Related papers: Iterative Distillation for Better Uncertainty Esti…

Multimodal sentiment analysis, a pivotal task in affective computing, seeks to understand human emotions by integrating cues from language, audio, and visual signals. While many recent approaches leverage complex attention mechanisms and…

Knowledge distillation (KD) is a widely adopted and effective method for compressing models in object detection tasks. Particularly, feature-based distillation methods have shown remarkable performance. Existing approaches often ignore the…

Owing to its rapid progress and broad application prospects, few-shot action recognition has attracted considerable interest. However, current methods are predominantly based on limited single-modal data, which does not fully exploit the…

Speech emotion recognition plays an important role in various applications. However, most existing approaches predict a single emotion label, oversimplifying the inherently ambiguous nature of human emotional expression. Recent large…

Knowledge distillation is a powerful method for model compression, enabling the efficient deployment of complex deep learning models (teachers), including large language models. However, its underlying statistical mechanisms remain unclear,…

A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e. the tendency of neural networks to fail to preserve the knowledge acquired from old tasks when learning new tasks. This problem has been widely…

Emotion recognition (ER) is an important task in Natural Language Processing (NLP), due to its high impact in real-world applications from health and well-being to author profiling, consumer analysis and security. Current approaches to ER,…

The most prominent subtask in emotion analysis is emotion classification; to assign a category to a textual unit, for instance a social media post. Many research questions from the social sciences do, however, not only require the detection…

Speech emotion recognition (SER), particularly for naturally expressed emotions, remains a challenging computational task. Key challenges include the inherent subjectivity in emotion annotation and the imbalanced distribution of emotion…

In this study, we explore in depth a few under-studied topics at the intersection of uncertainty estimation and segmentation. Prior work has shown that the quality of uncertainty estimates can be very sensitive to a range of variables. As…

Fine-grained sentiment analysis attempts to extract sentiment holders, targets and polar expressions and resolve the relationship between them, but progress has been hampered by the difficulty of annotation. Targeted sentiment analysis, on…

Human emotions can be inferred from facial expressions. However, the annotations of facial expressions are often highly noisy in common emotion coding models, including categorical and dimensional ones. To reduce human labelling effort on…

Distilled self-supervised models have shown competitive performance and efficiency in recent years. However, there is a lack of experience in jointly distilling multiple self-supervised speech models. In our work, we performed Ensemble…

Although neural networks are well suited for sequential transfer learning tasks, the catastrophic forgetting problem hinders proper integration of prior knowledge. In this work, we propose a solution to this problem by using a multi-task…

Besides spoken words, speech signals also carry information about speaker gender, age, and emotional state which can be used in a variety of speech analysis applications. In this paper, a divide and conquer strategy for ensemble…

Voice interfaces integral to the human-computer interaction systems can benefit from speech emotion recognition (SER) to customize responses based on user emotions. Since humans convey emotions through multi-modal audio-visual cues,…

Previous research on EMA data of mental disorders was mainly focused on multivariate regression-based approaches modeling each individual separately. This paper goes a step further towards exploring the use of non-linear interpretable…

Knowledge distillation is an effective approach to learn compact models (students) with the supervision of large and strong models (teachers). As empirically there exists a strong correlation between the performance of teacher and student…

Selecting an effective training signal for machine learning tasks is difficult: expert annotations are expensive, and crowd-sourced annotations may not be reliable. Recent work has demonstrated that learning from a distribution over labels…

Fluorescence microscopy images contain several channels, each indicating a marker staining the sample. Since many different marker combinations are utilized in practice, it has been challenging to apply deep learning based segmentation…