�ݺ�ߣshows by User: chicagokayaker

�ݺ�ߣshows by User: chicagokayaker / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: chicagokayaker / Tue, 08 Nov 2016 17:53:46 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: chicagokayaker Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector /slideshow/lec08-feature-aggregation-ii-fisher-vector-akula-and-super-vector/68419291 lec08-161108175346
Lec-08: Feature Aggregation II: Fisher Vector, Super Vector and AKULA [notes] Fisher Vector aggregation, Supervector aggregation, and AKULA aggregation ]]>
Lec-08: Feature Aggregation II: Fisher Vector, Super Vector and AKULA [notes] Fisher Vector aggregation, Supervector aggregation, and AKULA aggregation ]]> Tue, 08 Nov 2016 17:53:46 GMT /slideshow/lec08-feature-aggregation-ii-fisher-vector-akula-and-super-vector/68419291 chicagokayaker@slideshare.net(chicagokayaker) Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector chicagokayaker Lec-08: Feature Aggregation II: Fisher Vector, Super Vector and AKULA [notes] Fisher Vector aggregation, Supervector aggregation, and AKULA aggregation <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec08-161108175346-thumbnail.jpg?width=120&height=120&fit=bounds" /> Lec-08: Feature Aggregation II: Fisher Vector, Super Vector and AKULA [notes] Fisher Vector aggregation, Supervector aggregation, and AKULA aggregation

Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector from United States Air Force Academy

]]> 2442 6 https://cdn.slidesharecdn.com/ss_thumbnails/lec08-161108175346-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Lec07 aggregation-and-retrieval-system /slideshow/lec07-aggregationandretrievalsystem/68419143 lec07-aggregation-and-retrieval-system-161108175053
Lec-07: Feature Aggregation and Image Retrieval System [notes] Image retrieval system performance metrics, precision, recall, true positive rate, false positive rate; Bag of Words (BoW) and VLAD aggregation. ]]>
Lec-07: Feature Aggregation and Image Retrieval System [notes] Image retrieval system performance metrics, precision, recall, true positive rate, false positive rate; Bag of Words (BoW) and VLAD aggregation. ]]> Tue, 08 Nov 2016 17:50:52 GMT /slideshow/lec07-aggregationandretrievalsystem/68419143 chicagokayaker@slideshare.net(chicagokayaker) Lec07 aggregation-and-retrieval-system chicagokayaker Lec-07: Feature Aggregation and Image Retrieval System [notes] Image retrieval system performance metrics, precision, recall, true positive rate, false positive rate; Bag of Words (BoW) and VLAD aggregation. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec07-aggregation-and-retrieval-system-161108175053-thumbnail.jpg?width=120&height=120&fit=bounds" /> Lec-07: Feature Aggregation and Image Retrieval System [notes] Image retrieval system performance metrics, precision, recall, true positive rate, false positive rate; Bag of Words (BoW) and VLAD aggregation.

Lec07 aggregation-and-retrieval-system from United States Air Force Academy

]]> 748 2 https://cdn.slidesharecdn.com/ss_thumbnails/lec07-aggregation-and-retrieval-system-161108175053-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Lec11 object-re-id /slideshow/lec11-objectreid/68418996 lec11-object-re-id-161108174931
Lec-11: Visual Object Re-Identification [notes] Visual object modeling via key points aggregation, aggregation indexing/hashing, object re-identification and retrieval system, performance metric ]]>
Lec-11: Visual Object Re-Identification [notes] Visual object modeling via key points aggregation, aggregation indexing/hashing, object re-identification and retrieval system, performance metric ]]> Tue, 08 Nov 2016 17:49:31 GMT /slideshow/lec11-objectreid/68418996 chicagokayaker@slideshare.net(chicagokayaker) Lec11 object-re-id chicagokayaker Lec-11: Visual Object Re-Identification [notes] Visual object modeling via key points aggregation, aggregation indexing/hashing, object re-identification and retrieval system, performance metric <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec11-object-re-id-161108174931-thumbnail.jpg?width=120&height=120&fit=bounds" /> Lec-11: Visual Object Re-Identification [notes] Visual object modeling via key points aggregation, aggregation indexing/hashing, object re-identification and retrieval system, performance metric

