Filters








15,296 Hits in 7.1 sec

Viewpoint-invariant learning and detection of human heads

M. Weber, W. Einhauser, M. Welling, P. Perona
Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580)  
We present a method to learn models of human heads for the purpose of detection from different viewing angles.  ...  We address here the problem of detecting human heads in clutter idependently of their orientation around the vertical axis.  ...  The main source of hope comes from observing the human visual system; it can detect reliably and quickly human heads in clutter: independently of scale, viewpoint, in a large variety of lighting conditions  ... 
doi:10.1109/afgr.2000.840607 dblp:conf/fgr/WeberEWP00 fatcat:qn45shquyrb2xf4uhroytkx77e

Towards Viewpoint Invariant 3D Human Pose Estimation [article]

Albert Haque, Boya Peng, Zelun Luo, Alexandre Alahi, Serena Yeung, Li Fei-Fei
2016 arXiv   pre-print
We propose a viewpoint invariant model for 3D human pose estimation from a single depth image.  ...  To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space.  ...  Learned Viewpoint Invariant Embedding. We embed the input into a learned, viewpoint invariant feature space (see Figure 3 ).  ... 
arXiv:1603.07076v3 fatcat:hxe6advhrng2vavbx22o6ieriu

Towards Viewpoint Invariant 3D Human Pose Estimation [chapter]

Albert Haque, Boya Peng, Zelun Luo, Alexandre Alahi, Serena Yeung, Li Fei-Fei
2016 Lecture Notes in Computer Science  
We propose a viewpoint invariant model for 3D human pose estimation from a single depth image.  ...  To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space.  ...  We gratefully acknowledge the Clinical Excellence Research Center (CERC) at Stanford Medicine and thank the Office of Naval Research, Multidisciplinary University Research Initiatives Program (ONR MURI  ... 
doi:10.1007/978-3-319-46448-0_10 fatcat:4jmebq4en5bp3haajxlkxhq5vq

Detecting and Localizing 3D Object Classes using Viewpoint Invariant Reference Frames

Matthew Toews, Tal Arbel
2007 2007 IEEE 11th International Conference on Computer Vision  
In this paper, we investigate detection and localization of general 3D object classes by relating local scale-invariant features to a viewpoint invariant reference frame.  ...  Modeling and detection based on the optimal reference frame improves detection performance for both multiview and viewpoint invariant representations.  ...  from rear views of a head).  ... 
doi:10.1109/iccv.2007.4408832 dblp:conf/iccv/ToewsA07 fatcat:si4cwyi24bfhpjoltdr45bnuwu

A bottom-up, view-point invariant human detector

Nicolas Thome, Sebastien Ambellouis
2008 Pattern Recognition (ICPR), Proceedings of the International Conference on  
Heads, limbs and torsos are individually detected, and an efficient assembly strategy is used to perform the human detection and the part segmentation.  ...  We propose a bottom-up human detector that can deal with arbitrary poses and viewpoints.  ...  Therefore, and it is not clear how well the method will generalize for detecting humans in arbitrary poses and viewpoints. The work of Ren et. al. [8] is the most relevant to us.  ... 
doi:10.1109/icpr.2008.4761596 dblp:conf/icpr/ThomeA08 fatcat:aamp6icf3ve5lpkm32afi4via4

Detection, Localization, and Sex Classification of Faces from Arbitrary Viewpoints and under Occlusion

M. Toews, T. Arbel
2009 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper presents a novel framework for detecting, localizing, and classifying faces in terms of visual traits, e.g., sex or age, from arbitrary viewpoints and in the presence of occlusion.  ...  All three tasks are embedded in a general viewpoint-invariant model of object class appearance derived from local scale-invariant features, where features are probabilistically quantified in terms of their  ...  Viewpoint-Invariant Detection and Localization Before visual traits can be learned or classified, the image features reflective of traits must first be detected and localized (i.e., associated with specific  ... 
doi:10.1109/tpami.2008.233 pmid:19574619 fatcat:nl2hmpuly5crzbrh2bozzs7e2u

Human action recognition using an ensemble of body-part detectors

Bhaskar Chakraborty, Andrew D. Bagdanov, Jordi Gonzàlez, Xavier Roca
2011 Expert systems  
Three example-based body part detectors are trained to detect three components of the human body: the head, the legs and the arms.  ...  Grouping of these detections is then performed using a simple geometric constraint model which yields a viewpoint invariant human detector.  ...  Here detection of profile head and leg is shown.  ... 
doi:10.1111/j.1468-0394.2011.00610.x fatcat:x6ermka5pve2tih3syfoilz2fm

Mining discriminative 3D Poselet for cross-view action recognition

Jiang Wang, Xiaohan Nie, Yin Xia, Ying Wu
2014 IEEE Winter Conference on Applications of Computer Vision  
In this representation, an action is characterized by the spatio-temporal configuration of 3D Poselets, which are discriminatively discovered with a novel Poselet mining algorithm and can be detected with  ...  The Kinect skeleton is employed to facilitate the 3D Poselet mining and 3D Poselet detectors learning, but the recognition is solely based on 2D video input.  ...  For each 3D Poselet, we learn a view-invariant 3D Poselet detectors.  ... 
doi:10.1109/wacv.2014.6836043 dblp:conf/wacv/WangNXW14 fatcat:ctfx36irfvapnkn7v2mmfewca4

