring the relationships…
Many well-known, real-world problems involve dynamic data which describe the relationship among the entities. Hypergraphs are powerful combinatorial structures that are frequently used to model such data. For many of today's data-centric…
The low-level details and high-level semantics are both essential to the semantic segmentation task. However, to speed up the model inference, current approaches almost always sacrifice the low-level details, which leads to a considerable…
While nowadays deep neural networks achieve impressive performances on semantic segmentation tasks, they are usually trained by optimizing pixel-wise losses such as cross-entropy. As a result, the predictions outputted by such networks…
Network virtualization has caught the attention of many researchers in recent years. It facilitates the process of creating several virtual networks over a single physical network. Despite this advantage, however, network virtualization…
As smart grids increasingly depend on IoT devices and distributed energy management, they require decentralized, low latency orchestration of energy services. We address this with a unified framework for edge fog cloud infrastructures…
Real-world social networks and digital platforms are comprised of individuals (nodes) that are linked to other individuals or entities through multiple types of relationships (links). Sub-networks of such a network based on each type of…
In this work, we detail the design and structure of a Synopses Data Engine (SDE) which combines the virtues of parallel processing and stream summarization towards delivering interactive analytics at extreme scale. Our SDE is built on top…
Edge Computing is a new distributed Cloud Computing paradigm in which computing and storage capabilities are pushed to the topological edge of a network. However, various standards and implementations are promoted by different initiatives.…
Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image. Most existing methods use independent image-text encoding and apply complex hand-crafted modules or…
Reusable data/code and reproducible analyses are foundational to quality research. This aspect, however, is often overlooked when designing interactive stream analysis workflows for time-series data (e.g., eye-tracking data). A mechanism to…
Modern distributed applications increasingly rely on cloud-native platforms to abstract the complexity of deployment and scalability. As the de facto orchestration standard, Kubernetes enables this abstraction, but its declarative…
Enriching the robot representation of the operational environment is a challenging task that aims at bridging the gap between low-level sensor readings and high-level semantic understanding. Having a rich representation often requires…
Human drivers adeptly navigate complex scenarios by utilizing rich attentional semantics, but the current autonomous systems struggle to replicate this ability, as they often lose critical semantic information when converting 2D…
Network dynamics may be viewed as a process of change in the edge structure of a network, in the vertex set on which edges are defined, or in both simultaneously. Though early studies of such processes were primarily descriptive, recent…
Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emphasis on the high compression ratio of a single visual clue…
We study the question of how visual analysis can support the comparison of spatio-temporal ensemble data of liquid and gas flow in porous media. To this end, we focus on a case study, in which nine different research groups concurrently…
Edge computing has evolved to be a promising avenue to enhance the system computing capability by offloading processing tasks from the cloud to edge devices. In this paper, we propose a multi-layer edge computing framework called EdgeFlow.…