Related papers: Counterfactual Reasoning for Out-of-distribution M…

Despite commendable achievements made by existing work, prevailing multimodal sarcasm detection studies rely more on textual content over visual information. It unavoidably induces spurious correlations between textual words and labels,…

Target-oriented multimodal sentiment classification seeks to predict sentiment polarity for specific targets from image-text pairs. While existing works achieve competitive performance, they often over-rely on textual content and fail to…

With the rapid development of multimedia, the shift from unimodal textual sentiment analysis to multimodal image-text sentiment analysis has obtained academic and industrial attention in recent years. However, multimodal sentiment analysis…

Multimodal sentiment analysis is an important area for understanding the user's internal states. Deep learning methods were effective, but the problem of poor interpretability has gradually gained attention. Previous works have attempted to…

Out-of-distribution (OOD) generalisation aims to build a model that can generalise well on an unseen target domain using knowledge from multiple source domains. To this end, the model should seek the causal dependence between inputs and…

Out-of-distribution (OOD) generalization remains a fundamental challenge in real-world classification, where test distributions often differ substantially from training data. Most existing approaches pursue domain-invariant representations,…

Multimodal sentiment analysis aims to identify the emotions expressed by individuals through visual, language, and acoustic cues. However, most existing research assume that all modalities are available during both training and testing,…

While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work has explored using…

Multimodal Sentiment Analysis (MSA) aims to understand human intentions by integrating emotion-related clues from diverse modalities, such as visual, language, and audio. Unfortunately, the current MSA task invariably suffers from unplanned…

Multimodal intent understanding is a significant research area that requires effective leveraging of multiple modalities to analyze human language. Existing methods face two main challenges in this domain. Firstly, they have limitations in…

Two fundamental requirements for the deployment of machine learning models in safety-critical systems are to be able to detect out-of-distribution (OOD) data correctly and to be able to explain the prediction of the model. Although…

For text classification tasks, finetuned language models perform remarkably well. Yet, they tend to rely on spurious patterns in training data, thus limiting their performance on out-of-distribution (OOD) test data. Among recent models…

Counterfactually-Augmented Data (CAD) has the potential to improve language models' Out-Of-Distribution (OOD) generalization capability, as CAD induces language models to exploit causal features and exclude spurious correlations. However,…

We propose a novel approach to multimodal sentiment analysis using deep neural networks combining visual analysis and natural language processing. Our goal is different than the standard sentiment analysis goal of predicting whether a…

Counterfactually-Augmented Data (CAD) -- minimal editing of sentences to flip the corresponding labels -- has the potential to improve the Out-Of-Distribution (OOD) generalization capability of language models, as CAD induces language…

The brittleness of finetuned language model performance on out-of-distribution (OOD) test samples in unseen domains has been well-studied for English, yet is unexplored for multi-lingual models. Therefore, we study generalization to OOD…

Predicting counterfactual distributions in complex dynamical systems is essential for scientific modeling and decision-making in domains such as public health and medicine. However, existing methods often rely on point estimates or purely…

Multimodal video sentiment analysis aims to integrate multiple modal information to analyze the opinions and attitudes of speakers. Most previous work focuses on exploring the semantic interactions of intra- and inter-modality. However,…

In real-world applications, it is important and desirable to learn a model that performs well on out-of-distribution (OOD) data. Recently, causality has become a powerful tool to tackle the OOD generalization problem, with the idea resting…

The complex and dynamic real-world clinical environment demands reliable deep learning (DL) systems. Out-of-distribution (OOD) detection plays a critical role in enhancing the reliability and generalizability of DL models when encountering…