36,209 Hits in 5.3 sec

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
: A Practical and Robust System for Object Detection and Pose Estimation in Heavy Clutter using Active Illumination Liu, Ming ARISTA -Image Search to Annotation on Billions of Web Photos Author Index  ...  from Sparse Reflection Correspondences Demo: A Practical and Robust System for Object Detection and Pose Estimation in Heavy Clutter using Active Illumination Tyagi, Vivek Workshop: QPLC: A Novel Multimodal  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Modeling mutual context of object and human pose in human-object interaction activities

Bangpeng Yao, Li Fei-Fei
2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
In this paper we propose a new random field model to encode the mutual context of objects and human poses in human-object interaction activities.  ...  search approach, and the parameters of the model are estimated by a new max-margin algorithm.  ...  This research is partially supported by an NSF CAREER grant (IIS-0845230), a Google research award, and a Microsoft Research Fellowship to L.F-F.  ... 
doi:10.1109/cvpr.2010.5540235 dblp:conf/cvpr/YaoF10a fatcat:6hltqgrgznbxhcadpaf72tokqm

A Neural-Dynamic Architecture for Concurrent Estimation of Object Pose and Identity

Oliver Lomp, Christian Faubel, Gregor Schöner
2017 Frontiers in Neurorobotics  
Handling objects or interacting with a human user about objects on a shared tabletop requires that objects be identified after learning from a small number of views and that object pose be estimated.  ...  In a scenario with 30 everyday objects, the system achieves recognition rates of 87.2% from a single training view for each object, while also estimating pose quite precisely.  ...  The authors are thankful to a reviewer for suggesting a better kind of baseline comparison and to Raul Grieben for help in implementing that.  ... 
doi:10.3389/fnbot.2017.00023 pmid:28503145 pmcid:PMC5408094 fatcat:fdl5gim7xrbktpky6btjl6hqnu

Visual-based Positioning and Pose Estimation [article]

Somnuk Phon-Amnuaisuk, Ken T. Murata, La-Or Kovavisaruch, Tiong-Hoo Lim, Praphan Pavarangkoon, Takamichi Mizuhara
2022 arXiv   pre-print
Recent advances in deep learning and computer vision offer an excellent opportunity to investigate high-level visual analysis tasks such as human localization and human pose estimation.  ...  The results showed that the Visual-based Positioning and Pose Estimation could deliver position and pose estimations with good spatial and temporal resolutions.  ...  We would also like to thank anonymous reviewers for their constructive comments and suggestions.  ... 
arXiv:2204.09232v1 fatcat:of4f3d5ljff5pkbx4bfe5hr4ae

Video Analysis for Human Behavior Understanding

Jenq-Neng Hwang, Changick Kim, Hsu-Yung Cheng
2010 EURASIP Journal on Advances in Signal Processing  
, which are organized and ordered according to three broadly categorized topics: (1) human object detection, segmentation, and tracking; (2) human body modeling and action recognition; (3) crowd estimation  ...  To overcome these challenges, not only the traditional image processing, computer vision, pattern recognition, and machine learning techniques are required, but also advanced estimation theory and statistical  ...  A simulated annealed mechanism is utilized to infer the maximum posteriori distributions of joint positions. The two-stage approach demonstrates improvement on 3D pose estimation accuracy.  ... 
doi:10.1155/2010/402912 fatcat:tlz4nhdoojgizoqcfvzdii3cpu

Fast parametric viewpoint estimation for active object detection

Robert Eidenberger, Thilo Grundmann, Wendelin Feiten, Raoul Zoellner
2008 2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems  
Most current solutions to active perception planning struggle with complex state representations or fast and efficient sensor parameter selection strategies.  ...  This paper presents an exclusively parametric approach for the state estimation and decision making process to achieve very low computational complexity and short calculation times.  ...  In [2] an appearance-based approach to active object recognition is proposed.  ... 
doi:10.1109/mfi.2008.4648083 dblp:conf/mfi/EidenbergerGFZ08 fatcat:tjage7sifngzvdnosiuuodgzom

Analysis of the hands in egocentric vision: A survey [article]

Andrea Bandini, José Zariffa
2020 arXiv   pre-print
; and application (e.g., systems that used egocentric hand cues for solving a specific problem). Moreover, a list of the most prominent datasets with hand-based annotations is provided.  ...  This intrinsic advantage enables the study of the hands from multiple perspectives: localizing hands and their parts within the images; understanding what actions and activities the hands are involved  ...  The authors would also like to thank Gustavo Balbinot, Guijin Li, and Mehdy Dousty for the helpful discussions and feedback.  ... 
arXiv:1912.10867v2 fatcat:rd2cu3jbkvbvnii5s7fh5c2ncq

The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and Detection

Mihai Zanfir, Marius Leordeanu, Cristian Sminchisescu
2013 2013 IEEE International Conference on Computer Vision  
In this paper we propose a fast, simple, yet powerful non-parametric Moving Pose (MP) framework for low-latency human action and activity recognition.  ...  Central to our methodology is a moving pose descriptor that considers both pose information as well as differential quantities (speed and acceleration) of the human body joints within a short time window  ...  Since our goal is to design a fast, low-latency classification method, we will rely on only a few frames for efficient recognition.  ... 
doi:10.1109/iccv.2013.342 dblp:conf/iccv/ZanfirLS13 fatcat:ptsczli4zndgtjxmn2sjdqaioe

