Filters








28,390 Hits in 4.0 sec

Learning zeroth class dictionary for human action recognition [article]

Jia-xin Cai, Xin Tang, Lifang Zhang, Guocan Feng
2016 arXiv   pre-print
In this paper, a discriminative two-phase dictionary learning framework is proposed for classifying human action by sparse shape representations, in which the first-phase dictionary is learned on the selected  ...  discriminative frames and the second-phase dictionary is built for recognition using reconstruction errors of the first-phase dictionary as input features.  ...  Sect.3 presents the zeroth class dictionary learning framework for human action recognition.  ... 
arXiv:1603.04015v3 fatcat:e5zzrvgzqnewnfaqycliwewsy4

Discriminative Hierarchical Modeling of Spatio-temporally Composable Human Activities

Ivan Lillo, Alvaro Soto, Juan Carlos Niebles
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
At the lower level, body poses are encoded in a representative but discriminative pose dictionary. At the intermediate level, encoded poses span a space where simple human actions are composed.  ...  This paper proposes a framework for recognizing complex human activities in videos.  ...  In particular, rather than first learning a dictionary of body poses and then learning classifiers for actions and activities, our goal is to learn all relevant parameters simultaneously using a multiclass  ... 
doi:10.1109/cvpr.2014.109 dblp:conf/cvpr/LilloSN14 fatcat:cfzy2qanefd3bndh46fht3pbaa

A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets

Ivan Lillo, Juan Carlos Niebles, Alvaro Soto
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we introduce a new hierarchical model for human action recognition using body joint locations.  ...  That is, for each atomic action, the model generates temporal action annotations by estimating its starting and ending times, as well as, spatial annotations by inferring the human body parts that are  ...  Acknowledgements This work was partially funded by the FONDECYT grant 1151018, from CONICYT, Government of Chile; and by the Stanford AI Lab-Toyota Center for Artificial Intelligence Research.  ... 
doi:10.1109/cvpr.2016.218 dblp:conf/cvpr/LilloNS16 fatcat:lffts7ptevbulkolgp56m3mkh4

A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets [article]

Ivan Lillo, Juan Carlos Niebles, Alvaro Soto
2016 arXiv   pre-print
In this paper, we introduce a new hierarchical model for human action recognition using body joint locations.  ...  its robustness to common pose estimation errors.  ...  Acknowledgements This work was partially funded by the FONDECYT grant 1151018, from CONICYT, Government of Chile; and by the Stanford AI Lab-Toyota Center for Artificial Intelligence Research.  ... 
arXiv:1606.04992v1 fatcat:ho7z6hu52zclzgbyv2mj5hdtqa

Indian Classical Dance classification by learning dance pose bases

Soumitra Samanta, Pulak Purkait, Bhabatosh Chanda
2012 2012 IEEE Workshop on the Applications of Computer Vision (WACV)  
The pose basis is learned using an on-line dictionary learning technique. Finally each video is represented sparsely as a dance descriptor by pooling pose descriptor of all the frames.  ...  To deal with this problem, we use a sparse representation based dictionary learning technique.  ...  The table establishes that the proposed descriptor is suitable for general human action recognition task.  ... 
doi:10.1109/wacv.2012.6163050 dblp:conf/wacv/SamantaPC12 fatcat:wismnp6iv5arncdj5doyoyqeju

Recognizing interaction between human performers using 'key pose doublet'

Snehasis Mukherjee, Sujoy Kumar Biswas, Dipti Prasad Mukherjee
2011 Proceedings of the 19th ACM international conference on Multimedia - MM '11  
In this paper, we propose a graph theoretic approach for recognizing interactions between two human performers present in a video clip.  ...  From an initial dictionary of poses (visual words), we extract key poses (or key words) by ranking the poses on the centrality measure of graph connectivity.  ...  We construct the interaction descriptors (as action descriptors in [9] ) from the dictionary of 'key pose doublets' Ψ for recognition.  ... 
doi:10.1145/2072298.2072006 dblp:conf/mm/MukherjeeBM11 fatcat:ye4a3xsytfczpf5a2foi6n545i

Learning sparse representations for view-independent human action recognition based on fuzzy distances

Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas
2013 Neurocomputing  
In this paper, a method aiming at view-independent human action recognition is presented. Actions are described as series of successive human body poses.  ...  The performance of the proposed human action recognition method is evaluated on two publicly available action recognition databases aiming at different application scenarios.  ...  Acknowledgment The research leading to these results has received funding from the Collaborative European Project MOBISERV FP7-248434 (http://www.mobiserv.eu), An Integrated Intelligent Home Environment for  ... 
doi:10.1016/j.neucom.2013.05.021 fatcat:cpe3wyzirnb3zfjpcozaogpsca

A heterogeneous dictionary model for representation and recognition of human actions

Rushil Anirudh, Karthikeyan Ramamurthy, Jayaraman J. Thiagarajan, Pavan Turaga, Andreas Spanias
2013 2013 IEEE International Conference on Acoustics, Speech and Signal Processing  
When compared to centered clustering approaches such as K-means, we show that the proposed dictionary is a better generative model for human actions.  ...  In this paper, we consider low-dimensional and sparse representation models for human actions, that are consistent with how actions evolve in high-dimensional feature spaces.  ...  Most human actions evolve over time where they usually begin with a rest pose and end in an extreme pose. This transition is smooth resulting in smoothly varying features.  ... 
doi:10.1109/icassp.2013.6638303 dblp:conf/icassp/AnirudhRTTS13 fatcat:ory2pra5qfdwzcanyro6mockzi

