Related papers: Elevating Skeleton-Based Action Recognition with E…

Multimodal foundation models that can holistically process text alongside images, video, audio, and other sensory modalities are increasingly used in a variety of real-world applications. However, it is challenging to characterize and study…

Contrastive learning has gained significant attention in skeleton-based action recognition for its ability to learn robust representations from unlabeled data. However, existing methods rely on a single skeleton convention, which limits…

This study explores the application of self-supervised learning techniques for event sequences. It is a key modality in various applications such as banking, e-commerce, and healthcare. However, there is limited research on self-supervised…

Human skeleton-based action recognition has long been an indispensable aspect of artificial intelligence. Current state-of-the-art methods tend to consider only the dependencies between connected skeletal joints, limiting their ability to…

Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performance on old classes. Conventional methods, however,…

Recent advances in skeleton-based person re-identification (re-ID) obtain impressive performance via either hand-crafted skeleton descriptors or skeleton representation learning with deep learning paradigms. However, they typically require…

Multi-modal entity alignment aims to identify equivalent entities between two different multi-modal knowledge graphs, which consist of structural triples and images associated with entities. Most previous works focus on how to utilize and…

Visible-Infrared person re-identification (VI-ReID) is an important and challenging task in intelligent video surveillance. Existing methods mainly focus on learning a shared feature space to reduce the modality discrepancy between visible…

The proliferation of deep learning has significantly advanced various fields, yet Human Activity Recognition (HAR) has not fully capitalized on these developments, primarily due to the scarcity of labeled datasets. Despite the integration…

Imitation learning has emerged as a powerful paradigm in robot manipulation, yet its generalization capability remains constrained by object-specific dependencies in limited expert demonstrations. To address this challenge, we propose…

Obtaining common representations from different modalities is important in that they are interchangeable with each other in a classification problem. For example, we can train a classifier on image features in the common representations and…

Human action recognition plays an important role when developing intelligent interactions between humans and machines. While there is a lot of active research on improving the machine learning algorithms for skeleton-based action…

Multimodal fusion leverages information across modalities to learn better feature representations with the goal of improving performance in fusion-based tasks. However, multimodal datasets, especially in medical settings, are typically…

Self-paced learning has been beneficial for tasks where some initial knowledge is available, such as weakly supervised learning and domain adaptation, to select and order the training sample sequence, from easy to complex. However its…

Self-supervised learning is an efficient pre-training method for medical image analysis. However, current research is mostly confined to specific-modality data pre-training, consuming considerable time and resources without achieving…

Skeleton-based action recognition receives the attention of many researchers as it is robust to viewpoint and illumination changes, and its processing is much more efficient than the processing of video frames. With the emergence of deep…

Multimodality Representation Learning, as a technique of learning to embed information from different modalities and their correlations, has achieved remarkable success on a variety of applications, such as Visual Question Answering (VQA),…

Despite remarkable advances in emotion recognition, they are severely restrained from either the essentially limited property of the employed single modality, or the synchronous presence of all involved multiple modalities. Motivated by…

Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which train the two-stream model in a separate way. However, it's…

The focal point of egocentric video understanding is modelling hand-object interactions. Standard models, e.g. CNNs or Vision Transformers, which receive RGB frames as input perform well. However, their performance improves further by…