Related papers: TCGM: An Information-Theoretic Framework for Semi-…

Learning from fully-unlabeled data is challenging in Multimedia Forensics problems, such as Person Re-Identification and Text Authorship Attribution. Recent self-supervised learning methods have shown to be effective when dealing with…

Semi-supervised learning is a setting in which one has labeled and unlabeled data available. In this survey we explore different types of theoretical results when one uses unlabeled data in classification and regression tasks. Most methods…

We propose TG-LMM (Text-Guided Large Multi-Modal Model), a novel approach that leverages textual descriptions of organs to enhance segmentation accuracy in medical images. Existing medical image segmentation methods face several challenges:…

Multimodal VAEs seek to model the joint distribution over heterogeneous data (e.g.\ vision, language), whilst also capturing a shared representation across such modalities. Prior work has typically combined information from the modalities…

High annotation costs are a substantial bottleneck in applying modern deep learning architectures to clinically relevant medical use cases, substantiating the need for novel algorithms to learn from unlabeled data. In this work, we propose…

We propose a meta-learning method for semi-supervised learning that learns from multiple tasks with heterogeneous attribute spaces. The existing semi-supervised meta-learning methods assume that all tasks share the same attribute space,…

In this paper, a novel pattern classification approach is proposed by regularizing the classifier learning to maximize mutual information between the classification response and the true class label. We argue that, with the learned…

Graphs are growing rapidly, along with the number of distinct label categories associated with them. Applications like e-commerce, healthcare, recommendation systems, and various social media platforms are rapidly moving towards graph…

Multi-view learning is widely applied to real-life datasets, such as multiple omics biological data, but it often suffers from both missing views and missing labels. Prior probabilistic approaches addressed the missing view problem by using…

While supervised deep learning has achieved great success in a range of applications, relatively little work has studied the discovery of knowledge from unlabeled data. In this paper, we propose an unsupervised deep learning framework to…

Generative models (GMs) have received increasing research interest for their remarkable capacity to achieve comprehensive understanding. However, their potential application in the domain of multi-modal tracking has remained relatively…

In recent years, information-theoretic generalization bounds have gained increasing attention for analyzing the generalization capabilities of meta-learning algorithms. However, existing results are confined to two-step bounds, failing to…

Many recent datasets contain a variety of different data modalities, for instance, image, question, and answer data in visual question answering (VQA). When training deep net classifiers on those multi-modal datasets, the modalities get…

Existing multimodal methods typically assume that different modalities share the same category set. However, in real-world applications, the category distributions in multimodal data exhibit inconsistencies, which can hinder the model's…

Given some video-query pairs with untrimmed videos and sentence queries, temporal sentence grounding (TSG) aims to locate query-relevant segments in these videos. Although previous respectable TSG methods have achieved remarkable success,…

This paper addresses graph learning in Gaussian Graphical Models (GGMs). In this context, data matrices often come with auxiliary metadata (e.g., textual descriptions associated with each node) that is usually ignored in traditional graph…

Few-shot image classification remains a critical challenge in the field of computer vision, particularly in data-scarce environments. Existing methods typically rely on pre-trained visual-language models, such as CLIP. However, due to the…

In this paper we study the problem of learning from multiple modal data for purpose of document classification. In this problem, each document is composed two different modals of data, i.e., an image and a text. Cross-modal factor analysis…

Complex instruction-following with elaborate constraints is imperative for Large Language Models (LLMs). While existing methods have constructed data for complex instruction alignment, they all rely on a more advanced model, especially…

Contemporary cardiovascular management involves complex consideration and integration of multimodal cardiac datasets, where each modality provides distinct but complementary physiological characteristics. While the effective integration of…