Improving bag-of-poses with semi-temporal pose descriptors for skeleton-based action recognition

Saeid Agahian, Farhood Negin, Cemal Köse
2018 The Visual Computer  
Improving bag-of-poses with semi-temporal pose descriptors for skeleton-based action recognition.  ...  Keywords Skeleton-based · 3D action recognition · bag-of-words · key poses · Extreme learning machine · RGB-D  ...  .: Learning features combination for human action recognition from skeleton sequences. Pattern Recognition Letters (2017) 39.  ... 
doi:10.1007/s00371-018-1489-7 fatcat:k2oraunzfzdihfcx4uuoqtz67e

Multi-attributed Dictionary Learning for Sparse Coding

Chen-Kuo Chiang, Te-Feng Su, Chih Yen, Shang-Hong Lai
2013 2013 IEEE International Conference on Computer Vision  
We present a multi-attributed dictionary learning algorithm for sparse coding.  ...  We have demonstrated our algorithm on action classification and face recognition tasks on several publicly available datasets.  ...  Experimental Results We apply the proposed Multi-Attributed Dictionary Learning (MADL) to the task of action recognition and face recognition in our experiments.  ... 
doi:10.1109/iccv.2013.145 dblp:conf/iccv/ChiangSYL13 fatcat:i53ofar575gofloy4wdmwpno34

3D Action Recognition from Novel Viewpoints

Hossein Rahmani, Ajmal Mian
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
While learning the CNN model, we do not use action labels but only the pose labels after clustering all training poses into k clusters.  ...  For spatio-temporal representation, we propose group sparse Fourier Temporal Pyramid which robustly encodes the action specific most discriminative output features of the proposed human pose model.  ...  Acknowledgment We thank the authors of [9, 15, 27, 34, 54, 58, 67] for making their codes publicly available. We thank NVIDIA for their K40 GPU donation.  ... 
doi:10.1109/cvpr.2016.167 dblp:conf/cvpr/RahmaniM16 fatcat:zjhym2yw4jgsblnxu7hjy7b6g4

Action Recognition in Realistic Sports Videos [chapter]

Khurram Soomro, Amir R. Zamir
2014 Advances in Computer Vision and Pattern Recognition  
To provide further details about the existing action recognition methods in this area, we decompose the action recognition framework into three main steps of feature extraction, dictionary learning to  ...  the human actions in a realistic environment.  ...  The majority of existing frameworks for action recognition consist of three main steps: feature extraction, dictionary learning to form a representation for a video based on the extracted features, and  ... 
doi:10.1007/978-3-319-09396-3_9 fatcat:q5kjcsnp2zb7fo5j4wwkjel5re

Discriminative poses for early recognition in multi-camera networks

Scott Spurlock, Junjie Shan, Richard Souvenir
2015 Proceedings of the 9th International Conference on Distributed Smart Camera - ICDSC '15  
We present a framework for early action recognition in a multi-camera network. Our approach balances recognition accuracy with speed by dynamically selecting the best camera for classification.  ...  We follow an iterative clustering approach to learn sets of keyposes that are discriminative for recognition as well as for predicting the best camera for classification of future frames.  ...  INTRODUCTION For human action recognition, certain poses are highly predictive for particular actions. Methods based on this observation have been applied in the single-camera setting [9, 14] .  ... 
doi:10.1145/2789116.2789117 dblp:conf/icdsc/SpurlockSS15 fatcat:corea7ypkvfqzdqtiont44wpx4

Moving Poselets: A Discriminative and Interpretable Skeletal Motion Representation for Action Recognition

Lingling Tao, Rene Vidal
2015 2015 IEEE International Conference on Computer Vision Workshop (ICCVW)  
In contrast, our goal is to develop a principled feature learning framework to learn discriminative and interpretable skeletal motion patterns for action recognition.  ...  Given a video or time series of skeleton data, action recognition systems perform classification using cues such as motion, appearance, and pose.  ...  In [14] , each action is modeled by a sequence of latent poses, where the pose dictionary and action/activity classifiers are jointly learned via Latent Structural SVM [28] .  ... 
doi:10.1109/iccvw.2015.48 dblp:conf/iccvw/TaoV15 fatcat:yn3x4gi2xrejjngbiv2qx5afbu

Guest Editor's Introduction to the Special Issue on Domain Adaptation for Vision Applications

Dong Xu, Rama Chellappa, Trevor Darrell, Hal Daumé III
2014 International Journal of Computer Vision  
Acknowledgments We would like to thank all of the authors for submitting their excellent works and all the reviewers for their invaluable and timely evaluations. We are also grateful to Ms.  ...  Cordelia Schmid for their guidance and support during the entire process of developing this special issue.  ...  This work achieves the state-of-the-art performances for 3D head and 3D human pose estimation.  ... 
doi:10.1007/s11263-014-0730-8 fatcat:xzr7c7fly5bptjqjiuvm5hf3ai
« Previous Showing results 1 — 15 out of 28,390 results