Related papers: SSLCL: An Efficient Model-Agnostic Supervised Cont…
Deep learning models perform best with abundant, high-quality labels, yet such conditions are rarely achievable in EEG-based emotion recognition. Electroencephalogram (EEG) signals are easily corrupted by artifacts and individual…
The lack of labeled data is a common challenge in speech classification tasks, particularly those requiring extensive subjective assessment, such as cognitive state classification. In this work, we propose a Semi-Supervised Learning (SSL)…
Recently, image-text matching has attracted more and more attention from academia and industry, which is fundamental to understanding the latent correspondence across visual and textual modalities. However, most existing methods implicitly…
Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to…
Emotion Recognition in Conversations (ERC) is hard because discriminative evidence is sparse, localized, and often asynchronous across modalities. We center ERC on emotion hotspots and present a unified model that detects per-utterance…
Recently, wearable emotion recognition based on peripheral physiological signals has drawn massive attention due to its less invasive nature and its applicability in real-life scenarios. However, how to effectively fuse multimodal data…
The advent of deep learning models has made a considerable contribution to the achievement of Emotion Recognition in Conversation (ERC). However, this task still remains an important challenge due to the plurality and subjectivity of human…
Self-supervised learning (SSL) has recently become the favorite among feature learning methodologies. It is therefore appealing for domain adaptation approaches to consider incorporating SSL. The intuition is to enforce instance-level…
This paper introduces a semi-supervised contrastive learning framework and its application to text-independent speaker verification. The proposed framework employs generalized contrastive loss (GCL). GCL unifies losses from two different…
Advancements in spoken language processing have driven the development of spoken language models (SLMs), designed to achieve universal audio understanding by jointly learning text and audio representations for a wide range of tasks.…
Emotion recognition models using audio input data can enable the development of interactive systems with applications in mental healthcare, marketing, gaming, and social media analysis. While the field of affective computing using audio…
Self-supervised Learning (SSL) has emerged as a powerful technique in pre-training deep learning models without relying on expensive annotated labels, instead leveraging embedded signals in unlabeled data. While SSL has shown remarkable…
Text representation learning is significant as the cornerstone of natural language processing. In recent years, graph contrastive learning (GCL) has been widely used in text representation learning due to its ability to represent and…
Self-supervised contrastive learning (CL) has achieved remarkable empirical success, often producing representations that rival supervised pre-training on downstream tasks. Recent theory explains this by showing that the CL loss closely…
Learning robust feature representation from large-scale noisy faces stands out as one of the key challenges in high-performance face recognition. Recent attempts have been made to cope with this challenge by alleviating the intra-class…
Speech Emotion Recognition (SER) is a challenging task due to limited data and blurred boundaries of certain emotions. In this paper, we present a comprehensive approach to improve the SER performance throughout the model lifecycle,…
Human-annotated vision datasets inevitably contain a fraction of human mislabelled examples. While the detrimental effects of such mislabelling on supervised learning are well-researched, their influence on Supervised Contrastive Learning…
Despite their effectiveness, current deep learning models face challenges with images coming from different domains with varying appearance and content. We introduce SegCLR, a versatile framework designed to segment images across different…
Electroencephalogram (EEG)-based emotion recognition is vital for affective computing but faces challenges in feature utilization and cross-domain generalization. This work introduces EmotionCLIP, which reformulates recognition as an…
Expression of emotions is a crucial part of daily human communication. Emotion recognition in conversations (ERC) is an emerging field of study, where the primary task is to identify the emotion behind each utterance in a conversation.…