5,831 Hits in 9.0 sec

Full body image feature representations for gender profiling

Matthew Collins, Jianguo Zhang, Paul Miller, Hongbin Wang
2009 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops  
We first investigate a number of state-of-the-art image representations with regard to their suitability for gender profiling from static body images.  ...  Additionally, to the best of our knowledge, currently there is no publicly available dataset for full body gender recognition.  ...  The authors acknowledge funding from the Department for Employment and Learning Northern Ireland (DEL), the Queen's University Belfast Research Support Package D8203EEC, and from EPSRC grant EP/E028640  ... 
doi:10.1109/iccvw.2009.5457467 dblp:conf/iccvw/CollinsZMW09 fatcat:jveaeb6e7vg33gled2ejv36h7q

Real-time Full-body Visual Traits Recognition from Image Sequences [article]

Christoph Jung, Reimar Tausch, Christian Wojek
2010 International Symposium on Vision, Modeling, and Visualization  
state-of-the-art accuracy for single images.  ...  Few systems have recently applied recognition on low resolution full-body images, which shows lower performance than the facial regions but already can deliver classification results even if no face is  ...  After the gradients are extracted the image is divided by a grid into connected cells of fixed size (8 × 8 pixels was found to be optimal for people detection on 64 × 128 pixel full-body windows).  ... 
doi:10.2312/pe/vmv/vmv10/057-064 dblp:conf/vmv/JungTW10 fatcat:yxarytmyordlnjksb3xhgl45ki

Real-time full-body human gender recognition in (RGB)-D data

Timm Linder, Sven Wehner, Kai O. Arras
2015 2015 IEEE International Conference on Robotics and Automation (ICRA)  
Unlike previous work which typically considered faces or frontal body views in image data, we address the problem of recognizing gender in RGB-D data from side and back views as well.  ...  We then learn and compare several classifiers on the Kinect v2 data using a HOG baseline, two state-of-the-art deep-learning methods, and a recent tessellation-based learning approach.  ...  Thus, we adopt RGB-D and 3D data for the purpose of full-body gender recognition in this paper and make the following contributions: • We propose a novel gender recognition method based upon a depth-based  ... 
doi:10.1109/icra.2015.7139616 dblp:conf/icra/LinderWA15 fatcat:vzigg7in6jf3xarqsv33g6gyuu

Real-time full-body human attribute classification in RGB-D using a tessellation boosting approach

Timm Linder, Kai O. Arras
2015 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
In this paper, we address the problem of recognizing such attributes in RGB-D data from varying full-body views.  ...  Experiments on a multi-perspective RGB-D dataset with full-body views of over a hundred different persons show that the method is able to robustly recognize multiple attributes across different view directions  ...  In this paper, we extend our previous work on full-body human gender recognition in RGB-D data [1] for the task of more generally recognizing human attributes.  ... 
doi:10.1109/iros.2015.7353541 dblp:conf/iros/LinderA15 fatcat:di6fyyzlorcmzbefdkuznwx7c4

A survey of vision-based methods for action representation, segmentation and recognition

Daniel Weinland, Remi Ronfard, Edmond Boyer
2011 Computer Vision and Image Understanding  
We concentrate on approaches that aim on classification of full-body motions, such as kicking, punching, waving, etc. and we categorize them according to how they represent the spatial and temporal structure  ...  The purpose of this survey is to give an overview and categorization of the approaches used.  ...  , upper-body gestures, full-body gestures, etc.); the selected image features (interest points, landmarks, edges, optical flow, etc.); the class of statistical models used for learning and recognition  ... 
doi:10.1016/j.cviu.2010.10.002 fatcat:v5ivlriknrf3dauermcbnw7rga

Semantic Pyramids for Gender and Action Recognition

Fahad Shahbaz Khan, Joost van de Weijer, Rao Muhammad Anwer, Michael Felsberg, Carlo Gatta
2014 IEEE Transactions on Image Processing  
Most state-of-the-art approaches for gender and action recognition rely on the description of a single body part such as face or full-body.  ...  Our approach is fully automatic and based on combining information from full-body, upper-body and face regions for gender and action recognition in still images.  ...  ACKNOWLEDGEMENTS This work has been supported by SSF through a grant for the project CUAS, by VR through a grant for the project ETT, through the Strategic Area for ICT research ELLIIT, CADICS and The  ... 
doi:10.1109/tip.2014.2331759 pmid:24956369 fatcat:rst6ftnt7ndopkxhfw575uocxi

Real-Time Human Recognition at Night via Integrated Face and Gait Recognition Technologies

Samah A. F. Manssor, Shaoyuan Sun, Mohammed A. M. Elhassan
2021 Sensors  
the images for human recognition.  ...  Human recognition technology is a task that determines the people existing in images with the purpose of identifying them.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21134323 pmid:34202659 fatcat:rc3hvvakgzejpip3wo6i5nphfe

