Related papers: HaLP: Hallucinating Latent Positives for Skeleton-…

Self-supervised contrastive learning has emerged as a powerful paradigm for skeleton-based action recognition by enforcing consistency in the embedding space. However, existing methods rely on binary contrastive objectives that overlook the…

Skeleton-based human action recognition aims to classify human skeletal sequences, which are spatiotemporal representations of actions, into predefined categories. To reduce the reliance on costly annotations of skeletal sequences while…

Contrastive learning methods train visual encoders by comparing views from one instance to others. Typically, the views created from one instance are set as positive, while views from other instances are negative. This binary instance…

Contrastive learning has been applied to Human Activity Recognition (HAR) based on sensor data owing to its ability to achieve performance comparable to supervised learning with a large amount of unlabeled data and a small amount of labeled…

The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical images requires domain knowledge and can…

Self-supervised learning is a machine learning approach that generates implicit labels by learning underlined patterns and extracting discriminative features from unlabeled data without manual labelling. Contrastive learning introduces the…

Self-supervised learning (SSL) approaches have brought tremendous success across many tasks and domains. It has been argued that these successes can be attributed to a link between SSL and identifiable representation learning: Temporal…

Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…

This paper presents a novel end-to-end method for the problem of skeleton-based unsupervised human action recognition. We propose a new architecture with a convolutional autoencoder that uses graph Laplacian regularization to model the…

Self-supervised learning (SSL) has demonstrated its effectiveness in learning representations through comparison methods that align with human intuition. However, mainstream SSL methods heavily rely on high body datasets with single label,…

Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. However, neural collapse, where embeddings converge into a…

What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include more informative features by applying complex data…

Neuron labeling assigns textual descriptions to internal units of deep networks. Existing approaches typically rely on highly activating examples, often yielding broad or misleading labels by focusing on dominant but incidental visual…

The high cost of annotating data makes self-supervised approaches, such as contrastive learning methods, appealing for Human Activity Recognition (HAR). Effective contrastive learning relies on selecting informative positive and negative…

Contrastive learning has moved the state of the art for many tasks in computer vision and information retrieval in recent years. This poster is the first work that applies supervised contrastive learning to the task of product matching in…

Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on…

Encouraged by the success of contrastive learning on image classification tasks, we propose a new self-supervised method for the structured regression task of 3D hand pose estimation. Contrastive learning makes use of unlabeled data for the…

Human Activity Recognition (HAR) constitutes one of the most important tasks for wearable and mobile sensing given its implications in human well-being and health monitoring. Motivated by the limitations of labeled datasets in HAR,…

Contrastive learning and self-supervised techniques have gained prevalence in computer vision for the past few years. It is essential for medical image analysis, which is often notorious for its lack of annotations. Most existing…

For pursuing accurate skeleton-based action recognition, most prior methods use the strategy of combining Graph Convolution Networks (GCNs) with attention-based methods in a serial way. However, they regard the human skeleton as a complete…