Related papers: Uncertainty-Resilient Multimodal Learning via Cons…

Due to the ever-growing diversity of the data source, multi-modality feature learning has attracted more and more attention. However, most of these methods are designed by jointly learning feature representation from multi-modalities that…

Multimodal representation learning is fundamentally about transforming incomparable modalities into comparable representations. While prior research primarily focused on explicitly aligning these representations through targeted learning…

Today, the acquisition of various behavioral log data has enabled deeper understanding of customer preferences and future behaviors in the marketing field. In particular, multimodal deep learning has achieved highly accurate predictions by…

Weak-strong consistency learning strategies are widely employed in semi-supervised medical image segmentation to train models by leveraging limited labeled data and enforcing weak-to-strong consistency. However, existing methods primarily…

Multimodal recommendation aims to integrate collaborative signals with heterogeneous content such as visual and textual information, but remains challenged by modality-specific noise, semantic inconsistency, and unstable propagation over…

Multimodal recommendation has emerged as an effective paradigm for enhancing collaborative filtering by incorporating heterogeneous content modalities. Existing multimodal recommenders predominantly focus on reinforcing cross-modal…

Deep learning methods for unsupervised registration often rely on objectives that assume a uniform noise level across the spatial domain (e.g. mean-squared error loss), but noise distributions are often heteroscedastic and input-dependent…

Sequential recommender systems explore users' preferences and behavioral patterns from their historically generated data. Recently, researchers aim to improve sequential recommendation by utilizing massive user-generated multi-modal…

Converting different modalities into generalized text, which then serves as input prompts for large language models (LLMs), is a common approach for aligning multimodal models, particularly when pairwise data is limited. Text-centric…

Data-driven learning is generalized to consider history-dependent multi-fidelity data, while quantifying epistemic uncertainty and disentangling it from data noise (aleatoric uncertainty). This generalization is hierarchical and adapts to…

Accurate beam prediction is essential for mitigating signalling overhead and latency in integrated sensing and communication-enabled massive multi-input multi-output systems. With the aid of multimodal learning, the prediction accuracy can…

Multi-modal fusion is proven to be an effective method to improve the accuracy and robustness of speaker tracking, especially in complex scenarios. However, how to combine the heterogeneous information and exploit the complementarity of…

Learning from multiple modalities, such as audio and video, offers opportunities for leveraging complementary information, enhancing robustness, and improving contextual understanding and performance. However, combining such modalities…

In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…

The prevalence of noisy labels in real-world datasets poses a significant impediment to the effective deployment of deep learning models. While meta-learning strategies have emerged as a promising approach for addressing this challenge,…

Using multiple spatial modalities has been proven helpful in improving semantic segmentation performance. However, there are several real-world challenges that have yet to be addressed: (a) improving label efficiency and (b) enhancing…

Robust language processing systems are becoming increasingly important given the recent awareness of dangerous situations where brittle machine learning models can be easily broken with the presence of noises. In this paper, we introduce a…

Prevalent semantic speech tokenizers, designed to capture linguistic content, are surprisingly fragile. We find they are not robust to meaning-irrelevant acoustic perturbations; even at high Signal-to-Noise Ratios (SNRs) where speech is…

Learning with noisy labels, which aims to reduce expensive labors on accurate annotations, has become imperative in the Big Data era. Previous noise transition based method has achieved promising results and presented a theoretical…

Noise in data appears to be inevitable in most real-world machine learning applications and would cause severe overfitting problems. Not only can data features contain noise, but labels are also prone to be noisy due to human input. In this…