738 Hits in 8.6 sec

Multi-task Sparse Learning with Beta Process Prior for Action Recognition

Chunfeng Yuan, Weiming Hu, Guodong Tian, Shuang Yang, Haoran Wang
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper, we formulate human action recognition as a novel Multi-Task Sparse Learning(MTSL) framework which aims to construct a test sample with multiple features from as few bases as possible.  ...  Experimental results on the KTH and UCF sports datasets demonstrate the effectiveness of the proposed MTSL approach for action recognition.  ...  In this paper, motivated by the success of multi-task learning, we propose a novel Multi-Task Sparse Learning(MTSL) model combined with Beta Process Prior for human action recognition.  ... 
doi:10.1109/cvpr.2013.61 dblp:conf/cvpr/YuanHTYW13 fatcat:khyvhcfntrbdvnwgf7b4muhava

Structure-Preserving Sparse Decomposition for Facial Expression Analysis

Sima Taheri, Qiang Qiu, Rama Chellappa
2014 IEEE Transactions on Image Processing  
Since domain experts' knowledge may not always be available for constructing an AU-dictionary, we also propose a structure-preserving dictionary learning algorithm which we use to learn a structured dictionary  ...  We use the computed sparse code matrix for each expressive face to perform expression decomposition and recognition.  ...  The proposed algorithm can be generalized to recognition of human actions provided we have a good definition for human action units.  ... 
doi:10.1109/tip.2014.2331141 pmid:24956366 fatcat:nkkq62qd2fftzdl4xlvypenrl4

Sparse Code Filtering for Action Pattern Mining [chapter]

Wei Wang, Yan Yan, Liqiang Nie, Luming Zhang, Stefan Winkler, Nicu Sebe
2017 Lecture Notes in Computer Science  
In this paper, we tackle the multi-view action recognition problem by proposing a sparse code filtering (SCF) framework which can mine the action patterns.  ...  The experimental results on several public multi-view action recognition datasets demonstrate that the presented SCF framework outperforms other state-of-the-art methods.  ...  Results Multi-view Action Recognition. For the multi-view setting, we use the standard two-thirds and one-third split for training and testing.  ... 
doi:10.1007/978-3-319-54184-6_1 fatcat:p5jfcrxlhzfjdpthg3csew6jry

Multimodal Multipart Learning for Action Recognition in Depth Videos [article]

Amir Shahroudy, Gang Wang, Tian-Tsong Ng, Qingxiong Yang
2015 arXiv   pre-print
The articulated and complex nature of human actions makes the task of action recognition difficult.  ...  sparsity between them, in favor of a group feature selection.  ...  [23] used mixed norms as structured sparsity regularizers for heterogeneous feature fusion, and [24] extended this idea for a multi-view clustering.  ... 
arXiv:1507.08761v1 fatcat:3c2ifw37c5h2jaanwx4lix3ajy

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Levin, Anat Linear View Synthesis Using a Dimensionality Gap Light Field Prior Li, Baoxin Discriminative K-SVD for Dictionary Learning in Face Recognition YouTubeCat: Learning to Categorize Wild  ...  Automatic Image Annotation Using Group Sparsity Li, Jianguo Bundled Depth-Map Merging for Multi-View Stereo Li, Jun Workshop: Boosting Dense SIFT Descriptors and Shape Contexts of Face Images  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Learning View-Invariant Sparse Representations for Cross-View Action Recognition

Jingjing Zheng, Zhuolin Jiang
2013 2013 IEEE International Conference on Computer Vision  
We present an approach to jointly learn a set of viewspecific dictionaries and a common dictionary for crossview action recognition.  ...  Extensive experiments using the multi-view IXMAS dataset demonstrate that our approach outperforms many recent approaches for cross-view action recognition.  ...  Experiments We evaluated our approach for both cross-view and multi-view action recognition on the IXMAS multi-view dataset [28] .  ... 
doi:10.1109/iccv.2013.394 dblp:conf/iccv/ZhengJ13 fatcat:v74m6wjzl5da7ncabsk3icepsa

Action Recognition Based on Multi-scale Oriented Neighborhood Features

Jiangfeng Yang, Zheng Ma, Mei Xie
2015 International Journal of Signal Processing, Image Processing and Pattern Recognition  
Human action recognition usually consists of three stages: extracting local features from video sequences, learning action representation vectors via these local features, and classifying query action  ...  For reducing quantization error caused by K-means and VQ, soft vector quantization (SVQ) [20] and sparse coding (SC) [21] are proposed to encode local features for action recognition tasks [18] .  ...  Then learning an action model from the final behavior representations and recognizing query behaviors with the learnt model.  ... 
doi:10.14257/ijsip.2015.8.1.21 fatcat:r4d2lsyl4zdtlaw5jrhign22la

Local structure preserving sparse coding for infrared target recognition

Jing Han, Jiang Yue, Yi Zhang, Lianfa Bai, Zhao Zhang
2017 PLoS ONE  
enough local sparse structures to learn a sufficient sparse structure dictionary of a target class.  ...  We incorporate sparsity into a template matching concept to construct a local sparse structure matching (LSSM) model for general infrared target recognition.  ...  Expand the simple template set by scaling and rotating every image and its mirror in the template set (Fig 3(A) ), we can learn the dictionary of interested targets with multi-scale and multi-rotation  ... 
doi:10.1371/journal.pone.0173613 pmid:28323824 pmcid:PMC5360252 fatcat:fdl5vmflgvckbowzfzoysuwamu

