Related papers: SSL-SLR: Self-Supervised Representation Learning f…

Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent…

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research. In this work, we explore unsupervised…

Sign language representation learning presents unique challenges due to the complex spatio-temporal nature of signs and the scarcity of labeled datasets. Existing methods often rely either on models pre-trained on general visual tasks, that…

This paper presents an in-depth analysis of various self-supervision methods for isolated sign language recognition (ISLR). We consider four recently introduced transformer-based approaches to self-supervised learning from videos, and four…

Contrastive learning with the nearest neighbor has proved to be one of the most efficient self-supervised learning (SSL) techniques by utilizing the similarity of multiple instances within the same class. However, its efficacy is…

Self-supervised learning (SSL)-based speech models are extensively used for full-stack speech processing. However, it has been observed that improving SSL-based speech representations using unlabeled speech for content-related tasks is…

Self-supervised learning (SSL) excels at finding general-purpose latent representations from complex data, yet lacks a unifying theoretical framework that explains the diverse existing methods and guides the design of new ones. We cast SSL…

Robotic systems that rely primarily on self-supervised learning have the potential to decrease the amount of human annotation and engineering effort required to learn control strategies. In the same way that prior robotic systems have…

The objective of this paper is to learn semantic representations for sleep stage classification from raw physiological time series. Although supervised methods have gained remarkable performance, they are limited in clinical situations due…

The recent surge in large language models has automated translations of spoken and written languages. However, these advances remain largely inaccessible to American Sign Language (ASL) users, whose language relies on complex visual cues.…

Designing learning-based no-reference (NR) video quality assessment (VQA) algorithms for camera-captured videos is cumbersome due to the requirement of a large number of human annotations of quality. In this work, we propose a…

The dominant paradigm for learning video-text representations -- noise contrastive learning -- increases the similarity of the representations of pairs of samples that are known to be related, such as text and video from the same sample,…

While contrastive learning is proven to be an effective training strategy in computer vision, Natural Language Processing (NLP) is only recently adopting it as a self-supervised alternative to Masked Language Modeling (MLM) for improving…

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

Learning visual representation of high quality is essential for image classification. Recently, a series of contrastive representation learning methods have achieved preeminent success. Particularly, SupCon outperformed the dominant methods…

This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It roots from the observation that visual systems of human beings can easily identify video incoherence based on…

Isolated Sign Language Recognition (ISLR) is crucial for scalable sign language technology, yet language-specific approaches limit current models. To address this, we propose a one-shot learning approach that generalises across languages…

Sign language recognition (SLR) has recently achieved a breakthrough in performance thanks to deep neural networks trained on large annotated sign datasets. Of the many different sign languages, these annotated datasets are only available…

Handwriting authentication is a valuable tool used in various fields, such as fraud prevention and cultural heritage protection. However, it remains a challenging task due to the complex features, severe damage, and lack of supervision. In…

Self-supervised learning (SSL) approaches, such as contrastive and generative methods, have advanced environmental sound representation learning using unlabeled data. However, how these approaches can complement each other within a unified…