Related papers: CoMuTe: A Convolutional Neural Network Based Devic…

Convolutional neural networks (CNNs) have shown great performance as general feature representations for object recognition applications. However, for multi-label images that contain multiple objects from different categories, scales and…

Cross-Domain Few-shot Semantic Segmentation (CD-FSS) aims to train generalized models that can segment classes from different domains with a few labeled images. Previous works have proven the effectiveness of feature transformation in…

For signal processing related to localization technologies, non line of sight (NLOS) multipaths have a significant impact on the localization error level. This study proposes a localization correction method based on convolution neural…

Multi-source stationary computed tomography (MSS-CT) offers significant advantages in medical and industrial applications due to its gantry-less scan architecture and/or capability of simultaneous multi-source emission. However, the lack of…

We introduce FedDCT, a novel distributed learning paradigm that enables the usage of large, high-performance CNNs on resource-limited edge devices. As opposed to traditional FL approaches, which require each client to train the full-size…

Multi-label image classification is a critical task in machine learning that aims to accurately assign multiple labels to a single image. While existing methods often utilize attention mechanisms or graph convolutional networks to model…

We consider the problem of integrating non-imaging information into segmentation networks to improve performance. Conditioning layers such as FiLM provide the means to selectively amplify or suppress the contribution of different feature…

Object classification is one of the many holy grails in computer vision and as such has resulted in a very large number of algorithms being proposed already. Specifically in recent years there has been considerable progress in this area…

Convolution neural networks (CNNs) and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this…

Detecting and classifying targets in video streams from surveillance cameras is a cumbersome, error-prone and expensive task. Often, the incurred costs are prohibitive for real-time monitoring. This leads to data being stored locally or…

Indoor localization is a fundamental problem in location-based applications. Current approaches to this problem typically rely on Radio Frequency technology, which requires not only supporting infrastructures but human efforts to measure…

In this paper, a multi-modal data based semi-supervised learning (SSL) framework that jointly use channel state information (CSI) data and RGB images for vehicle positioning is designed. In particular, an outdoor positioning system where…

Top-performing computer vision models are powered by convolutional neural networks (CNNs). Training an accurate CNN highly depends on both the raw sensor data and their associated ground truth (GT). Collecting such GT is usually done…

Appropriate allocation of system resources is essential for meeting the increased user-traffic demands in the next generation wireless technologies. Traditionally, the system relies on channel state information (CSI) of the users for…

Device-free localization (DFL) is an emerging technology for estimating the position of a human or object that is not equipped with any electronic tag, nor participate actively in the localization process. Similar to device-based…

In certain emerging applications such as health monitoring wearable and traffic monitoring systems, Internet-of-Things (IoT) devices generate or collect a huge amount of multi-label datasets. Within these datasets, each instance is linked…

Device-free (DF) localization is an emerging technology that allows the detection and tracking of entities that do not carry any devices nor participate actively in the localization process. Typically, DF systems require a large number of…

This paper proposes a novel framework for multi-label image recognition without any training data, called data-free framework, which uses knowledge of pre-trained Large Language Model (LLM) to learn prompts to adapt pretrained…

We introduce WiCluster, a new machine learning (ML) approach for passive indoor positioning using radio frequency (RF) channel state information (CSI). WiCluster can predict both a zone-level position and a precise 2D or 3D position,…

This paper presents a Convolutional Neural Network (CNN) approach for counting and locating objects in high-density imagery. To the best of our knowledge, this is the first object counting and locating method based on a feature map…