An Elastic Shape Variational Autoencoder for Skeleton Pose Trajectories
Systems and Information Engineering, University of Virginia（弗吉尼亚大学系统与信息工程系）；Biomedical Engineering, Johns Hopkins University（约翰霍普金斯大学生物医学工程系）；Dept. of Applied Mathematics and Statistics, Johns Hopkins University（约翰霍普金斯大学应用数学与统计学系）
Arafat Rahman, Shashwat Kumar, Laura E. Barnes, Anuj Srivastava
Deep generative models provide flexible frameworks for modeling complex, structured data such as images, videos, 3D objects, and texts. However, when applied to sequences of human skeletons, standard variational autoencoders (VAEs) often allocate substantial capacity to nuisance factors-such as camera orientation, subject scale, viewpoint, and execution speed-rather than the intrinsic geometry of shapes and their motion. We propose the Elastic Shape - Variational Autoencoder (ES-VAE), a geometry-aware generative model for skeletal trajectories that leverages the transported square-root velocity field (TSRVF) representation on Kendall's shape manifold. This representation inherently removes rigid translations, rotations, and global scaling of shapes, and temporal rate variability of sequences, isolating the underlying shape dynamics. The ES-VAE encoder maps skeletal sequences to a low-dimensional latent space incorporating the Riemannian logarithm map, while the decoder reconstructs sequences using the corresponding exponential map. We demonstrate the effectiveness of ES-VAE on two datasets. First, we analyze skeletal gait cycles to predict clinical mobility scores and classify subjects into healthy and post-stroke groups. Second, we evaluate action recognition on the NTU RGB+D dataset. Across both settings, ES-VAE consistently outperforms standard VAEs and a range of sequence modeling baselines, including temporal convolutional networks, transformers, and graph convolutional networks. More broadly, ES-VAE provides a principled framework for learning generative models of longitudinal data on pose shape manifolds, offering improved latent representation and downstream performance compared to existing deep learning approaches.
Hefei University（合肥学院）；School of Artificial Intelligence and Big Data, Hefei University（合肥学院人工智能与大数据学院）；Institute of Applied Optimization, School of Artificial Intelligence and Big Data, Hefei University（合肥学院人工智能与大数据学院应用优化研究所）；School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；University of Science and Technology of China（中国科学技术大学）
Recently, with the availability of cost-effective depth cameras coupled with real-time skeleton estimation, the interest in skeleton-based human action recognition is renewed. Most of the existing skeletal representation approaches use either the joint location or the dynamics model. Differing from the previous studies, we propose a new method called Denoising Autoencoder with Temporal and Categorical Constraints (DAE_CTC)} to study the skeletal representation in a view of skeleton reconstruction. Based on the concept of learning under privileged information, we integrate action categories and…
SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognition
School of Engineering Science, Simon Fraser University（西蒙菲莎大学工程科学学院）；School of Information Science and Technology, Eastern Institute of Technology（东方理工信息科学与技术学院）
Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition
University of North Carolina at Charlotte（夏洛特北卡罗来纳大学）；Northern Illinois University（北伊利诺伊大学）；Center for Research in Computer Vision, University of Central Florida（中佛罗里达大学计算机视觉研究中心）
School of Computing（计算机学院）；NUS Graduate School（新加坡国立大学研究生院）；National University of Singapore（新加坡国立大学）
We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. MCAE models motion in a two-level hierarchy. In the lower level, a spatio-temporal motion signal is divided into short, local, and semantic-agnostic snippets. In the higher level, the snippets are aggregated to form full-length semantic-aware segments. For both levels, we represent motion with a set of learned transformation invariant templates and the corresponding geometric transformations by using capsule autoencoders of a novel…
Shanghai Jiao Tong University（上海交通大学）；Qing Yuan Research Institute（清源研究院）
Detecting aligned 3D keypoints is essential under many scenarios such as object tracking, shape retrieval and robotics. However, it is generally hard to prepare a high-quality dataset for all types of objects due to the ambiguity of keypoint itself. Meanwhile, current unsupervised detectors are unable to generate aligned keypoints with good coverage. In this paper, we propose an unsupervised aligned keypoint detector, Skeleton Merger, which utilizes skeletons to reconstruct objects. It is based on an Autoencoder architecture. The encoder proposes keypoints and predicts activation strengths of …
Inria（法国国家信息与自动化研究所）；Toyota Motor Europe（丰田汽车欧洲公司）；Shanghai AI Laboratory（上海人工智能实验室）
Current self-supervised approaches for skeleton action representation learning often focus on constrained scenarios, where videos and skeleton data are recorded in laboratory settings. When dealing with estimated skeleton data in real-world videos, such methods perform poorly due to the large variations across subjects and camera viewpoints. To address this issue, we introduce ViA, a novel View-Invariant Autoencoder for self-supervised skeleton action representation learning. ViA leverages motion retargeting between different human performers as a pretext task, in order to disentangle the late…
Towards Efficient General Feature Prediction in Masked Skeleton Modeling
Hefei University of Technology（合肥工业大学）；Jilin University（吉林大学）；Zhejiang Gongshang University（浙江工商大学）；University of Science and Technology of China（中国科学技术大学）
