2,957 Hits in 7.5 sec

Sparsity Based Locality-Sensitive Discriminative Dictionary Learning for Video Semantic Analysis

Ben-Bright Benuwa, Yongzhao Zhan, Benjamin Ghansah, Ernest K. Ansah, Andriana Sarkodie
2018 Mathematical Problems in Engineering  
In video semantic analysis (VSA), the local structure of video data contains more vital discriminative information needed for classification.  ...  In the proposed algorithm, a discriminant loss function for the category based on sparse coding of the sparse coefficients is introduced into structure of locality-sensitive dictionary learning (LSDL)  ...  More recently, there has been an advancement in sparse dictionary learning for video semantic as proposed in [2] , a video semantic detection method based on locality-sensitive discriminant sparse representation  ... 
doi:10.1155/2018/9312563 fatcat:qnrsbiwnxjdffcj3g5kkcvpxhe

An Efficient Method for Automatic Video Annotation and Retrieval in Visual Sensor Networks

Jiangfan Feng, Wenwen Zhou
2014 International Journal of Distributed Sensor Networks  
Although it has been studied extensively, semantic representation of visual information is not well understood.  ...  To address the problem of pattern classification in video annotation, this paper proposes a discriminative constraint to find a solution to approach the sparse representative coefficients with discrimination  ...  Diversify Video Key Frame Representation Based on Local Structure Constraint Sparse Coding .  ... 
doi:10.1155/2014/832512 fatcat:lqr3p4ca45fp3ijry2l6mc5m5q

Scalable Mobile Video Retrieval with Sparse Projection Learning and Pseudo Label Mining

Guan-Long Wu, Yin-Hsi Kuo, Tzu-Hsuan Chiu, Winston H. Hsu, Lexing Xie
2013 IEEE Multimedia  
In addition, we propose a novel sparse projection method to address the efficiency challenge. It learns a discriminative compact representation that drastically reduces transmission cost.  ...  The average query time on 100K videos consumes only 0.592 seconds. Index Terms hashing, sparsity, mobile video retrieval, explicit semantic analysis !  ...  Our implementation is based on Python and the distance calculation functions of L2 and hamming distances are optimized by Cython to achieve competitive performance with Native C implementation.  ... 
doi:10.1109/mmul.2013.13 fatcat:p7lstaewyvb7nanycftda7vtlq

The heterogeneous feature selection with structural sparsity for multimedia annotation and hashing: a survey

Fei Wu, Yahong Han, Xiang Liu, Jian Shao, Yueting Zhuang, Zhongfei Zhang
2012 International Journal of Multimedia Information Retrieval  
Therefore, the selection of limited discriminative features for certain semantics is hence crucial to make the understanding of multimedia more interpretable.  ...  However, the obtained features are often over-complete to describe certain semantics.  ...  [15] extended PDA to sparse discriminant analysis (SDA).  ... 
doi:10.1007/s13735-012-0001-9 fatcat:4ihorofn6zbg3mzqnifihgcydm

Image classification based on sparse coding multi-scale spatial latent semantic analysis

Tao He
2019 EURASIP Journal on Image and Video Processing  
semantic analysis.  ...  The proposed multi-scale spatial latent semantic analysis method based on sparse coding has higher average classification accuracy than many existing methods, which verifies its effectiveness and robustness  ...  Therefore, if discriminant analysis can be added to the sparse coding model to enhance the discriminant of image sparse vector representation, it will play a great role in improving the performance of  ... 
doi:10.1186/s13640-019-0425-8 fatcat:l5fkcmptdbfj5byirj33xz7vke

Representations of Keypoint-Based Semantic Concept Detection: A Comprehensive Study

Yu-Gang Jiang, Jun Yang, Chong-Wah Ngo, A.G. Hauptmann
2010 IEEE transactions on multimedia  
Based on the local keypoints extracted as salient image patches, an image can be described as a "bag-of-visualwords (BoW)" and this representation has appeared promising for object and scene classification  ...  Based on our empirical findings, we further apply our method to detect a large set of 374 semantic concepts.  ...  In [4] , Nowak et al. studied the sampling strategies of BoW to compare dense (grid-based local image patches) and sparse (keypoints) representation.  ... 
doi:10.1109/tmm.2009.2036235 fatcat:z5d2cdc7mbe5na6p7bmsj5xtii

Towards optimal bag-of-features for object categorization and semantic video retrieval

Yu-Gang Jiang, Chong-Wah Ngo, Jun Yang
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
Bag-of-features (BoF) deriving from local keypoints has recently appeared promising for object and scene classification.  ...  The factors include the choices of detector, kernel, vocabulary size and weighting scheme.  ...  In [17] , Nowak et al. studied the sampling strategies of BoF to contrast dense (local patches) and sparse (keypoints) representation.  ... 
doi:10.1145/1282280.1282352 dblp:conf/civr/JiangNY07 fatcat:ww26ir6h5ng7nfxcfbnvqilhbu

