Related papers: PREFAB: PREFerence-based Affective Modeling for Lo…

High-quality labels are expensive to obtain for many machine learning tasks, such as medical image classification tasks. Therefore, probabilistic (weak) labels produced by weak supervision tools are used to seed a process in which…

When training data are collected from human annotators, the design of the annotation instrument, the instructions given to annotators, the characteristics of the annotators, and their interactions can impact training data. This study…

Preference-based reinforcement learning (RL) offers a promising approach for aligning policies with human intent but is often constrained by the high cost of human feedback. In this work, we introduce PrefVLM, a framework that integrates…

Aspect-based sentiment analysis (ABSA) in natural language processing enables organizations to understand customer opinions on specific product aspects. While deep learning models are widely used for English ABSA, their application in…

Aggregating multiple annotations into a single ground truth label may hide valuable insights into annotator disagreement, particularly in tasks where subjectivity plays a crucial role. In this work, we explore methods for identifying…

Tabular data is the foundation of the information age and has been extensively studied. Recent studies show that neural-based models are effective in learning contextual representation for tabular data. The learning of an effective…

When we can not assume a large amount of annotated data , active learning is a good strategy. It consists in learning a model on a small amount of annotated data (annotation budget) and in choosing the best set of points to annotate in…

Facial attractiveness prediction (FAP) aims to assess facial attractiveness automatically based on human aesthetic perception. Previous methods using deep convolutional neural networks have improved the performance, but their large-scale…

Facial emotion recognition has been typically cast as a single-label classification problem of one out of six prototypical emotions. However, that is an oversimplification that is unsuitable for representing the multifaceted spectrum of…

Pixel-wise annotations are notoriously labourious and costly to obtain in the medical domain. To mitigate this burden, weakly supervised approaches based on bounding box annotations-much easier to acquire-offer a practical alternative.…

Deep generative models have the capacity to render high fidelity images of content like human faces. Recently, there has been substantial progress in conditionally generating images with specific quantitative attributes, like the emotion…

The increasing accuracy of automatic chord estimation systems, the availability of vast amounts of heterogeneous reference annotations, and insights from annotator subjectivity research make chord label personalization increasingly…

Text sentiment analysis, also known as opinion mining, is research on the calculation of people's views, evaluations, attitude and emotions expressed by entities. Text sentiment analysis can be divided into text-level sentiment analysis,…

We present Affect2MM, a learning method for time-series emotion prediction for multimedia content. Our goal is to automatically capture the varying emotions depicted by characters in real-life human-centric situations and behaviors. We use…

Incorporating every annotator's perspective is crucial for unbiased data modeling. Annotator fatigue and changing opinions over time can distort dataset annotations. To combat this, we propose to learn a more accurate representation of…

We propose an annotation approach that captures not only labels but also the reading process underlying annotators' decisions, e.g., what parts of the text they focus on, re-read or skim. Using this framework, we conduct a case study on the…

Clinical notes in electronic health records contain highly heterogeneous writing styles, including non-standard terminology or abbreviations. Using these notes in predictive modeling has traditionally required preprocessing (e.g. taking…

From a computational viewpoint, emotions continue to be intriguingly hard to understand. In research, direct, real-time inspection in realistic settings is not possible. Discrete, indirect, post-hoc recordings are therefore the norm. As a…

With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws…

While training models and labeling data are resource-intensive, a wealth of pre-trained models and unlabeled data exists. To effectively utilize these resources, we present an approach to actively select pre-trained models while minimizing…