Learning Dictionary of Discriminative Part Detectors for Image Categorization and Cosegmentation

Jian Sun, Jean Ponce
2016 International Journal of Computer Vision  
We use a latent SVM model regularized by l 1,2 group sparsity to learn the discriminative part detectors.  ...  This paper proposes a novel approach to learning mid-level image models for image categorization and cosegmentation.  ...  Figure 9 shows examples of cosegmentation results. 8C ONCLUSION In this work, we have proposed a novel latent SVMs with group sparsity to learn discriminative part detectors for image recognition.  ... 
doi:10.1007/s11263-016-0899-0 fatcat:65fpa3yifngfbgeqwtcvvideme

Dynamic Spatio-Temporal Bag of Expressions (D-STBoE) Model for Human Action Recognition

Saima Nazir, Muhammad Haroon Yousaf, Jean-Christophe Nebel, Sergio A. Velastin
2019 Sensors  
Human action recognition (HAR) has emerged as a core research domain for video understanding and analysis, thus attracting many researchers.  ...  Furthermore, we train a multi-class Support Vector Machine (SVM) for classifying bag of expressions into action classes.  ...  Action Recognition Since we use a multi-class support vector machine model for action recognition, we need to select both a kernel function and a multi-class model.  ... 
doi:10.3390/s19122790 fatcat:37k7ahzbyrcq5f6e3chtnllrcm

Hierarchically Learned View-Invariant Representations for Cross-View Action Recognition

Yang Liu, Zhaoyang Lu, Jing Li, Tao Yang
2018 IEEE transactions on circuits and systems for video technology (Print)  
Recognizing human actions from varied views is challenging due to huge appearance variations in different views.  ...  Therefore, the finally learned feature representation is view-invariant and robust for substantial distribution difference across views even the view difference is large.  ...  This illustrates that JSRDA can learn robust and discriminative view-invariant representations for multi-view action recognition even with large view difference.  ... 
doi:10.1109/tcsvt.2018.2868123 fatcat:pqk7unx2vzbjpaimtkh4rt3uta

Sparse Coding for Classification via Discrimination Ensemble

Yuhui Quan, Yong Xu, Yuping Sun, Yan Huang, Hui Ji
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Discriminative sparse coding has emerged as a promising technique in image analysis and recognition, which couples the process of classifier training and the process of dictionary learning for improving  ...  In this paper, we proposed a discriminative sparse coding method which jointly learns a dictionary for sparse coding and an ensemble classifier for discrimination.  ...  Then group sparsity is imposed on the grouped sparse codes, e.g. [10, 12] . The resultant structured sparse codes are more discriminative for classification than the purely sparse ones.  ... 
doi:10.1109/cvpr.2016.629 dblp:conf/cvpr/QuanXSHJ16 fatcat:sprjp5nm5bchnlo6z2nmav4mvi

View-Invariant Feature Representation for Action Recognition under Multiple Views

Kumbala Reddy, Tirumala Engineering College, Gullipalli Naidu, Bulusu Vardhan, JB Institute of Engineering and Technology, Jawaharlal Nehru Technological University College of Engineering
2019 International Journal of Intelligent Engineering and Systems  
The proposed method is validated over the standard multi-view IXMAS dataset and experimental results confirm that the proposed method outperforms the conventional approaches with respect to Recognition  ...  To enhance the performance of Multi-view Action Recognition, we propose a novel Feature extraction and Feature Selection mechanism that allows building a mutual relationship between the actions sequences  ...  [15] proposed a new 'multi-view discriminative and structured dictionary learning with group sparsity and graph model (GM-GS-DSDL)' for MVHAR based on the fusion of features obtained in multiple views  ... 
doi:10.22266/ijies2019.1231.01 fatcat:m55dl7jgmngm3iwd2klv6u2v2y

Sparse Modeling of Human Actions from Motion Imagery

Alexey Castrodad, Guillermo Sapiro
2012 International Journal of Computer Vision  
Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently  ...  Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining  ...  Hermina for very helpful suggestions and insightful discussions. We also thank Dr.  ... 
doi:10.1007/s11263-012-0534-7 fatcat:us2ujbp56bhqjfbfv235jsb6xa

Particle PHD Filter Based Multiple Human Tracking Using Online Group-Structured Dictionary Learning

Zeyu Fu, Pengming Feng, Federico Angelini, Jonathon Chambers, Syed Mohsen Naqvi
2018 IEEE Access  
In addition, online group-structured dictionary learning with a maximum voting method is used to robustly estimate the target birth intensity.  ...  The proposed system mainly exploits two concepts: a novel adaptive gating technique and an online group-structured dictionary learning strategy.  ...  The residual measurements are further processed via proposed online group-structured dictionary learning which includes dictionary construction based on training data, multi-task group-structured sparsity  ... 
doi:10.1109/access.2018.2816805 fatcat:u7juboqk2bggvfd5w7k6p5meqa
« Previous Showing results 1 — 15 out of 738 results