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Pareto Discriminant Analysis Fetter, Richard Increasing Depth Resolution of Electron Microscopy of Neural Circuits using Sparse Tomographic Reconstruction Feulner, Johannes Lymph Node Detection  ...  Analysis Based on High Dimensional Clustering Liu, Beyang Single Image Depth Estimation From Predicted Semantic Labels Liu, Ce Exploring Features in a Bayesian Framework for Material Recognition  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Face Recognition in the Scrambled Domain via Salience-Aware Ensembles of Many Kernels

Richard Jiang, Somaya Al-Maadeed, Ahmed Bouridane, Danny Crookes, M. Emre Celebi
2016 IEEE Transactions on Information Forensics and Security  
While chaotic pattern recognition is still a challenging task, in this paper we propose a new ensemble approach -Many-Kernel Random Discriminant Analysis (MK-RDA) to discover discriminative patterns from  ...  With the rapid development of internet-of-things (IoT), face scrambling has been proposed for privacy protection during IoT-targeted image/video distribution.  ...  After we obtain the many kernel based representation κi k , we can then apply discriminant analysis over each kernel subspace and find For a set of training data and its kernel representation {κi k },  ... 
doi:10.1109/tifs.2016.2555792 fatcat:d2gkr67vszebjb3xntnqr2dtge

Visual Cue Cluster Construction via Information Bottleneck Principle and Kernel Density Estimation [chapter]

Winston H. Hsu, Shih-Fu Chang
2005 Lecture Notes in Computer Science  
and used for discriminative classification of semantic labels.  ...  The proposed VC 3 framework is general and effective, leading to exciting potential in solving other problems of semantic video analysis.  ...  This material is based upon work funded in whole by the U.S. Government.  ... 
doi:10.1007/11526346_12 fatcat:zki76rdqmzaypdul5ebm6wgnhe

MoWLD: a robust motion image descriptor for violence detection

Tao Zhang, Wenjing Jia, Baoqing Yang, Jie Yang, Xiangjian He, Zhonglong Zheng
2015 Multimedia tools and applications  
In order to obtain more discriminative features, we adopt the sparse coding and max pooling scheme to further process the selected MoWLDs.  ...  Automatic violence detection from video is a hot topic for many video surveillance applications.  ...  However, the common Gaussian kernel density estimator [6] lacks local adaptivity, and this often results in a higher sensitivity to outliers.  ... 
doi:10.1007/s11042-015-3133-0 fatcat:y3vswnv2bnfwbibt4kbijsp3gi

Group sparse representation for image categorization and semantic video retrieval

YaNan Liu, Fei Wu, YueTing Zhuang
2011 Science China Information Sciences  
Experiments In this section, we evaluate the performance of the proposed group sparse representation based on "bagof-SIFT-words" for image categorization and semantic video retrieval.  ...  By conducting experiments on these above datasets, we expect to obtain a more comprehensive study on the bag-of-SIFT-word-based group sparse representation for image categorization and video semantic retrieval  ... 
doi:10.1007/s11432-011-4344-2 fatcat:rx7vdz76fnbkvmzpxpj67vuata

Table of Contents

2021 IEEE transactions on multimedia  
Cen, and Z.He Image/Video/Graphics Analysis and Synthesis Prominent Local Representation for Dynamic Textures Based on High-Order Gaussian-Gradients . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Budagavi Sparse Multimedia Signal Processing Patch Based Video Summarization With Block Sparse Representation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/tmm.2021.3132246 fatcat:el7u2udtybddrpbl5gxkvfricy

Sparse Ensemble Learning for Concept Detection

Sheng Tang, Yan-Tao Zheng, Yu Wang, Tat-Seng Chua
2012 IEEE transactions on multimedia  
This work presents a novel sparse ensemble learning scheme for concept detection in videos.  ...  More importantly, the sparse NMF ensures that an exemplar is projected to only a few bases (localities) with non-zero coefficients.  ...  In contrast to holistic representations of principal component analysis and vector quantization, NMF can learn partsbased representations like parts of faces and semantic features of text [51] due to  ... 
doi:10.1109/tmm.2011.2168198 fatcat:yg5dvk75qvgilgsxvdrslblguu

High-level event recognition in unconstrained videos

Yu-Gang Jiang, Subhabrata Bhattacharya, Shih-Fu Chang, Mubarak Shah
2012 International Journal of Multimedia Information Retrieval  
While the existing solutions vary, we identify common key modules and provide detailed descriptions along with some insights for each of them, including extraction and representation of low-level features  ...  In this paper, we review current technologies for complex event recognition in unconstrained videos.  ...  Local features A video frame can be represented efficiently using a set of discriminative local features extracted from it.  ... 
doi:10.1007/s13735-012-0024-2 fatcat:mfzttic3svb4tho2xb6aczgp4y
« Previous Showing results 1 — 15 out of 2,957 results