A Review on Video-Based Human Activity Recognition

Shian-Ru Ke, Hoang Thuc, Yong-Jin Lee, Jenq-Neng Hwang, Jang-Hee Yoo, Kyoung-Ho Choi
2013 Computers  
Three aspects for human activity recognition are addressed including core technology, human activity recognition systems, and applications from low-level to high-level representation.  ...  In the human activity recognition systems, three main types are mentioned, including single person activity recognition, multiple people interaction and crowd behavior, and abnormal activity recognition  ...  To be invariant to the speed of the activity, a sequenced-based voting approach is designed for the activity recognition. The computation of the indexing approach is comparatively low.  ... 
doi:10.3390/computers2020088 fatcat:zb3wlmwjjvbfne2ck6uyjtffdq

A Survey on Model Based Approaches for 2D and 3D Visual Human Pose Recovery

Xavier Perez-Sala, Sergio Escalera, Cecilio Angulo, Jordi Gonzàlez
2014 Sensors  
In this paper, we define a general taxonomy to group model based approaches for Human Pose Recovery, which is composed of five main modules: appearance, viewpoint, spatial relations, temporal consistence  ...  Several approaches have been reported, and significant improvements have been obtained in both data representation and model design.  ...  Author Contributions All authors contributed extensively to the work presented in this paper and wrote the manuscript.  ... 
doi:10.3390/s140304189 pmid:24594613 pmcid:PMC4003939 fatcat:m37lzyl5tne6jgu3aurjz6stiy

Discriminative learning of visual words for 3D human pose estimation

Huazhong Ning, Wei Xu, Yihong Gong, Thomas Huang
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
Our approach also achieves fast computational speed thanks to the integral histograms used in APC descriptor extraction and fast inference of pose regressors.  ...  This paper addresses the problem of recovering 3D human pose from a single monocular image, using a discriminative bag-of-words approach.  ...  Government VACE program, and in part by a Grant from NEC Laboratories America, Inc., USA.  ... 
doi:10.1109/cvpr.2008.4587534 dblp:conf/cvpr/NingXGH08 fatcat:irwxmqs3gzds7i6vr4jvw4og5y

Interactive activity recognition using pose-based spatio–temporal relation features and four-level Pachinko Allocation Model

Thien Huynh-The, Ba-Vui Le, Sungyoung Lee, Yongik Yoon
2016 Information Sciences  
We propose a novel approach that permits to deeply understand complex personperson activities based on the knowledge coming from human pose analysis.  ...  The joint coordinates of interactive objects are first located by an efficient human pose estimation algorithm.  ...  The pose of individual human object are good enough for single action recognition; however, for interaction recognition, the relations between two objects have to be exploited due to the pose similarity  ... 
doi:10.1016/j.ins.2016.06.016 fatcat:xaesiv7qivdy7la53h2qmukk54

Context and observation driven latent variable model for human pose estimation

Abhinav Gupta, Trista Chen, Francine Chen, Don Kimber, Larry S. Davis
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative.  ...  We then present an approach to use information from scene/objects to provide context for human pose estimation for such parameterized actions.  ...  Acknowledgement The authors would like to thank FXPAL for supporting the research described in the paper. Most of the work has been done while the first author was visiting FXPAL. This  ... 
doi:10.1109/cvpr.2008.4587511 dblp:conf/cvpr/GuptaCCKD08 fatcat:no7czbsnxjgmbeju7qbyyxyo4y

Silhouette-based object phenotype recognition using 3D shape priors

Yu Chen, Tae-Kyun Kim, Roberto Cipolla
2011 2011 International Conference on Computer Vision  
Our approach combines both generative and discriminative learning. We use latent probabilistic generative models to capture 3D shape and pose variations from a set of 3D mesh models.  ...  This paper tackles the novel challenging problem of 3D object phenotype recognition from a single 2D silhouette.  ...  [3] tackled more general deformable object categories. The shape and pose generators need only a small number of latent variables to estimate, yet are able to capture complex 3D object shapes.  ... 
doi:10.1109/iccv.2011.6126221 dblp:conf/iccv/ChenKC11 fatcat:nzy53ierw5flrmqa3fuj2m2sca

An Efficient Face Tracker Using Active Shape Model

S. K. Murugaraja, K Balamurali
2014 IOSR Journal of Computer Engineering  
The Active Shape Model is used to recover the shape of the face and then find the face after comparing the faces.  ...  The GLF feature is a global feature and does not depend on a specific face model, and thus is effective in tracking low-resolution faces.  ...  POSE-ROBUST ALBEDO ESTIMATION FROM A SINGLE IMAGE We present a stochastic filtering approach to perform albedo estimation from a single non-frontal face image.  ... 
doi:10.9790/0661-16259196 fatcat:pjn6vjcxjbcvrbqnyot4ovezxu
« Previous Showing results 1 — 15 out of 36,209 results