Istituto Italiano di Tecnologia (IIT)（意大利技术研究院）；University of Trento（特伦托大学）
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 skeletal geometry across the temporal dynamics of actions. Our approach is robust towards viewpoint variations by including a self-supervised gradient reverse layer that ensures generalization across camera views. The proposed method is validated on NTU-60 and NTU-120 large-scale datasets in which it outperforms all prior unsupervised skeleton-based approaches o…
Deep learning-based 3D human pose estimation performs best when trained on large amounts of labeled data, making combined learning from many datasets an important research direction. One obstacle to this endeavor are the different skeleton formats provided by different datasets, i.e., they do not label the same set of anatomical landmarks. There is little prior research on how to best supervise one model with such discrepant labels. We show that simply using separate output heads for different skeletons results in inconsistent depth estimates and insufficient information sharing across skeleto…
IRISA（法国国家信息与自动化研究所布列塔尼分支）；Université de Bretagne Sud（南布列塔尼大学）
In the scope of gestural action recognition, the size of the feature vector representing movements is in general quite large especially when full body movements are considered. Furthermore, this feature vector evolves during the movement performance so that a complete movement is fully represented by a matrix M of size DxT , whose element M i, j represents the value of feature i at timestamps j. Many studies have addressed dimensionality reduction considering only the size of the feature vector lying in R D to reduce both the variability of gestural sequences expressed in the reduced space, an…
The Chinese University of Hong Kong（香港中文大学）；T Stone Robotics Institute of CUHK（香港中文大学汤申机器人研究所）
Learning a good 3D human pose representation is important for human pose related tasks, e.g. human 3D pose estimation and action recognition. Within all these problems, preserving the intrinsic pose information and adapting to view variations are two critical issues. In this work, we propose a novel Siamese denoising autoencoder to learn a 3D pose representation by disentangling the pose-dependent and view-dependent feature from the human skeleton data, in a fully unsupervised manner. These two disentangled features are utilized together as the representation of the 3D pose. To consider both t…
Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentation
University of Bonn, Germany（波恩大学）；University College London, UK（伦敦大学学院）；Lamarr Institute for Machine Learning and Artificial Intelligence, Germany（拉马尔人工智能与机器学习研究所）
Retargeting Motions to Diverse Skeletons via Learnable Flattening
Institute of Computer Science, University of Göttingen（哥廷根大学计算机科学研究所）；Campus Institute Data Science, University Göttingen（哥廷根大学数据科学校园研究所）；Pantomim P.S.A
We propose a new architecture for the learning of predictive spatio-temporal motion models from data alone. Our approach, dubbed the Dropout Autoencoder LSTM, is capable of synthesizing natural looking motion sequences over long time horizons without catastrophic drift or motion degradation. The model consists of two components, a 3-layer recurrent neural network to model temporal aspects and a novel auto-encoder that is trained to implicitly recover the spatial structure of the human skeleton via randomly removing information about joints during training time. This Dropout Autoencoder (D-AE) …
The gesture recognition using motion capture data and depth sensors has recently drawn more attention in vision recognition. Currently most systems only classify dataset with a couple of dozens different actions. Moreover, feature extraction from the data is often computational complex. In this paper, we propose a novel system to recognize the actions from skeleton data with simple, but effective, features using deep neural networks. Features are extracted for each frame based on the relative positions of joints (PO), temporal differences (TD), and normalized trajectories of motion (NT). Given…
Objectives. We generate via advanced Deep Learning (DL) techniques artificial leaf images in an automatized way. We aim to dispose of a source of training samples for AI applications for modern crop management. Such applications require large amounts of data and, while leaf images are not truly scarce, image collection and annotation remains a very time--consuming process. Data scarcity can be addressed by augmentation techniques consisting in simple transformations of samples belonging to a small dataset, but the richness of the augmented data is limited: this motivates the search for alterna…
The Australian National University（澳大利亚国立大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）
Human pose forecasting is an important problem in computer vision with applications to human-robot interaction, visual surveillance, and autonomous driving. Usually, forecasting algorithms use 3D skeleton sequences and are trained to forecast for a few milliseconds into the future. Long-range forecasting is challenging due to the difficulty of estimating how long a person continues an activity. To this end, our contributions are threefold: (i) we propose a generative framework for poses using variational autoencoders based on Deep Markov Models (DMMs); (ii) we evaluate our pose forecasts using…
Basis restricted elastic shape analysis on the space of unregistered surfaces
Florida State University（佛罗里达州立大学）；Univ. Lille（里尔大学）；CNRS（法国国家科学研究中心）；Centrale Lille（里尔中央理工学院）；Institut Mines-Télécom（法国矿业电信学院）；CRIStAL（CRIStAL研究中心）；IMT Nord Europe（IMT北欧洲学院）；Centre for Digital Systems（数字系统中心）；University of Houston（休斯顿大学）
