Related papers: Prototype VOEvent Network Systems based on VTP and…
Multimedia data is highly expressive and has traditionally been very difficult for a machine to interpret. Middleware systems such as complex event processing (CEP) mine patterns from data streams and send notifications to users in a timely…
Audio-visual event localization aims to localize an event that is both audible and visible in the wild, which is a widespread audio-visual scene analysis task for unconstrained videos. To address this task, we propose a Multimodal Parallel…
Large Language Model (LLM)-based Vision-Language Models (VLMs) have substantially extended the boundaries of visual understanding capabilities. However, their high computational demands hinder deployment on resource-constrained edge…
The Space-based multi-band astronomical Variable Objects Monitor (SVOM) mission was launched in June 2024. It is a joint Sino-French collaboration designed to detect, localize, and study gammaray bursts (GRBs) and other high-energy…
Turn-taking management is crucial for any social interaction. Still, it is challenging to model human-machine interaction due to the complexity of the social context and its multimodal nature. Unlike conventional systems based on silence…
Just as the astronomical "Time Domain" is a catch-phrase for a diverse group of different science objectives involving time-varying phenomena in all astrophysical regimes from the solar system to cosmological scales, so the "Virtual…
Networked control systems enable real-time control and coordination of distributed systems, leveraging the low latency, high reliability, and massive connectivity offered by 5G and future 6G networks. Applications include autonomous…
Deploying high-performance vision transformer (ViT) models on ubiquitous Internet of Things (IoT) devices to provide high-quality vision services will revolutionize the way we live, work, and interact with the world. Due to the…
This paper proposed a fully-simulated environment by integrating an on-sensor visual computing device, SCAMP, and CoppeliaSim robot simulator via interface and remote API. Within this platform, a mobile robot obstacle avoidance and target…
Crowd-sourced video distribution is frequently of interest in the local vicinity. In this paper, we propose a novel design to transfer such content over opportunistic networks with adaptive quality encoding to achieve reasonable delay…
This volume contains the papers presented at the 23rd International Overture Workshop, held on the 11th of June 2025. This event was the latest in a series of workshops around the Vienna Development Method (VDM), the open-source project…
The Stream Control Transmission Protocol (SCTP) is a connection and message oriented transport protocol. It supports multiple uni-directional streams in each direction allowing user message sequence preservation within each stream. This…
Vehicle-to-everything (V2X) technologies offer a promising paradigm to mitigate the limitations of constrained observability in single-vehicle systems. Prior work primarily focuses on single-frame cooperative perception, which fuses agents'…
Multimodal large language models suffer from severe computational and memory bottlenecks, as the number of visual tokens far exceeds that of textual tokens. While recent methods employ projector modules to align and compress visual tokens…
We introduce a general range of science drivers for using the Virtual Observatory (VO) and identify some common aspects to these as well as the advantages of VO data access. We then illustrate the use of existing VO tools to tackle multi…
In 2024, the outbreak of Human Metapneumovirus (HMPV) in China, which later spread to the UK and other countries, raised significant public concern. While HMPV typically causes mild symptoms, its effects on vulnerable individuals prompted…
A cost effective, gesture based modelling technique called Virtual Interactive Prototyping (VIP) is described in this paper. Prototyping is implemented by projecting a virtual model of the equipment to be prototyped. Users can interact with…
We present VoXtream, a fully autoregressive, zero-shot streaming text-to-speech (TTS) system for real-time use that begins speaking from the first word. VoXtream directly maps incoming phonemes to audio tokens using a monotonic alignment…
Wireless sensor networks (WSNs) are promising solutions for large infrastructure monitoring because of their ease of installation, computing and communication capability, and cost-effectiveness. Long-term structural health monitoring (SHM),…
Vision-Language Pre-training (VLP) models have shown remarkable performance on various downstream tasks. Their success heavily relies on the scale of pre-trained cross-modal datasets. However, the lack of large-scale datasets and benchmarks…