Related papers: C-SL: Contrastive Sound Localization with Inertial…
Current deep learning (DL) based approaches to speech intelligibility enhancement in noisy environments are generally trained to minimise the distance between clean and enhanced speech features. These often result in improved speech quality…
Underwater environments pose significant challenges for visual Simultaneous Localization and Mapping (SLAM) systems due to limited visibility, inadequate illumination, and sporadic loss of structural features in images. Addressing these…
This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…
The high cost of annotating data makes self-supervised approaches, such as contrastive learning methods, appealing for Human Activity Recognition (HAR). Effective contrastive learning relies on selecting informative positive and negative…
Visual sound localization is a typical and challenging problem that predicts the location of objects corresponding to the sound source in a video. Previous methods mainly used the audio-visual association between global audio and one-scale…
Recognizing underwater targets from acoustic signals is a challenging task owing to the intricate ocean environments and variable underwater channels. While deep learning-based systems have become the mainstream approach for underwater…
Contrastive learning has emerged as a powerful technique in audio-visual representation learning, leveraging the natural co-occurrence of audio and visual modalities in webscale video datasets. However, conventional contrastive audio-visual…
The Continuous Spontaneous Localisation (CSL) model is the most studied among collapse models, which describes the breakdown of the superposition principle for macroscopic systems. Here, we derive an upper bound on the parameters of the…
Despite recent success, most contrastive self-supervised learning methods are domain-specific, relying heavily on data augmentation techniques that require knowledge about a particular domain, such as image cropping and rotation. To…
Visual localization is a crucial component in the application of mobile robot and autonomous driving. Image retrieval is an efficient and effective technique in image-based localization methods. Due to the drastic variability of…
Conventional approaches to sound localization and separation are based on microphone arrays in artificial systems. Inspired by the selective perception of human auditory system, we design a multi-source listening system which can separate…
Contrastive learning constitutes an emerging branch of self-supervised learning that leverages large amounts of unlabeled data, by learning a latent space, where pairs of different views of the same sample are associated. In this paper, we…
Wireless localization has become a promising technology for offering intelligent location-based services. Although its localization accuracy is improved under specific scenarios, the short of environmental dynamic vulnerability still…
Existing Cross-Domain Few-Shot Learning (CDFSL) methods require access to source domain data to train a model in the pre-training phase. However, due to increasing concerns about data privacy and the desire to reduce data transmission and…
We introduce COLA, a self-supervised pre-training approach for learning a general-purpose representation of audio. Our approach is based on contrastive learning: it learns a representation which assigns high similarity to audio segments…
Correlation exploitation is essential for efficient multi-user channel estimation (MUCE) in massive MIMO systems. However, the existing works either rely on presumed strong correlation or learn the correlation through large amount of…
Sound source localization (SSL) demonstrates remarkable results in controlled settings but struggles in real-world deployment due to dual imbalance challenges: intra-task imbalance arising from long-tailed direction-of-arrival (DoA)…
Electroencephalography-to-Text generation (EEG-to-Text), which aims to directly generate natural text from EEG signals has drawn increasing attention in recent years due to the enormous potential for Brain-computer interfaces (BCIs).…
Auscultation is crucial for diagnosing lung diseases. The COVID-19 pandemic has revealed the limitations of traditional, in-person lung sound assessments. To overcome these issues, advancements in digital stethoscopes and artificial…
Self-supervised contrastive learning (CL) has achieved state-of-the-art performance in representation learning by minimizing the distance between positive pairs while maximizing that of negative ones. Recently, it has been verified that the…