English
Related papers

Related papers: Delving Deep into One-Shot Skeleton-based Action R…

200 papers

Skeleton sequences are lightweight and compact, and thus are ideal candidates for action recognition on edge devices. Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues,…

Computer Vision and Pattern Recognition · Computer Science 2022-08-24 Zhenyue Qin , Yang Liu , Pan Ji , Dongwoo Kim , Lei Wang , Bob McKay , Saeed Anwar , Tom Gedeon

Skeleton-based Human Activity Recognition has achieved great interest in recent years as skeleton data has demonstrated being robust to illumination changes, body scales, dynamic camera views, and complex background. In particular,…

Computer Vision and Pattern Recognition · Computer Science 2021-06-23 Chiara Plizzari , Marco Cannici , Matteo Matteucci

Active non-line-of-sight imaging systems are of growing interest for diverse applications. The most commonly proposed approaches to date rely on exploiting time-resolved measurements, i.e., measuring the time it takes for short light pulses…

Image and Video Processing · Electrical Eng. & Systems 2017-11-20 Christos Thrampoulidis , Gal Shulkind , Feihu Xu , William T. Freeman , Jeffrey H. Shapiro , Antonio Torralba , Franco N. C. Wong , Gregory W. Wornell

Instance-aware segmentation of unseen objects is essential for a robotic system in an unstructured environment. Although previous works achieved encouraging results, they were limited to segmenting the only visible regions of unseen…

Robotics · Computer Science 2022-03-01 Seunghyeok Back , Joosoon Lee , Taewon Kim , Sangjun Noh , Raeyoung Kang , Seongho Bak , Kyoobin Lee

Reasoning about potential occlusions is essential for robots to efficiently predict whether an object exists in an environment. Though existing work shows that a robot with active perception can achieve various tasks, it is still unclear if…

Robotics · Computer Science 2021-07-30 Mengdi Li , Cornelius Weber , Matthias Kerzel , Jae Hee Lee , Zheni Zeng , Zhiyuan Liu , Stefan Wermter

R}easoning for Robust Human Pose and Shape Estimation), designed to estimate human body shape and pose from single-view images. ReBaR effectively addresses the challenges of occlusions and depth ambiguity by learning reference features for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yongkang Cheng , Mingjiang Liang , Jifeng Ning , Gaoge Han , Wei Liu , Shaoli Huang

This paper presents a new method for 3D action recognition with skeleton sequences (i.e., 3D trajectories of human skeleton joints). The proposed method first transforms each skeleton sequence into three clips each consisting of several…

Computer Vision and Pattern Recognition · Computer Science 2017-11-21 Qiuhong Ke , Mohammed Bennamoun , Senjian An , Ferdous Sohel , Farid Boussaid

Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in recent years. Generally, the performance of existing methods drops when the target person is too small/large, or…

Computer Vision and Pattern Recognition · Computer Science 2020-04-27 Yu Cheng , Bo Yang , Bo Wang , Robby T. Tan

Recent advancements in computational resources and Deep Learning methodologies has significantly benefited development of intelligent vision-based surveillance applications. Gait recognition in the presence of occlusion is one of the…

Computer Vision and Pattern Recognition · Computer Science 2021-10-20 Somnath Sendhil Kumara , Pratik Chattopadhyaya , Lipo Wang

While current skeleton action recognition models demonstrate impressive performance on large-scale datasets, their adaptation to new application scenarios remains challenging. These challenges are particularly pronounced when facing new…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Zongye Zhang , Wenrui Cai , Qingjie Liu , Yunhong Wang

3D action recognition - analysis of human actions based on 3D skeleton data - becomes popular recently due to its succinctness, robustness, and view-invariant representation. Recent attempts on this problem suggested to develop RNN-based…

Computer Vision and Pattern Recognition · Computer Science 2016-07-27 Jun Liu , Amir Shahroudy , Dong Xu , Gang Wang

Optical motion capture is a foundational technology driving advancements in cutting-edge fields such as virtual reality and film production. However, system performance suffers severely under large-scale marker occlusions common in…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Chen Qian , Danyang Li , Xinran Yu , Zheng Yang , Qiang Ma

Most image-based 3D object reconstructors assume that objects are fully visible, ignoring occlusions that commonly occur in real-world scenarios. In this paper, we introduce Amodal3R, a conditional 3D generative model designed to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Tianhao Wu , Chuanxia Zheng , Frank Guan , Andrea Vedaldi , Tat-Jen Cham

Despite significant progress, we show that state of the art 3D human pose and shape estimation methods remain sensitive to partial occlusion and can produce dramatically wrong predictions although much of the body is observable. To address…

Computer Vision and Pattern Recognition · Computer Science 2021-10-13 Muhammed Kocabas , Chun-Hao P. Huang , Otmar Hilliges , Michael J. Black

Emotion recognition through body movements has emerged as a compelling and privacy-preserving alternative to traditional methods that rely on facial expressions or physiological signals. Recent advancements in 3D skeleton acquisition…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Haifeng Lu , Jiuyi Chen , Zhen Zhang , Ruida Liu , Runhao Zeng , Xiping Hu

Given that approximately half of science, technology, engineering, and mathematics (STEM) undergraduate students in U.S. colleges and universities leave by the end of the first year [15], it is crucial to improve the quality of classroom…

Computer Vision and Pattern Recognition · Computer Science 2024-03-01 Shrouk Wally , Ahmed Elsayed , Islam Alkabbany , Asem Ali , Aly Farag

Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. However, occlusions and moving objects are still some of the major…

Computer Vision and Pattern Recognition · Computer Science 2021-10-25 Jiaojiao Fang , Guizhong Liu

Segmenting highly-overlapping image objects is challenging, because there is typically no distinction between real object contours and occlusion boundaries on images. Unlike previous instance segmentation methods, we model image formation…

Computer Vision and Pattern Recognition · Computer Science 2023-03-13 Lei Ke , Yu-Wing Tai , Chi-Keung Tang

Unwanted camera occlusions, such as debris, dust, rain-drops, and snow, can severely degrade the performance of computer-vision systems. Dynamic occlusions are particularly challenging because of the continuously changing pattern. Existing…

Computer Vision and Pattern Recognition · Computer Science 2023-08-02 Rong Zou , Manasi Muglikar , Nico Messikommer , Davide Scaramuzza

Occlusion is commonplace in realistic human-robot shared environments, yet its effects are not considered in standard 3D human pose estimation benchmarks. This leaves the question open: how robust are state-of-the-art 3D pose estimation…

Computer Vision and Pattern Recognition · Computer Science 2019-01-14 István Sárándi , Timm Linder , Kai O. Arras , Bastian Leibe