Lec11 object-re-id from United States Air Force Academy

]]> 395 6 https://cdn.slidesharecdn.com/ss_thumbnails/lec11-object-re-id-161108174931-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Lec12 review-part-i /slideshow/lec12-reviewparti/68418802 lec12-review-part-i-161108174831
Reviewing Part I of the Image Analysis & Retrieval class, features, aggregation, and object identification. ]]>
Reviewing Part I of the Image Analysis & Retrieval class, features, aggregation, and object identification. ]]> Tue, 08 Nov 2016 17:48:31 GMT /slideshow/lec12-reviewparti/68418802 chicagokayaker@slideshare.net(chicagokayaker) Lec12 review-part-i chicagokayaker Reviewing Part I of the Image Analysis & Retrieval class, features, aggregation, and object identification. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec12-review-part-i-161108174831-thumbnail.jpg?width=120&height=120&fit=bounds" /> Reviewing Part I of the Image Analysis & Retrieval class, features, aggregation, and object identification.

Lec12 review-part-i from United States Air Force Academy

]]> 357 8 https://cdn.slidesharecdn.com/ss_thumbnails/lec12-review-part-i-161108174831-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Lec14 eigenface and fisherface /slideshow/lec14-eigenface-and-fisherface/68418714 lec14-eigenfaceandfisherface-161108174733
Lec-14: Eigenface and Fisherface [notes] application of subspace holistic approach in face recognition, eigenface and fisherface methods. ]]>
Lec-14: Eigenface and Fisherface [notes] application of subspace holistic approach in face recognition, eigenface and fisherface methods. ]]> Tue, 08 Nov 2016 17:47:33 GMT /slideshow/lec14-eigenface-and-fisherface/68418714 chicagokayaker@slideshare.net(chicagokayaker) Lec14 eigenface and fisherface chicagokayaker Lec-14: Eigenface and Fisherface [notes] application of subspace holistic approach in face recognition, eigenface and fisherface methods. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec14-eigenfaceandfisherface-161108174733-thumbnail.jpg?width=120&height=120&fit=bounds" /> Lec-14: Eigenface and Fisherface [notes] application of subspace holistic approach in face recognition, eigenface and fisherface methods.

Lec14 eigenface and fisherface from United States Air Force Academy

]]> 1816 1 https://cdn.slidesharecdn.com/ss_thumbnails/lec14-eigenfaceandfisherface-161108174733-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Lec15 graph laplacian embedding /slideshow/lec15-graph-laplacian-embedding/68418635 lec15-graphlaplacianembedding-161108174529
Processing [notes] affinity graph preserving embedding, graph Laplacian, Laplacian Embedding, Laplacian face, graph Fourier transforms, and applications in compression and classification. ]]>
Processing [notes] affinity graph preserving embedding, graph Laplacian, Laplacian Embedding, Laplacian face, graph Fourier transforms, and applications in compression and classification. ]]> Tue, 08 Nov 2016 17:45:29 GMT /slideshow/lec15-graph-laplacian-embedding/68418635 chicagokayaker@slideshare.net(chicagokayaker) Lec15 graph laplacian embedding chicagokayaker Processing [notes] affinity graph preserving embedding, graph Laplacian, Laplacian Embedding, Laplacian face, graph Fourier transforms, and applications in compression and classification. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec15-graphlaplacianembedding-161108174529-thumbnail.jpg?width=120&height=120&fit=bounds" /> Processing [notes] affinity graph preserving embedding, graph Laplacian, Laplacian Embedding, Laplacian face, graph Fourier transforms, and applications in compression and classification.

