Search Results

Convolutional neural network (CNN) currently has been widely used to undertake the task of image classification. Unfortunately, a trained CNN model is a nonlinear system with high complexity, and the implicit decision knowledge carried by the CNN model ...

Deep learning has achieved impressive results in nuclei segmentation, but the massive requirement for pixel-wise labels remains a significant challenge. To alleviate the annotation burden, existing methods generate pseudo masks for model training ...

This paper focuses on the covariance-based activity detection problem in a multi-cell massive multiple-input multiple-output (MIMO) system. In this system, active devices transmit their signature sequences to multiple base stations (BSs), and the BSs ...

Large vision-language models (VLMs) have achieved substantial progress in multimodal perception and reasoning. When integrated into an embodied agent, existing embodied VLM works either output detailed action sequences at the manipulation level or ...

The limited nonverbal cues and spatially distributed nature of remote communication make it challenging for unacquainted members to be expressive during social interactions over video conferencing. Though it enables seeing others' facial expressions, the ...

This study addresses the declining trend in the number of countries hosting the Olympics, exploring how to systematically evaluate the benefits of hosting and proposing innovative strategies to enhance sustainability and success. Using a TOPSIS model-...

This paper investigates the effect of low-resolution analog-to-digital converters (ADCs) on device activity detection in massive machine-type communications (mMTC). The low-resolution ADCs induce two challenges on the device activity detection compared ...

Text editing refers to the task of creating new sentences by altering existing text through methods such as replacing, inserting, or deleting. Two commonly used techniques for text editing are Seq2Seq and sequence labeling. The Seq2Seq method can ...

Deep Neural Networks (DNNs) have shown excellent image classification performance both in accuracy and efficiency. Therefore, it is of great value to deploy adversarial patch to protect critical facilities from DNNs-based scene classification in ...

Database management systems (DBMSs) are prone to logic bugs that can result in incorrect query results. Current debugging tools are limited to single table queries and struggle with issues like lack of ground-truth results and repetitive query space ...

In this poster, we propose a novel searchable encryption (SE) scheme that leverages access control encryption to enhance the security and flexibility of search operations. Our approach requires collaborative authority users to authorize data users ...

Dementia describes a syndrome of cognitive degeneration, and Behavioural and Psychological Symptoms of Dementia (BPSD) is the non-cognitive symptom. BPSD can be improved by care services. To aid better care service, we explore the potential of using ...

In this paper, we introduce Affective Umbrella, a novel system to record, analyze and visualize physiological data in real time via an umbrella handle. We implement a biofeedback loop design in the system that triggers visualization changes to reflect ...

Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples. Though visual imperceptibility is the desired property of adversarial ...

Consider the problem of simultaneous estimation of location and variance matrix under Huber's contaminated Gaussian model. First, we study minimum f-divergence estimation at the population level, corresponding to a generative adversarial method with a ...

Malicious code attacks have severely hindered the current development of the Internet technologies. Once the devices are infected with virus, the damages to companies and users are unpredictable. Although researchers have developed malware ...

In this paper we revisit feature fusion, an old-fashioned topic, in the new context of text-to-video retrieval. Different from previous research that considers feature fusion only at one end, let it be video or text, we aim for feature fusion for ...

Negation is a common linguistic skill that allows human to express what we do NOT want. Naturally, one might expect video retrieval to support natural-language queries with negation, e.g., finding shots of kids sitting on the floor and not playing with ...

The count of mitotic cells is a key feature in tumor diagnosis. However, due to the variability of mitotic cell morphology, detecting mitotic cells in tumor tissues is a highly challenging task. At the same time, the performance of the trained ...

ImageFlowing is a ‘living’ photograph that reproduces the biometric signs of the photographer. Viewers can feel how the photographer felt through photographer’s breathing, heartbeats and skin temperature. We extend a two-dimensional picture into a multi-...