Related papers: Cluster-Level Contrastive Learning for Emotion Rec…
Contrastive learning (CL) benefits the training of sequential recommendation models with informative self-supervision signals. Existing solutions apply general sequential data augmentation strategies to generate positive pairs and encourage…
Concept-oriented deep learning (CODL) is a general approach to meet the future challenges for deep learning: (1) learning with little or no external supervision, (2) coping with test examples that come from a different distribution than the…
EEG-based emotion recognition plays an important role in developing adaptive brain-computer communication systems, yet faces two fundamental challenges in practical implementations: (1) effective integration of non-stationary…
Background: Neural networks produce biased classification results due to correlation bias (they learn correlations between their inputs and outputs to classify samples, even when those correlations do not represent cause-and-effect…
Emotion Recognition in Conversation (ERC) is critical for enabling natural human-machine interactions. However, existing methods predominantly employ categorical or dimensional emotion annotations, which often fail to adequately represent…
Unsupervised Domain Adaptation (UDA), which aims to explore the transferrable features from a well-labeled source domain to a related unlabeled target domain, has been widely progressed. Nevertheless, as one of the mainstream, existing…
New intent discovery is a crucial capability for task-oriented dialogue systems. Existing methods focus on transferring in-domain (IND) prior knowledge to out-of-domain (OOD) data through pre-training and clustering stages. They either…
Human emotion recognition plays a crucial role in facilitating seamless interactions between humans and computers. In this paper, we present our innovative methodology for tackling the Valence-Arousal (VA) Estimation Challenge, the…
Contrastive learning has shown promising potential for learning robust representations by utilizing unlabeled data. However, constructing effective positive-negative pairs for contrastive learning on facial behavior datasets remains…
With the flourishing of social media platforms, vision-language pre-training (VLP) recently has received great attention and many remarkable progresses have been achieved. The success of VLP largely benefits from the information…
Emotional Support Conversation (ESC) is a typical dialogue that can effectively assist the user in mitigating emotional pressures. However, owing to the inherent subjectivity involved in analyzing emotions, current non-artificial…
Self-supervised learning has recently achieved great success in representation learning without human annotations. The dominant method -- that is contrastive learning, is generally based on instance discrimination tasks, i.e., individual…
The valence analysis of speakers' utterances or written posts helps to understand the activation and variations of the emotional state throughout the conversation. More recently, the concept of Emotion Carriers (EC) has been introduced to…
Context-aware methods have achieved remarkable advancements in supervised scene text recognition by leveraging semantic priors from words. Considering the heterogeneity of text and background in STR, we propose that such contextual priors…
Deep neural network-based classifiers trained with the categorical cross-entropy (CCE) loss are sensitive to label noise in the training data. One common type of method that can mitigate the impact of label noise can be viewed as supervised…
EEG signals are usually simple to obtain but expensive to label. Although supervised learning has been widely used in the field of EEG signal analysis, its generalization performance is limited by the amount of annotated data.…
Self-supervised learning (SSL) has recently achieved great success in mining the user-item interactions for collaborative filtering. As a major paradigm, contrastive learning (CL) based SSL helps address data sparsity in Web platforms by…
Most video-and-language representation learning approaches employ contrastive learning, e.g., CLIP, to project the video and text features into a common latent space according to the semantic similarities of text-video pairs. However, such…
Unsupervised visual representation learning has gained much attention from the computer vision community because of the recent achievement of contrastive learning. Most of the existing contrastive learning frameworks adopt the instance…
Generalized Category Discovery (GCD) aims to cluster unlabeled images into known and novel categories using labeled images from known classes. To address the challenge of transferring features from known to unknown classes while mitigating…