Lec15 graph laplacian embedding from United States Air Force Academy

]]> 1256 3 https://cdn.slidesharecdn.com/ss_thumbnails/lec15-graphlaplacianembedding-161108174529-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Lec17 sparse signal processing & applications /slideshow/lec17-sparse-signal-processing-applications/68418520 lec17-sparsesignalprocessing-161108174335
Lec-17: Sparse Signal Processing & Applications [notes] Sparse signal processing, recovery of sparse signal via L1 minimization. Applications including face recognition, coupled dictionary learning for image super-resolution. ]]>
Lec-17: Sparse Signal Processing & Applications [notes] Sparse signal processing, recovery of sparse signal via L1 minimization. Applications including face recognition, coupled dictionary learning for image super-resolution. ]]> Tue, 08 Nov 2016 17:43:35 GMT /slideshow/lec17-sparse-signal-processing-applications/68418520 chicagokayaker@slideshare.net(chicagokayaker) Lec17 sparse signal processing & applications chicagokayaker Lec-17: Sparse Signal Processing & Applications [notes] Sparse signal processing, recovery of sparse signal via L1 minimization. Applications including face recognition, coupled dictionary learning for image super-resolution. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec17-sparsesignalprocessing-161108174335-thumbnail.jpg?width=120&height=120&fit=bounds" /> Lec-17: Sparse Signal Processing & Applications [notes] Sparse signal processing, recovery of sparse signal via L1 minimization. Applications including face recognition, coupled dictionary learning for image super-resolution.

Lec17 sparse signal processing & applications from United States Air Force Academy

]]> 1733 10 https://cdn.slidesharecdn.com/ss_thumbnails/lec17-sparsesignalprocessing-161108174335-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Lec16 subspace optimization /slideshow/lec16-subspace-optimization/68418418 lec16-subspaceoptimization-161108174215
Lec-16: Subspace/Transform Optimization Address the non-linearity issues in appearance manifolds by having a piece-wise linear solution. Query driven local model learning, subspace indexing on Grassmann manifold, direct Newtonian method of subspace optimization on Grassmann manifold. ]]>
Lec-16: Subspace/Transform Optimization Address the non-linearity issues in appearance manifolds by having a piece-wise linear solution. Query driven local model learning, subspace indexing on Grassmann manifold, direct Newtonian method of subspace optimization on Grassmann manifold. ]]> Tue, 08 Nov 2016 17:42:15 GMT /slideshow/lec16-subspace-optimization/68418418 chicagokayaker@slideshare.net(chicagokayaker) Lec16 subspace optimization chicagokayaker Lec-16: Subspace/Transform Optimization Address the non-linearity issues in appearance manifolds by having a piece-wise linear solution. Query driven local model learning, subspace indexing on Grassmann manifold, direct Newtonian method of subspace optimization on Grassmann manifold. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec16-subspaceoptimization-161108174215-thumbnail.jpg?width=120&height=120&fit=bounds" /> Lec-16: Subspace/Transform Optimization Address the non-linearity issues in appearance manifolds by having a piece-wise linear solution. Query driven local model learning, subspace indexing on Grassmann manifold, direct Newtonian method of subspace optimization on Grassmann manifold.

Lec16 subspace optimization from United States Air Force Academy

]]> 566 4 https://cdn.slidesharecdn.com/ss_thumbnails/lec16-subspaceoptimization-161108174215-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Lec11 rate distortion optimization /slideshow/lec11-rate-distortion-optimization/59794988 lec11-ratedistortionoptimization-160320211617
Rate Distortion Optimization, video coding, Lagrangian Relaxation]]>
Rate Distortion Optimization, video coding, Lagrangian Relaxation]]> Sun, 20 Mar 2016 21:16:17 GMT /slideshow/lec11-rate-distortion-optimization/59794988 chicagokayaker@slideshare.net(chicagokayaker) Lec11 rate distortion optimization chicagokayaker Rate Distortion Optimization, video coding, Lagrangian Relaxation <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec11-ratedistortionoptimization-160320211617-thumbnail.jpg?width=120&height=120&fit=bounds" /> Rate Distortion Optimization, video coding, Lagrangian Relaxation

