Related papers: STAIR: Manipulating Collaborative and Multimodal I…

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…

Self-supervised representation learning for human action recognition has developed rapidly in recent years. Most of the existing works are based on skeleton data while using a multi-modality setup. These works overlooked the differences in…

Multimodal recommender systems utilize various types of information to model user preferences and item features, helping users discover items aligned with their interests. The integration of multimodal information mitigates the inherent…

Image Style Transfer (IST) is an interdisciplinary topic of computer vision and art that continuously attracts researchers' interests. Different from traditional Image-guided Image Style Transfer (IIST) methods that require a style…

Modern recommender systems often embed users and items into low-dimensional latent representations, based on their observed interactions. In practical recommendation scenarios, users often exhibit various intents which drive them to…

Online Class-Incremental continual Learning (OCIL) addresses the challenge of continuously learning from a single-channel data stream, adapting to new tasks while mitigating catastrophic forgetting. Recently, Mutual Information (MI)-based…

Explainability and effectiveness are two key aspects for building recommender systems. Prior efforts mostly focus on incorporating side information to achieve better recommendation performance. However, these methods have some weaknesses:…

Many retrieval applications can benefit from multiple modalities, e.g., text that contains images on Wikipedia, for which how to represent multimodal data is the critical component. Most deep multimodal learning methods typically involve…

The use of multimodal data in assisted diagnosis and segmentation has emerged as a prominent area of interest in current research. However, one of the primary challenges is how to effectively fuse multimodal features. Most of the current…

Multi-modal stance detection (MSD) aims to determine an author's stance toward a given target using both textual and visual content. While recent methods leverage multi-modal fusion and prompt-based learning, most fail to distinguish…

In multi-modal learning, some modalities are more influential than others, and their absence can have a significant impact on classification/segmentation accuracy. Addressing this challenge, we propose a novel approach called Meta-learned…

In cold-start scenarios, the scarcity of collaborative signals for new items exacerbates the Matthew effect, which undermines platform diversity and remains a persistent challenge in real-world recommender systems. Existing methods…

Images and structured tables are essential parts of real-world databases. Though tabular-image representation learning is promising to create new insights, it remains a challenging task, as tabular data is typically heterogeneous and…

Multimodal learning aims to leverage information from diverse data modalities to achieve more comprehensive performance. However, conventional multimodal models often suffer from modality imbalance, where one or a few modalities dominate…

Composed Image Retrieval (CIR) retrieves target images using a multi-modal query that combines a reference image with text describing desired modifications. The primary challenge is effectively fusing this visual and textual information.…

Collaborative perception by leveraging the shared semantic information plays a crucial role in overcoming the individual limitations of isolated agents. However, existing collaborative perception methods tend to focus solely on the spatial…

Session-based recommendation systems must capture implicit user intents from sessions. However, existing models suffer from issues such as item interaction dominance and noisy sessions. We propose a multi-channel recommendation model,…

Real-life medical data is often multimodal and incomplete, fueling the growing need for advanced deep learning models capable of integrating them efficiently. The use of diverse modalities, including histopathology slides, MRI, and genetic…

Graph-based social recommendation systems have shown significant promise in enhancing recommendation performance, particularly in addressing the issue of data sparsity in user behaviors. Typically, these systems leverage Graph Neural…

Recommender systems are fundamental information filtering techniques to recommend content or items that meet users' personalities and potential needs. As a crucial solution to address the difficulty of user identification and unavailability…