Related papers: SGA-INTERACT: A 3D Skeleton-based Benchmark for Gr…

We present a new deep learning approach for real-time 3D human action recognition from skeletal data and apply it to develop a vision-based intelligent surveillance system. Given a skeleton sequence, we propose to encode skeleton poses and…

In this paper, we study the problem of one-shot skeleton-based action recognition, which poses unique challenges in learning transferable representation from base classes to novel classes, particularly for fine-grained actions. Existing…

Skeleton-based action recognition task is entangled with complex spatio-temporal variations of skeleton joints, and remains challenging for Recurrent Neural Networks (RNNs). In this work, we propose a temporal-then-spatial recalibration…

This paper introduces a simple yet effective strategy for exercise classification and muscle group activation prediction (MGAP). These tasks have significant implications for personal fitness, facilitating more affordable, accessible,…

We introduce a novel deep learning framework for data-driven motion retargeting between skeletons, which may have different structure, yet corresponding to homeomorphic graphs. Importantly, our approach learns how to retarget without…

Understanding human activity is a crucial aspect of developing intelligent robots, particularly in the domain of human-robot collaboration. Nevertheless, existing systems encounter challenges such as over-segmentation, attributed to errors…

Simulating how organized groups (e.g., corporations) make decisions (e.g., responding to a competitor's move) is essential for understanding real-world dynamics and could benefit relevant applications (e.g., market prediction). In this…

This work addresses the problem of Social Activity Recognition (SAR), a critical component in real-world tasks like surveillance and assistive robotics. Unlike traditional event understanding approaches, SAR necessitates modeling individual…

Skeleton-based action recognition receives increasing attention because the skeleton representations reduce the amount of training data by eliminating visual information irrelevant to actions. To further improve the sample efficiency,…

Automated social behaviour analysis of mice has become an increasingly popular research area in behavioural neuroscience. Recently, pose information (i.e., locations of keypoints or skeleton) has been used to interpret social behaviours of…

In group activity recognition, the temporal dynamics of the whole activity can be inferred based on the dynamics of the individual people representing the activity. We build a deep model to capture these dynamics based on LSTM (long-short…

Inferring future activity information based on observed activity data is a crucial step to improve the accuracy of early activity prediction. Traditional methods based on generative adversarial networks(GAN) or joint learning frameworks can…

Skeleton data, which consists of only the 2D/3D coordinates of the human joints, has been widely studied for human action recognition. Existing methods take the semantics as prior knowledge to group human joints and draw correlations…

Combining skeleton structure with graph convolutional networks has achieved remarkable performance in human action recognition. Since current research focuses on designing basic graph for representing skeleton data, these embedding features…

Skeleton-based human action recognition is a longstanding challenge due to its complex dynamics. Some fine-grain details of the dynamics play a vital role in classification. The existing work largely focuses on designing incremental neural…

This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the state-of-the-art method of CASA, where sequences of 3D…

Robot navigation in densely populated environments presents significant challenges, particularly regarding the interplay between individual and group dynamics. Current navigation models predominantly address interactions with individual…

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…

Deep learning approaches deliver state-of-the-art performance in recognition of spatiotemporal human motion data. However, one of the main challenges in these recognition tasks is limited available training data. Insufficient training data…

This work introduces a novel framework for dynamic factor model-based group-level analysis of multiple subjects time series data, called GRoup Integrative DYnamic factor (GRIDY) models. The framework identifies and characterizes…