Lec11 rate distortion optimization from United States Air Force Academy

]]> 1459 7 https://cdn.slidesharecdn.com/ss_thumbnails/lec11-ratedistortionoptimization-160320211617-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Lec-03 Entropy Coding I: Hoffmann & Golomb Codes /slideshow/lec03-entropy-coding-i-hoffmann-golomb-codes/58355212 lec03-160217035355
practical entropy coding schemes, huffman coding, golomb coding and applications.]]>
practical entropy coding schemes, huffman coding, golomb coding and applications.]]> Wed, 17 Feb 2016 03:53:55 GMT /slideshow/lec03-entropy-coding-i-hoffmann-golomb-codes/58355212 chicagokayaker@slideshare.net(chicagokayaker) Lec-03 Entropy Coding I: Hoffmann & Golomb Codes chicagokayaker practical entropy coding schemes, huffman coding, golomb coding and applications. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec03-160217035355-thumbnail.jpg?width=120&height=120&fit=bounds" /> practical entropy coding schemes, huffman coding, golomb coding and applications.

Lec-03 Entropy Coding I: Hoffmann & Golomb Codes from United States Air Force Academy

]]> 3532 6 https://cdn.slidesharecdn.com/ss_thumbnails/lec03-160217035355-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Multimedia Communication Lec02: Info Theory and Entropy /slideshow/multimedia-communication-lec02-info-theory-and-entropy/58355177 lec02-160217035135
Introduction of info theory basis for image/video coding, especially, entropy, rate-distortion theory, entropy coding, huffman coding, arithmetic coding]]>
Introduction of info theory basis for image/video coding, especially, entropy, rate-distortion theory, entropy coding, huffman coding, arithmetic coding]]> Wed, 17 Feb 2016 03:51:35 GMT /slideshow/multimedia-communication-lec02-info-theory-and-entropy/58355177 chicagokayaker@slideshare.net(chicagokayaker) Multimedia Communication Lec02: Info Theory and Entropy chicagokayaker Introduction of info theory basis for image/video coding, especially, entropy, rate-distortion theory, entropy coding, huffman coding, arithmetic coding <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec02-160217035135-thumbnail.jpg?width=120&height=120&fit=bounds" /> Introduction of info theory basis for image/video coding, especially, entropy, rate-distortion theory, entropy coding, huffman coding, arithmetic coding

Multimedia Communication Lec02: Info Theory and Entropy from United States Air Force Academy

]]> 934 8 https://cdn.slidesharecdn.com/ss_thumbnails/lec02-160217035135-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 ECE 4490 Multimedia Communication Lec01 /chicagokayaker/ece-4490-multimedia-communication-lec01 lec01-160217034945
Introduction to Multimedia Communication ]]>
Introduction to Multimedia Communication ]]> Wed, 17 Feb 2016 03:49:45 GMT /chicagokayaker/ece-4490-multimedia-communication-lec01 chicagokayaker@slideshare.net(chicagokayaker) ECE 4490 Multimedia Communication Lec01 chicagokayaker Introduction to Multimedia Communication <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lec01-160217034945-thumbnail.jpg?width=120&height=120&fit=bounds" /> Introduction to Multimedia Communication

ECE 4490 Multimedia Communication Lec01 from United States Air Force Academy

]]> 404 4 https://cdn.slidesharecdn.com/ss_thumbnails/lec01-160217034945-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Mobile Visual Search: Object Re-Identification Against Large Repositories /slideshow/mobile-visual-search-object-reidentification-against-large-repositories/57343175 mobilevisualsearch-ustc-160121201256
Invited talk at USTC and SJTU, discuss recent progress in object re-identification against very large repository, especially the problem of fast key point detection, feature repeatability prediction, aggregation, and object repository indexing and search. ]]>
Invited talk at USTC and SJTU, discuss recent progress in object re-identification against very large repository, especially the problem of fast key point detection, feature repeatability prediction, aggregation, and object repository indexing and search. ]]> Thu, 21 Jan 2016 20:12:56 GMT /slideshow/mobile-visual-search-object-reidentification-against-large-repositories/57343175 chicagokayaker@slideshare.net(chicagokayaker) Mobile Visual Search: Object Re-Identification Against Large Repositories chicagokayaker Invited talk at USTC and SJTU, discuss recent progress in object re-identification against very large repository, especially the problem of fast key point detection, feature repeatability prediction, aggregation, and object repository indexing and search. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/mobilevisualsearch-ustc-160121201256-thumbnail.jpg?width=120&height=120&fit=bounds" /> Invited talk at USTC and SJTU, discuss recent progress in object re-identification against very large repository, especially the problem of fast key point detection, feature repeatability prediction, aggregation, and object repository indexing and search.

