Related papers: Multi-Label Zero-Shot Human Action Recognition via…

Tiny Actions Challenge focuses on understanding human activities in real-world surveillance. Basically, there are two main difficulties for activity recognition in this scenario. First, human activities are often recorded at a distance, and…

In this work, we focus on label efficient learning for video action detection. We develop a novel semi-supervised active learning approach which utilizes both labeled as well as unlabeled data along with informative sample selection for…

We present a generative framework for zero-shot action recognition where some of the possible action classes do not occur in the training data. Our approach is based on modeling each action class using a probability distribution whose…

Real-time human activity recognition plays an essential role in real-world human-centered robotics applications, such as assisted living and human-robot collaboration. Although previous methods based on skeletal data to encode human poses…

Due to burdensome data requirements, learning from demonstration often falls short of its promise to allow users to quickly and naturally program robots. Demonstrations are inherently ambiguous and incomplete, making correct generalization…

In this work, we tackle the problem of performing multi-label classification in the case of extremely heterogeneous data and with decentralized Machine Learning. Solving this issue is very important in IoT scenarios, where data coming from…

Understanding human actions from visual observations is essential for human--robot interaction, particularly when semantic interpretation of unfamiliar or hard-to-annotate actions is required. In scenarios such as rapid and less common…

Many real-world scenarios, such as human activity recognition (HAR) in IoT, can be formalized as a multi-task multi-view learning problem. Each specific task consists of multiple shared feature views collected from multiple sources, either…

Existing action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors. This requires actor-specific pose estimation (e.g., humans vs. animals), leading to cumbersome…

Zero-shot action recognition (ZSAR) aims to learn an alignment model between videos and class descriptions of seen actions that is transferable to unseen actions. The text queries (class descriptions) used in existing ZSAR works, however,…

Representation of human actions as a sequence of human body movements or action attributes enables the development of models for human activity recognition and summarization. We present an extension of the low-rank representation (LRR)…

Human activity recognition serves as the foundation for various emerging applications. In recent years, researchers have used collaborative sensing of multi-source sensors to capture complex and dynamic human activities. However, multimodal…

Unlike the sparse label action detection task, where a single action occurs in each timestamp of a video, in a dense multi-label scenario, actions can overlap. To address this challenging task, it is necessary to simultaneously learn (i)…

Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. However, mainstream solutions generally adopt hand-crafted…

Human Activity Recognition~(HAR) is the classification of human movement, captured using one or more sensors either as wearables or embedded in the environment~(e.g. depth cameras, pressure mats). State-of-the-art methods of HAR rely on…

We present a unified framework for understanding human social behaviors in raw image sequences. Our model jointly detects multiple individuals, infers their social actions, and estimates the collective actions with a single feed-forward…

Human activity recognition (HAR) using wearable sensors has advanced through various machine learning paradigms, each with inherent trade-offs between performance and labeling requirements. While fully supervised techniques achieve high…

In human vision objects and their parts can be visually recognized from purely spatial or purely temporal information but the mechanisms integrating space and time are poorly understood. Here we show that human visual recognition of objects…

A major emerging challenge is how to protect people's privacy as cameras and computer vision are increasingly integrated into our daily lives, including in smart devices inside homes. A potential solution is to capture and record just the…

Human actions in videos are 3D signals. However, there are a few methods available for multiple human action recognition. For long videos, it's difficult to search within a video for a specific action and/or person. For that, this paper…