Related papers: PCBEAR: Pose Concept Bottleneck for Explainable Ac…

Human Action Recognition (HAR), one of the most important tasks in computer vision, has developed rapidly in the past decade and has a wide range of applications in health monitoring, intelligent surveillance, virtual reality, human…

Robustness to domain changes is a key capability for effective deployment of human action recognition systems in real-world scenarios, where action categories at inference can present important domain shifts or even unseen actions from…

Human pose estimation and tracking are fundamental tasks for understanding human behaviors in videos. Existing top-down framework-based methods usually perform three-stage tasks: human detection, pose estimation and tracking. Although…

Creating pose-driven human avatars is about modeling the mapping from the low-frequency driving pose to high-frequency dynamic human appearances, so an effective pose encoding method that can encode high-fidelity human details is essential…

In recent years, face recognition systems have achieved exceptional success due to promising advances in deep learning architectures. However, they still fail to achieve expected accuracy when matching profile images against a gallery of…

Image retrieval plays a pivotal role in applications from wildlife conservation to healthcare, for finding individual animals or relevant images to aid diagnosis. Although deep learning techniques for image retrieval have advanced…

Models based on human-understandable concepts have received extensive attention to improve model interpretability for trustworthy artificial intelligence in the field of medical image analysis. These methods can provide convincing…

Transformers have demonstrated remarkable performance in skeleton-based human action recognition, yet their quadratic computational complexity remains a bottleneck for real-world applications. To mitigate this, linear attention mechanisms…

Human pose estimation in unconstrained images and videos is a fundamental computer vision task. To illustrate the evolutionary path in technique, in this survey we summarize representative human pose methods in a structured taxonomy, with a…

Robotic manipulation, in particular in-hand object manipulation, often requires an accurate estimate of the object's 6D pose. To improve the accuracy of the estimated pose, state-of-the-art approaches in 6D object pose estimation use…

Explainable AI seeks to bring light to the decision-making processes of black-box models. Traditional saliency-based methods, while highlighting influential data segments, often lack semantic understanding. Recent advancements, such as…

A prior represents a set of beliefs or assumptions about a system, aiding inference and decision-making. In this paper, we introduce the challenge of unsupervised categorical prior learning in pose estimation, where AI models learn a…

This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection…

Concept Bottleneck Models (CBMs) improve the explainability of black-box Deep Learning (DL) by introducing intermediate semantic concepts. However, standard CBMs often overlook domain-specific relationships and causal mechanisms, and their…

This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level weak spatial models. Unconstrained…

The imperative to comprehend the behaviors of deep learning models is of utmost importance. In this realm, Explainable Artificial Intelligence (XAI) has emerged as a promising avenue, garnering increasing interest in recent years. Despite…

Robots that interact with humans in a physical space or application need to think about the person's posture, which typically comes from visual sensors like cameras and infra-red. Artificial intelligence and machine learning algorithms use…

Deep learning representations are often difficult to interpret, which can hinder their deployment in sensitive applications. Concept Bottleneck Models (CBMs) have emerged as a promising approach to mitigate this issue by learning…

Developing high-performing, yet interpretable models remains a critical challenge in modern AI. Concept-based models (CBMs) attempt to address this by extracting human-understandable concepts from a global encoding (e.g., image encoding)…

We introduce a novel deep learning based group activity recognition approach called the Pose Only Group Activity Recognition System (POGARS), designed to use only tracked poses of people to predict the performed group activity. In contrast…