Viewpoint-Aware Action Recognition using Skeleton-Based Features from Still Images

Seong-heum Kim, Donghyeon Cho
2021 Electronics  
Second, we extract 2D/3D joints using state-of-the-art convolutional neural networks and analyze the geometric relationships of the joints for computing 2D and 3D skeleton features.  ...  The robustness of the proposed method to viewpoint changes was quantitatively confirmed using two multi-view datasets.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/electronics10091118 fatcat:gita5i46nves7jvkyrkcdz6hlu

View Invariance for Human Action Recognition

Vasu Parameswaran, Rama Chellappa
2006 International Journal of Computer Vision  
This paper presents an approach for viewpoint invariant human action recognition, an area that has received scant attention so far, relative to the overall body of work in human action recognition.  ...  We exploit these techniques and model actions in terms of view-invariant canonical body poses and trajectories in 2D invariance space, leading to a simple and effective way to represent and recognize human  ...  Rao et al. (2002) consider the problem of learning and recognizing actions performed by a human hand.  ... 
doi:10.1007/s11263-005-3671-4 fatcat:p6ib5hhsynbrpckps3am27nx4m

Fast Multi-aspect 2D Human Detection [chapter]

Tai-Peng Tian, Stan Sclaroff
2010 Lecture Notes in Computer Science  
We address the problem of detecting human figures in images, taking into account that the image of the human figure may be taken from a range of viewpoints.  ...  We demonstrate the effectiveness of the new model for the human parsing problem using the Iterative Parsing data set and results are competitive with the state of the art detection algorithm of Andriluka  ...  Furthermore, we are interested in recovering the pose of the human figure, where the pose is described by the position and orientation of the legs, arms, torso, and head.  ... 
doi:10.1007/978-3-642-15558-1_33 fatcat:cd2se2gerzcllhgwuvlf3o3u6i

Head pose estimation using multilinear subspace analysis for robot human awareness

Tonislav Ivanov, Larry Matthies, M. Alex O. Vasilescu
2009 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops  
We demonstrate a pipeline of on-the-move detection of pedestrians with a robot stereo vision system, segmentation of the head, and head pose estimation in cluttered urban street scenes.  ...  Mobile robots, operating in unconstrained indoor and outdoor environments, would benefit in many ways from perception of the human awareness around them.  ...  We can determine head pose of unknown people in unconstrained environment.  ... 
doi:10.1109/iccvw.2009.5457694 dblp:conf/iccvw/IvanovMV09 fatcat:sgew4rjmyrhizgstxxgwbskrje

Soft biometric trait classification from real-world face videos conditioned on head pose estimation

Meltem Demirkus, Doina Precup, James J. Clark, Tal Arbel
2012 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
set of frames and features to use in a temporal fusion scheme for soft biometric trait classification.  ...  Experiments performed on large, real-world video sequences show that our head pose estimator outperforms the current state-of-the-art head pose approaches (by up to 51%), whereas our head pose conditioned  ...  The approach by Toews and Arbel [30] created a viewpoint-invariant appearance model for face detection purpose. The model used local invariant features, i.e.  ... 
doi:10.1109/cvprw.2012.6239227 dblp:conf/cvpr/DemirkusPCA12 fatcat:vfuvxbv6qjffnnph5mirnan6mu

View-invariant human-body detection with extension to human action recognition using component-wise HMM of body parts

Bhaskar Chakraborty, Ognjen Rudovic, Jordi Gonzalez
2008 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition  
We incorporate 10 sub-classifiers for the head, arms and the leg detection. Each sub-classifier detects body parts under a specific range of viewpoints.  ...  To achieve this goal we detect the human in its body parts and then learn the changes of those body parts for action recognition.  ...  Jordi Gonzàlez also acknowledges the support of a Juan de la Cierva Postdoctoral fellowship from the Spanish MEC.  ... 
doi:10.1109/afgr.2008.4813302 dblp:conf/fgr/ChakrabortyRG08 fatcat:hzk4ivovjjavxjuym5bdwewktm

Temporal Contiguity Training Influences Behavioral and Neural Measures of Viewpoint Tolerance

Chayenne Van Meel, Hans P. Op de Beeck
2018 Frontiers in Human Neuroscience  
Participants saw training sequences of face images creating the appearance of a rotating head.  ...  Humans can often recognize faces across viewpoints despite the large changes in lowlevel image properties a shift in viewpoint introduces.  ...  viewpoint-invariant than shape features.  ... 
doi:10.3389/fnhum.2018.00013 pmid:29441006 pmcid:PMC5797614 fatcat:tth6mmrcwrhxvmy2ixcdw6ogq4
« Previous Showing results 1 — 15 out of 15,296 results