English
Related papers

Related papers: Self-Supervised 3D Action Representation Learning …

200 papers

We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D detector on the source domain with our proposed random object…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Jihan Yang , Shaoshuai Shi , Zhe Wang , Hongsheng Li , Xiaojuan Qi

Point cloud analysis (such as 3D segmentation and detection) is a challenging task, because of not only the irregular geometries of many millions of unordered points, but also the great variations caused by depth, viewpoint, occlusion, etc.…

Computer Vision and Pattern Recognition · Computer Science 2023-07-28 Tuo Feng , Wenguan Wang , Xiaohan Wang , Yi Yang , Qinghua Zheng

To integrate action recognition into autonomous robotic systems, it is essential to address challenges such as person occlusions-a common yet often overlooked scenario in existing self-supervised skeleton-based action recognition methods.…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Yifei Chen , Kunyu Peng , Alina Roitberg , David Schneider , Jiaming Zhang , Junwei Zheng , Yufan Chen , Ruiping Liu , Kailun Yang , Rainer Stiefelhagen

Skeleton-based action recognition is a central task in computer vision and human-robot interaction. However, most previous methods suffer from overlooking the explicit exploitation of the latent data distributions (i.e., the intra-class…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Shaojie Zhang , Jianqin Yin , Yonghao Dang

Global registration of point clouds aims to find an optimal alignment of a sequence of 2D or 3D point sets. In this paper, we present a novel method that takes advantage of current deep learning techniques for unsupervised learning of…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Lingjing Wang , Yi Shi , Xiang Li , Yi Fang

Self-supervised 3D representation learning aims to learn effective representations from large-scale unlabeled point clouds. Most existing approaches adopt point discrimination as the pretext task, which assigns matched points in two…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Chengyao Wang , Li Jiang , Xiaoyang Wu , Zhuotao Tian , Bohao Peng , Hengshuang Zhao , Jiaya Jia

Recent methods in self-supervised learning have demonstrated that masking-based pretext tasks extend beyond NLP, serving as useful pretraining objectives in computer vision. However, existing approaches apply random or ad hoc masking…

Computer Vision and Pattern Recognition · Computer Science 2022-12-19 Dylan Sam , Min Bai , Tristan McKinney , Li Erran Li

Current state-of-the-art methods cast monocular 3D human pose estimation as a learning problem by training neural networks on large data sets of images and corresponding skeleton poses. In contrast, we propose an approach that can exploit…

Computer Vision and Pattern Recognition · Computer Science 2020-10-14 Simon Jenni , Paolo Favaro

Person re-identification via 3D skeletons is an emerging topic with great potential in security-critical applications. Existing methods typically learn body and motion features from the body-joint trajectory, whereas they lack a systematic…

Computer Vision and Pattern Recognition · Computer Science 2021-07-06 Haocong Rao , Xiping Hu , Jun Cheng , Bin Hu

Perceptual understanding of the scene and the relationship between its different components is important for successful completion of robotic tasks. Representation learning has been shown to be a powerful technique for this, but most of the…

Skeleton-based action recognition aims to project skeleton sequences to action categories, where skeleton sequences are derived from multiple forms of pre-detected points. Compared with earlier methods that focus on exploring single-form…

Computer Vision and Pattern Recognition · Computer Science 2022-07-01 Xuanhan Wang , Yan Dai , Lianli Gao , Jingkuan Song

Part mobility analysis is a significant aspect required to achieve a functional understanding of 3D objects. It would be natural to obtain part mobility from the continuous part motion of 3D objects. In this study, we introduce a…

Computer Vision and Pattern Recognition · Computer Science 2021-03-03 Yahao Shi , Xinyu Cao , Bin Zhou

Traditional approaches in unsupervised or self supervised learning for skeleton-based action classification have concentrated predominantly on the dynamic aspects of skeletal sequences. Yet, the intricate interaction between the moving and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Shanaka Ramesh Gunasekara , Wanqing Li , Philip Ogunbona , Jack Yang

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…

Computer Vision and Pattern Recognition · Computer Science 2021-03-23 Lei Shi , Yifan Zhang , Jian Cheng , Hanqing Lu

Self-supervised pretraining has become the mainstream approach for learning MRI representations from unlabeled scans. However, most existing objectives still treat each scan primarily as static aggregations of slices, patches or volumes. We…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Yu Wang , Qingchao Chen

In this work, we propose to learn local descriptors for point clouds in a self-supervised manner. In each iteration of the training, the input of the network is merely one unlabeled point cloud. On top of our previous work, that directly…

Robotics · Computer Science 2020-03-12 Yijun Yuan , Jiawei Hou , Andreas Nüchter , Sören Schwertfeger

Skeleton-based action recognition has recently attracted a lot of attention. Researchers are coming up with new approaches for extracting spatio-temporal relations and making considerable progress on large-scale skeleton-based datasets.…

Computer Vision and Pattern Recognition · Computer Science 2019-12-19 Sangwoo Cho , Muhammad Hasan Maqbool , Fei Liu , Hassan Foroosh

In medical image analysis, the cost of acquiring high-quality data and their annotation by experts is a barrier in many medical applications. Most of the techniques used are based on supervised learning framework and need a large amount of…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Siladittya Manna , Saumik Bhattacharya , Umapada Pal

Self-supervised, multi-modal learning has been successful in holistic representation of complex scenarios. This can be useful to consolidate information from multiple modalities which have multiple, versatile uses. Its application in…

Computer Vision and Pattern Recognition · Computer Science 2020-11-03 Aniruddha Tamhane , Jie Ying Wu , Mathias Unberath

In low-level video analyses, effective representations are important to derive the correspondences between video frames. These representations have been learned in a self-supervised fashion from unlabeled images or videos, using carefully…

Computer Vision and Pattern Recognition · Computer Science 2023-06-23 Rui Li , Dong Liu