This makes them overlook the many possible interactions across the input modalities and deems them unsafe for high-risk tasks requiring reliable uncertainty estimation.

Specifically, we observe that CLIP's visual encoder tends to

As posts on social media increase rapidly, analyzing the sentiments embedded in image-text pairs has become a popular research topic in recent years. Although existing works achieve impressive accomplishments in simultaneously harnessing image and text information, they lack the considerations of possible low-quality and missing modalities. In real-world applications, these issues might frequently occur, leading to urgent needs for models capable of predicting sentiment robustly. Therefore, we propose a Distribution-based feature Recovery and Fusion (DRF) method for robust multimodal sentiment analysis of image-text pairs. Specifically, we maintain a feature queue for each modality to approximate their feature distributions, through which we can simultaneously handle low-quality and missing modalities in a unified framework. For low-quality modalities, we reduce their contributions to the fusion by quantitatively estimating modality qualities based on the distributions. For missing modalities, we build inter-modal mapping relationships supervised by samples and distributions, thereby recovering the missing modalities from available ones. In experiments, two disruption strategies that corrupt and discard some modalities in samples are adopted to mimic the low-quality and missing modalities in various real-world scenarios. Through comprehensive experiments on three publicly available image-text datasets, we demonstrate the universal improvements of DRF compared to SOTA methods under both two strategies, validating its effectiveness in robust multimodal sentiment analysis.

Abstract--Prevalent empathy prediction techniques primarily concentrate on a singular modality, typically textual, thus neglecting multi-modal processing capabilities. They also overlook the utilization of certain privileged information, which may encompass additional empathetic content. In response, we introduce an advanced multi-modal empathy prediction method integrating video, audio, and text information. The method comprises the Multi-Modal Empathy Prediction and Supervisory Documentation Assisted Training. We use pre-trained networks in the empathy prediction network to extract features from various modalities, followed by a cross-modal fusion. This process yields a multi-modal feature representation, which is employed to predict empathy labels. T o enhance the extraction of text features, we incorporate supervisory documents as privileged information during the assisted training phase. Specifically, we apply the Latent Dirichlet Allocation model to identify potential topic distributions to constrain text features. These supervisory documents, created by supervisors, focus on the counseling topics and the counselor's display of empathy. Notably, this privileged information is only available during training and is not accessible during the prediction phase. Experimental results on the multi-modal and dialogue empathy datasets demonstrate that our approach is superior to the existing methods. MP A THY is characterized by an emotional response that arises from the interplay between inherent traits and situational factors. This empathetic response is spontaneously triggered, yet it is also sculpted by deliberate cognitive control.

In the contemporary digital landscape, multi-modal media manipulation has emerged as a significant societal threat, impacting the reliability and integrity of information dissemination. Current detection methodologies in this domain often overlook the crucial aspect of localized information, despite the fact that manipulations frequently occur in specific areas, particularly in facial regions. In response to this critical observation, we propose the M4-BLIP framework. This innovative framework utilizes the BLIP-2 model, renowned for its ability to extract local features, as the cornerstone for feature extraction. Complementing this, we incorporate local facial information as prior knowledge. A specially designed alignment and fusion module within M4-BLIP meticulously integrates these local and global features, creating a harmonious blend that enhances detection accuracy. Furthermore, our approach seamlessly integrates with Large Language Models (LLM), significantly improving the interpretability of the detection outcomes. Extensive quantitative and visualization experiments validate the effectiveness of our framework against the state-of-the-art competitors.

Climate change demands effective legislative action to mitigate its impacts. This study explores the application of machine learning (ML) to understand the progression of climate policy from announcement to adoption, focusing on policies within the European Green Deal. We present a dataset of 165 policies, incorporating text and metadata. We aim to predict a policy's progression status, and compare text representation methods, including TF-IDF, BERT, and ClimateBERT. Metadata features are included to evaluate the impact on predictive performance. On text features alone, ClimateBERT outperforms other approaches (RMSE = 0.17, R^2 = 0.29), while BERT achieves superior performance with the addition of metadata features (RMSE = 0.16, R^2 = 0.38). Using methods from explainable AI highlights the influence of factors such as policy wording and metadata including political party and country representation. These findings underscore the potential of ML tools in supporting climate policy analysis and decision-making.

Test-time adaptation paradigm provides flexibility towards domain shifts by performing immediate adaptation on unlabeled target data from the source model. Vision-Language Models (VLMs) leverage their generalization capabilities for diverse downstream tasks, and test-time prompt tuning has emerged as a prominent solution for adapting VLMs. In this work, we explore contrastive VLMs and identify the modality gap caused by a single dominant feature dimension across modalities. We observe that the dominant dimensions in both text and image modalities exhibit high predictive sensitivity, and that constraining their influence can improve calibration error. Building on this insight, we propose dimensional entropy maximization that regularizes the distribution of textual features toward uniformity to mitigate the dependency of dominant dimensions. Our method alleviates the degradation of calibration performance in test-time prompt tuning, offering a simple yet effective solution to enhance the reliability of VLMs in real-world deployment scenarios.

Deep learning relies heavily on data augmentation to mitigate limited data, especially in medical imaging. Recent multimodal learning integrates text and images for segmentation, known as referring or text-guided image segmentation. However, common augmentations like rotation and flipping disrupt spatial alignment between image and text, weakening performance. To address this, we propose an early fusion framework that combines text and visual features before augmentation, preserving spatial consistency. We also design a lightweight generator that projects text embeddings into visual space, bridging semantic gaps. Visualization of generated pseudo-images shows accurate region localization. Our method is evaluated on three medical imaging tasks and four segmentation frameworks, achieving state-of-the-art results. Code is publicly available on GitHub: https://github.com/11yxk/MedSeg_EarlyFusion.

Specifically, we observe that CLIP's visual encoder tends to