Search Results

Given the wide adoption of multimodal sensors (e.g., camera, lidar, radar) by <italic>autonomous vehicle</italic>s (AVs), deep analytics to fuse their outputs for a robust perception become imperative. However, existing fusion methods often make two ...

New Wi-Fi systems have leveraged beamforming to manage a significant portion of traffic for achieving high throughput and reliability. Unfortunately, this has amplified certain security risks since beamforming critically relies on the clear-text ...

In Video-based Facial Expression Recognition (V-FER), models are typically trained on closed-set datasets with a fixed number of known classes. However, these models struggle with unknown classes common in real-world scenarios. In this paper, we ...

Accurate segmentation of polyps is crucial for efficient colorectal cancer detection during the colonoscopy screenings. State Space Models, exemplified by Mamba, have recently emerged as a promising approach, excelling in long-range interaction ...

The contact-free sensing nature of Wi-Fi has been leveraged to achieve privacy breaches such as <italic>keystroke inference</italic> (KI). However, the use of <italic>channel state information</italic> (CSI) in existing attacks is highly questionable due ...

We present the All-Seeing Project V2: a new model and dataset designed for understanding object relations in images. Specifically, we propose the All-Seeing Model V2 (ASMv2) that integrates the formulation of text generation, object localization, ...

Few-shot object detection (FSOD) studies how to detect novel objects with few annotated examples effectively. Recently, it has been demonstrated that decent feature embeddings, including the general feature embeddings that are more invariant to ...

Low-orbit mega-constellation network, which utilize thousands of satellites to provide a variety of network services and collect a wide range of space information, is a rapidly growing field. Each satellite collects TB-level data daily, including ...

In the swift evolution of 5G cellular communication technology and Internet of Things (IoT), the consumer electronics market is booming. Consumer IoT has become an emerging industry. However, the development of the consumer IoT is subject to limited ...

ship-radiated noise classification has long been a challenge in hydroacoustic engineering. Deep learning techniques, the mainstream solution to this challenge now, often fail to provide accurate classification results for practical applications because ...

This paper introduces a new immersed boundary (IB) method for viscous incompressible flow, based on a Fourier spectral method for the fluid solver and on the nonuniform fast Fourier transform (NUFFT) algorithm for coupling the fluid with the ...

• The FSIB method is gridless and has exact translation invariance.
• A divergence-free interpolated velocity field that conserves volume.
• Equivalent to the use of a new ‘sinc’ kernel in the framework of IB method.
• Improved ...

Rust is an emergent systems programming language highlighting memory safety through its Ownership and Borrowing System (OBS). Formalizing OBS in semantics is essential in certifying Rust’s memory safety guarantees. Existing formalizations of OBS ...$\mathbb{}$$\mathbb{}$

Given the popularity of interactive artificial intelligence models like ChatGPT, public perceptions of emerging Artificial Intelligence Generated Content (AIGC) have sparked widespread discussion. Companies and research institutions worldwide have ...

Deep neural networks (DNNs) are vulnerable to adversarial examples (AEs), which are well-designed input samples with imperceptible perturbations. Existing methods generate AEs to evaluate the robustness of DNN-based natural language processing ...

The implicit-association test (IAT) is a method for measuring subconscious associations between concepts in memory. It is widely used in social psychology research for assessing associations that people may be unable or unwilling to articulate, including ...

The limited bandwidth of Wi-Fi severely confines the granularity (especially in differentiating multiple subjects) of Wi-Fi sensing, posing a significant challenge for its wide adoption. Though utilizing multiple channels to expand the effective ...

In applications of Multi-Agent Path Finding (MAPF), it is often the sum of planning and execution times that needs to be minimised (i.e., the Goal Achievement Time). Yet current methods seldom optimise for this objective. Optimal algorithms reduce ...

One area of research in multi-agent path finding is to determine how replanning can be efficiently achieved in the case of agents being delayed during execution. One option is to reschedule the passing order of agents, i.e., the sequence in which agents ...

With the rapid development of artificial intelligence, image processing technology has been more and more widely used. Image enhancement is an important part of image processing, and has become a research hotspot of theory and application of ...

Personalization improves user experience by tailoring interactions relevant to each user’s background and preferences. However, personalization requires information about users that platforms often collect without their awareness or their enthusiastic ...