相关论文: InfoMAE: Pair-Efficient Cross-Modal Alignment for …

Multimodal sensing systems are increasingly prevalent in various real-world applications. Most existing multimodal learning approaches heavily rely on training with a large amount of synchronized, complete multimodal data. However, such a…

In many machine learning systems that jointly learn from multiple modalities, a core research question is to understand the nature of multimodal interactions: how modalities combine to provide new task-relevant information that was not…

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

Emotion recognition models using audio input data can enable the development of interactive systems with applications in mental healthcare, marketing, gaming, and social media analysis. While the field of affective computing using audio…

Multimodal learning has significantly enhanced machine learning performance but still faces numerous challenges and limitations. Imbalanced multimodal learning is one of the problems extensively studied in recent works and is typically…

Multi-modal fusion is crucial for Internet of Things (IoT) perception, widely deployed in smart homes, intelligent transport, industrial automation, and healthcare. However, existing systems often face challenges: high model complexity…

In recent years, pre-trained visual-linguistic models have demonstrated tremendous potential, becoming a crucial foundational framework for numerous downstream tasks. However, the information density between text and images is not uniformly…

Missing or corrupted modalities are common in physiological signal-based medical applications owing to hardware constraints or motion artifacts. However, most existing methods assume the availability of all modalities, resulting in…

The Internet of Things (IoT) integrates more than billions of intelligent devices over the globe with the capability of communicating with other connected devices with little to no human intervention. IoT enables data aggregation and…

To address the modality learning degeneration caused by modality imbalance, existing multimodal learning~(MML) approaches primarily attempt to balance the optimization process of each modality from the perspective of model learning.…

Semi-supervised learning (SSL) seeks to enhance task performance by training on both labeled and unlabeled data. Mainstream SSL image classification methods mostly optimize a loss that additively combines a supervised classification…

Deep learning-based AMC methods have achieved remarkable performance, but their practical deployment remains constrained by the high cost of labeled data. Although self-supervised learning (SSL) reduces the reliance on labels, existing…

Recent studies have demonstrated that vision models can effectively learn multimodal audio-image representations when paired. However, the challenge of enabling deep models to learn representations from unpaired modalities remains…

Wearable devices enable continuous multi-modal physiological and behavioral monitoring, yet analysis of these data streams faces fundamental challenges including the lack of gold-standard labels and incomplete sensor data. While…

Recently, the paradigm of massive ultra-reliable low-latency IoT communications (URLLC-IoT) has gained growing interest. Reliable delay-critical uplink transmission in IoT is a challenging task since low-complex devices typically do not…

We investigate the utility of in-domain self-supervised pre-training of vision models in the analysis of remote sensing imagery. Self-supervised learning (SSL) has emerged as a promising approach for remote sensing image classification due…

Automatic modulation classification (AMC) is a basic technology in intelligent wireless communication systems. It is important for tasks such as spectrum monitoring, cognitive radio, and secure communications. In recent years, deep learning…

The mechanism of connecting multimodal signals through self-attention operation is a key factor in the success of multimodal Transformer networks in remote sensing data fusion tasks. However, traditional approaches assume access to all…

Latest federated learning (FL) methods started to focus on how to use unlabeled data in clients for training due to users' privacy concerns, high labeling costs, or lack of expertise. However, current Federated…

Recently, masked image modeling (MIM), an important self-supervised learning (SSL) method, has drawn attention for its effectiveness in learning data representation from unlabeled data. Numerous studies underscore the advantages of MIM,…