Filters








11,666 Hits in 4.5 sec

Retrieval-based face annotation by weak label regularized local coordinate coding

Dayong Wang, Steven C.H. Hoi, Ying He, Jianke Zhu
2011 Proceedings of the 19th ACM international conference on Multimedia - MM '11  
In particular, we propose an effective Weak Label Regularized Local Coordinate Coding (WLRLCC) technique, which exploits the local coordinate coding principle in learning sparse features, and meanwhile  ...  Retrieval-based face annotation is a promising paradigm in mining massive web facial images for automated face annotation. Such an annotation paradigm usually encounters two key challenges.  ...  Problem Formulation Sparse Features via Local Coordinate Coding Sparse representation has been successfully applied in many applications, e.g., face recognition [35] , graph construction [29] , and  ... 
doi:10.1145/2072298.2072345 dblp:conf/mm/WangHHZ11 fatcat:w2edfatosba3zlwdjalj4uzjve

Label to region by bi-layer sparsity priors

Xiaobai Liu, Bin Cheng, Shuicheng Yan, Jinhui Tang, Tat Seng Chua, Hai Jin
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
The underlying philosophy of bi-layer sparse coding is that an image or semantic region can be sparsely reconstructed via the atomic image patches belonging to the images with common labels, while the  ...  Besides, the presenting bi-layer sparse coding framework can be naturally applied to perform image annotation on new test images.  ...  DIRECT IMAGE ANNOTATION BY BI-LAYER SPARSE CODING In this section, we show how the proposed bi-layer sparse coding formulation can be used for direct image annotation on new test images by propagating  ... 
doi:10.1145/1631272.1631291 dblp:conf/mm/LiuCYTCJ09 fatcat:skfkxthcsnf5pnybijejfvycva

Joint dictionary learning and topic modeling for image clustering

Lingbo Li, Mingyuan Zhou, Eric Wang, Lawrence Carin
2011 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
The model is applied to cluster multiple images, and a subset of the images may be annotated. Example results are presented on the MNIST digit data and on the Microsoft MSRC multi-scene image data.  ...  INTRODUCTION There has been much recent interest in developing statistical models for automatic clustering and annotation of images, based on local image features as well as available meta-data such as  ...  Recent advances in image classification show that substantially improved performance may be achieved by extracting features from local descriptors with dictionary learning and sparse coding, this replacing  ... 
doi:10.1109/icassp.2011.5946757 dblp:conf/icassp/LiZWC11 fatcat:bhgtwjbqczalpp7dua6t4diouy

Regression based automatic face annotation for deformable model building

Akshay Asthana, Simon Lucey, Roland Goecke
2011 Pattern Recognition  
We propose a regression-based approach for automatic annotation of face images at arbitrary pose and expression, and for deformable model building using only the annotated frontal images.  ...  We show the generalisability of the proposed approach by automatically annotating the face images from four different databases and verifying the results by comparing them with a ground truth obtained  ...  In [4] , the problem of automatic annotation and model building is recast as an energy-minimising image coding problem.  ... 
doi:10.1016/j.patcog.2011.03.014 fatcat:bxhbuddbozdbbdktd3qsz4iv2e

Multi-label sparse coding for automatic image annotation

Changhu Wang, Shuicheng Yan, Lei Zhang, Hong-Jiang Zhang
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper, we present a multi-label sparse coding framework for feature extraction and classification within the context of automatic image annotation.  ...  Extensive image annotation experiments on the Corel5k and Corel30k databases both show the superior performance of the proposed multi-label sparse coding framework over the state-of-the-art algorithms.  ...  Multi-Label Sparse Coding Framework In this section, we introduce the multi-label sparse coding framework for automatic image annotation.  ... 
doi:10.1109/cvprw.2009.5206866 fatcat:ljzpfckhqvaz7c334feddwet6y

Multi-label sparse coding for automatic image annotation

Changhu Wang, Shuicheng Yan, Lei Zhang, Hong-Jiang Zhang
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper, we present a multi-label sparse coding framework for feature extraction and classification within the context of automatic image annotation.  ...  Extensive image annotation experiments on the Corel5k and Corel30k databases both show the superior performance of the proposed multi-label sparse coding framework over the state-of-the-art algorithms.  ...  Multi-Label Sparse Coding Framework In this section, we introduce the multi-label sparse coding framework for automatic image annotation.  ... 
doi:10.1109/cvpr.2009.5206866 dblp:conf/cvpr/WangYZZ09 fatcat:25hi7qqbcvahpai4dewokfwydu

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Fast Sparse Representation with Prototypes Huang, Junzhou Automatic Image Annotation Using Group Sparsity Huang, Kaiqi Visual Tracking via Incremental Self-tuning Particle Filtering on the Affine Group  ...  Cross-Dataset Action Detection Locality-constrained Linear Coding for Image Classification Spatialized Epitome and Its Applications Supervised Translation-Invariant Sparse Coding Workshop: A Robust Framework  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Stochastic Coordinate Coding and Its Application for Drosophila Gene Expression Pattern Annotation [article]

Binbin Lin, Qingyang Li, Qian Sun, Ming-Jun Lai, Ian Davidson, Wei Fan, Jieping Ye
2014 arXiv   pre-print
The proposed algorithm alternatively updates the sparse codes via just a few steps of coordinate descent and updates the dictionary via second order stochastic gradient descent.  ...  Previous studies have demonstrated that sparse coding is effective for extracting features from gene expression images.  ...  Invariance to local distortions is required for an accurate annotation system. Several prior works on the automatic annotation of Drosophila gene expression images have been reported.  ... 
arXiv:1407.8147v2 fatcat:cn6i27z43zfbdgin5dbhvujm4e

