Related papers: Transforming Indoor Localization: Advanced Transfo…
Accurate camera localization is an essential part of tracking systems. However, localization results are greatly affected by illumination. Including data collected under various lighting conditions can improve the robustness of the…
Integrating Spiking Neural Networks (SNNs) with Transformer architectures offers a promising pathway to balance energy efficiency and performance, particularly for edge vision applications. However, existing Spiking Transformers face two…
Weakly supervised object localization is a challenging task which aims to localize objects with coarse annotations such as image categories. Existing deep network approaches are mainly based on class activation map, which focuses on…
Precise indoor localization is an increasingly demanding requirement for various emerging applications, like Virtual/Augmented reality and personalized advertising. Current indoor environments are equipped with pluralities of WiFi access…
Processing 3D data efficiently has always been a challenge. Spatial operations on large-scale point clouds, stored as sparse data, require extra cost. Attracted by the success of transformers, researchers are using multi-head attention for…
Driven by the continuous development of models such as Multi-Layer Perceptron, Convolutional Neural Network (CNN), and Transformer, deep learning has made breakthrough progress in fields such as computer vision and natural language…
Spiking Neural Networks (SNNs), particularly Spiking Transformers, offer energy-efficient processing of event-based sensor data for healthcare applications. Yet current architectures are rigid: they are trained and deployed as static…
Foundation models achieve state-of-the-art performance across different tasks, but their size and computational demands raise concerns about accessibility and sustainability. Existing efficiency methods often require additional retraining…
With the increasing demand for edge device powered location-based services in indoor environments, Wi-Fi received signal strength (RSS) fingerprinting has become popular, given the unavailability of GPS indoors. However, achieving robust…
Localization of wireless transmitters based on channel state information (CSI) fingerprinting finds widespread use in indoor as well as outdoor scenarios. Fingerprinting localization first builds a database containing CSI with measured…
Transformer models are powerful sequence-to-sequence architectures that are capable of directly mapping speech inputs to transcriptions or translations. However, the mechanism for modeling positions in this model was tailored for text…
Smartphones together with RSSI fingerprinting serve as an efficient approach for delivering a low-cost and high-accuracy indoor localization solution. However, a few critical challenges have prevented the wide-spread proliferation of this…
Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial…
While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…
Precise indoor localization is one of the key requirements for fifth Generation (5G) and beyond, concerning various wireless communication systems, whose applications span different vertical sectors. Although many highly accurate methods…
We propose an indoor localization algorithm for visible light systems by considering effects of non-line-of-sight (NLOS) propagation. The proposed algorithm, named database assisted nonlinear least squares (DA-NLS), utilizes ideas from both…
State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications. Low-bit deep neural network quantization techniques provides a powerful solution to dramatically…
Transformer-based approaches have been successfully used to obtain state-of-the-art accuracy on natural language processing (NLP) tasks with semi-structured tables. These model architectures are typically deep, resulting in slow training…
Versatile and adaptive semantic understanding would enable autonomous systems to comprehend and interact with their surroundings. Existing fixed-class models limit the adaptability of indoor mobile and assistive autonomous systems. In this…
Recently, infrared small target detection (IRSTD) has been dominated by deep-learning-based methods. However, these methods mainly focus on the design of complex model structures to extract discriminative features, leaving the loss…