Human Attribute Recognition— A Comprehensive Survey

Ehsan Yaghoubi, Farhad Khezeli, Diana Borza, SV Aruna Kumar, João Neves, Hugo Proença
2020 Applied Sciences  
evaluation metrics used in the HAR context.  ...  HAR's main challenges; (2) we provide a comprehensive discussion over the publicly available datasets for the development and evaluation of novel HAR approaches; (3) we outline the applications and typical  ...  On the other hand, in manipulation works, face images are modified (e.g., glasses are removed or added) using generative models. • Full-body Attribute Recognition (FAR).  ... 
doi:10.3390/app10165608 fatcat:yrzjf2v73fabbagqfyxfuhzfla


Mehshan Ahad, COMSATS University, Islamabad, Pakistan, Muhammad Fayyaz
2021 Azerbaijan Journal of High Performance Computing  
After that, images are divided into two halves on the ratio of 2:3 to acquire sets of upper body and lower body.  ...  The exciting area is separated in the first step, which is the full body from the images.  ...  Gender Recognition dependent on static body features can perform distinguishing identification.  ... 
doi:10.32010/26166127.2021. fatcat:4aw5jpremrcrtb26y6srratyke

Using a Rotating 3D LiDAR on a Mobile Robot for Estimation of Person's Body Angle and Gender

Dražen Brščić, Rhys Wyn Evans, Matthias Rehm, Takayuki Kanda
2020 Sensors  
In particular, we tested the estimation of the person's body orientation and their gender.  ...  We studied the use of a rotating multi-layer 3D Light Detection And Ranging (LiDAR) sensor (specifically the Velodyne HDL-32E) mounted on a social robot for the estimation of features of people around  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s20143964 pmid:32708707 pmcid:PMC7411808 fatcat:2joqvharrnauppghwgh2yfllgm

Vision-based Human Gender Recognition: A Survey [article]

Choon Boon Ng, Yong Haur Tay, Bok Min Goi
2012 arXiv   pre-print
Based on the results, good performance have been achieved for datasets captured under controlled environments, but there is still much work that can be done to improve the robustness of gender recognition  ...  Gender is an important demographic attribute of people. This paper provides a survey of human gender recognition in computer vision.  ...  Gender Recognition by Body Here, we refer to the use of the static human body (either partially or as a whole) in an image to infer gender, as opposed to using the face region only.  ... 
arXiv:1204.1611v1 fatcat:qoanqj7tkjfrjlf3blw3wh4p54

Survey on Video Analysis of Human Walking Motion

S. Nissi Paul, Y. Jayanta Singh
2014 International Journal of Signal Processing, Image Processing and Pattern Recognition  
In computer vision related applications, video analysis of human walking motion is currently one of the most active research topics.  ...  This paper presents a survey of different methodologies used for human walking motion analysis, approaches used for human detection or segmentation, various tracking methods, approaches for pose estimation  ...  applications refer to the task of full body motion capture without the need of markers or any specialist suits.  ... 
doi:10.14257/ijsip.2014.7.3.10 fatcat:fr7h75fowraffnbo4v3gt7v45e

Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond [article]

Krishna Kumar Singh, Hao Yu, Aron Sarmasi, Gautam Pradeep, Yong Jae Lee
2018 arXiv   pre-print
We perform extensive experiments to showcase the advantage of Hide-and-Seek on these various visual recognition problems.  ...  However, Hide-and-Seek is not tied only to the image localization task, and can generalize to other forms of visual input like videos, as well as other recognition tasks like image classification, temporal  ...  ACKNOWLEDGMENTS We thank Alyosha Efros, Jitendra Malik, and Abhinav Gupta for helpful discussions.  ... 
arXiv:1811.02545v1 fatcat:5tfquqbggvacxnvoogun5mop4u

Eye tracker as an implied social presence: awareness of being eye-tracked induces social-norm-based looking behaviour [article]

Hoo Keat Wong, Ian D. Stephen
2019 Journal of Eye Movement Research  
This study examines the impact of awareness of being eye-tracked on eye movement behaviour in a laboratory setting.  ...  (who believed they were being eye-tracked), whereas informed participants fixated longer on the mouth and shorter on the eyes of female models than misinformed participants did.  ...  Acknowledgements The authors are grateful to all the participants who took part in this experiment.  ... 
doi:10.16910/jemr.12.2.5 pmid:33828723 pmcid:PMC7881876 fatcat:z5m65ggnkvc2nagd27hzaq6mmm

Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction [article]

Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt, Gerard Pons-Moll
2021 arXiv   pre-print
Given sparse 3D point clouds sampled on the surface of a dressed person, we use an Implicit Part Network (IP-Net)to jointly predict the outer 3D surface of the dressed person, the and inner body surface  ...  We subsequently use correspondences to fit the body model to our inner surface and then non-rigidly deform it (under a parametric body + displacement model) to the outer surface in order to capture garment  ...  We generate the sparse point clouds by randomly sampling 5k points on our scans, which we vox- elize into a grid of size 128x128x128 for our input.  ... 
arXiv:2007.11432v2 fatcat:mtcxrvdszjc4fhfo7gztc74gqq
« Previous Showing results 1 — 15 out of 5,831 results