Fine-grained object recognition in underwater visual data

C. Spampinato, S. Palazzo, P. H. Joalland, S. Paris, H. Glotin, K. Blanc, D. Lingrand, F. Precioso
2015 Multimedia tools and applications  
The resulting annotated dataset, containing over one million annotations (AA-1M), was then manually checked by removing false positives as well as images with occlusions between fish or showing partially  ...  We first describe a new annotated dataset of about 35,000 fish images (MA-35K dataset), derived from the Fish4Knowledge project, covering 10 fish species from the Eastern Indo-Pacific bio-geographic zone  ...  scheme based on MB-LTP robust to illumination/color variation transformations to a finegrained analysis via Fisher vectors and sparse coding trained on SIFT local features.  ... 
doi:10.1007/s11042-015-2601-x fatcat:hxf2xw6thzagfnrlti3qibfufq

Scalable Visual Instance Mining with Instance Graph

Wei Li, Changhu Wang, Lei Zhang, Yong Rui, Bo Zhang
2015 Procedings of the British Machine Vision Conference 2015  
These methods are capable of discovering small instances via instancelevel local matches, but they do not consider the structure of connections between images.  ...  Specifically, the goal is to automatically discover frequent visual instances from a collection of images.  ...  These methods are capable of discovering small instances via instancelevel local matches, but they do not consider the structure of connections between images.  ... 
doi:10.5244/c.29.98 dblp:conf/bmvc/LiWZRZ15 fatcat:lv4dk4cdvrchted6umft5avahy

Image Retrieval using Sparse Codewords with Cryptography for Enhanced Security

Munmun N. Bhagat, Prof. B. B. Gite
2014 IOSR Journal of Computer Engineering  
Secured Quick Crypt (SQC) encryption algorithm is applied on images when they are transferred via network. This will protect image from getting attacked.  ...  In this paper, automatically detected human attributes are used to enhance the performance of content based face image retrieval.  ...  Attribute-enhanced sparse coding uses automatically detected human attributes to construct semantic code words in the offline stage.  ... 
doi:10.9790/0661-16252226 fatcat:3dbxk4jpqff33bl5hl4nfkc3du

Image-level and group-level models for Drosophila gene expression pattern annotation

Qian Sun, Sherin Muckatira, Lei Yuan, Shuiwang Ji, Stuart Newfeld, Sudhir Kumar, Jieping Ye
2013 BMC Bioinformatics  
The spatial sparse coding approach is used to represent local patches of images in comparison with the well-known bag-of-words (BoW) method.  ...  Moreover, combining sparse coding and image-level scheme leads to consistent performance improvement in keywords annotation.  ...  For the sparse coding, we use a subset of images to tune λ via cross-validation. We use average pooling for both BoW and sparse coding.  ... 
doi:10.1186/1471-2105-14-350 pmid:24299119 pmcid:PMC3924186 fatcat:43oezi32jvattcr3lgreitympu

Neural Process Reconstruction from Sparse User Scribbles [chapter]

Mike Roberts, Won-Ki Jeong, Amelio Vázquez-Reina, Markus Unger, Horst Bischof, Jeff Lichtman, Hanspeter Pfister
2011 Lecture Notes in Computer Science  
We present a novel semi-automatic method for segmenting neural processes in large, highly anisotropic EM (electron microscopy) image stacks.  ...  Our method takes advantage of sparse scribble annotations provided by the user to guide a 3D variational segmentation model, thereby allowing our method to globally optimally enforce 3D geometric constraints  ...  We also wish to thank Yongsheng Pan for providing us with the Markov Surfaces source code, and Manhee Lee for helping us to collect ground truth data.  ... 
doi:10.1007/978-3-642-23623-5_78 fatcat:jckvmjj2hnghxp2xoxvgtjdtvm

Retrieval-Based Face Annotation by Weak Label Regularized Local Coordinate Coding

Dayong Wang, Steven C. H. Hoi, Ying He, Jianke Zhu, Tao Mei, Jiebo Luo
2014 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we propose an effective Weak Label Regularized Local Coordinate Coding (WLRLCC) technique, which exploits the principle of local coordinate coding by learning sparse features, and employs  ...  Moreover, an effective sparse reconstruction scheme is developed to perform the face annotation task.  ...  Problem Formulation Sparse Features via Local Coordinate Coding Sparse representation has been successfully applied in many applications.  ... 
doi:10.1109/tpami.2013.145 pmid:24457510 fatcat:iru5qo5iybh4tfkxbac5j2ggwe

Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds

Sudheendra Vijayanarasimhan, Kristen Grauman
2014 International Journal of Computer Vision  
We present an approach for live learning of object detectors, in which the system autonomously refines its models by actively requesting crowd-sourced annotations on images crawled from the Web.  ...  on sparse coding of local features combined with a max pooling scheme.  ...  Given the name of a class of interest, our system produces a detector to localize novel instances using automatically obtained images and annotations.  ... 
doi:10.1007/s11263-014-0721-9 fatcat:czao4jerlzaxzlbero63i47nnq
« Previous Showing results 1 — 15 out of 11,666 results