Mobile Visual Search: Object Re-Identification Against Large Repositories from United States Air Force Academy

]]> 969 9 https://cdn.slidesharecdn.com/ss_thumbnails/mobilevisualsearch-ustc-160121201256-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Tutorial on MPEG CDVS/CDVA Standardization at ICNITS L3 Meeting /slideshow/tutorial-on-mpeg-cdvscdva-standardization-at-icnits-l3-meeting/39674667 usnb-tutorial-cdvs-v1-140929170452-phpapp01
Overview of the MPEG standardization efforts in CDVS - Compact Descriptor for Visual Search, and CDVA - Compact Descriptor for Video Analytics.]]>
Overview of the MPEG standardization efforts in CDVS - Compact Descriptor for Visual Search, and CDVA - Compact Descriptor for Video Analytics.]]> Mon, 29 Sep 2014 17:04:52 GMT /slideshow/tutorial-on-mpeg-cdvscdva-standardization-at-icnits-l3-meeting/39674667 chicagokayaker@slideshare.net(chicagokayaker) Tutorial on MPEG CDVS/CDVA Standardization at ICNITS L3 Meeting chicagokayaker Overview of the MPEG standardization efforts in CDVS - Compact Descriptor for Visual Search, and CDVA - Compact Descriptor for Video Analytics. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/usnb-tutorial-cdvs-v1-140929170452-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Overview of the MPEG standardization efforts in CDVS - Compact Descriptor for Visual Search, and CDVA - Compact Descriptor for Video Analytics.

Tutorial on MPEG CDVS/CDVA Standardization at ICNITS L3 Meeting from United States Air Force Academy

]]> 1706 4 https://cdn.slidesharecdn.com/ss_thumbnails/usnb-tutorial-cdvs-v1-140929170452-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Light Weight Fingerprinting for Video Playback Verification in MPEG DASH /slideshow/light-weight-fingerprinting-for-video-playback-verification-in-mpeg-dash/36170838 pv2013-140622173250-phpapp01
Adaptive HTTP Streaming solutions are phasing out traditional online video distribution solutions such as progressive download. MPEG DASH is an open standardized solution that has been developed to minimize solution fragmentation and to ensure quick market adoption. However, the openness of the standard loosens the grip of content providers on the client behavior and may threaten the success of the whole ecosystem. This paper proposes a content fingerprinting and verification mechanism for restricting the client’s playback behavior in such an open environment by using a very light weight Eigen thumbnail appearance differential fingerprinting. Simulation results demonstrate the effectiveness of the proposed solution. Keywords—MPEG DASH; Video Fingerprinting; Playback Verification; Eigen Appearance;]]>
Adaptive HTTP Streaming solutions are phasing out traditional online video distribution solutions such as progressive download. MPEG DASH is an open standardized solution that has been developed to minimize solution fragmentation and to ensure quick market adoption. However, the openness of the standard loosens the grip of content providers on the client behavior and may threaten the success of the whole ecosystem. This paper proposes a content fingerprinting and verification mechanism for restricting the client’s playback behavior in such an open environment by using a very light weight Eigen thumbnail appearance differential fingerprinting. Simulation results demonstrate the effectiveness of the proposed solution. Keywords—MPEG DASH; Video Fingerprinting; Playback Verification; Eigen Appearance;]]> Sun, 22 Jun 2014 17:32:50 GMT /slideshow/light-weight-fingerprinting-for-video-playback-verification-in-mpeg-dash/36170838 chicagokayaker@slideshare.net(chicagokayaker) Light Weight Fingerprinting for Video Playback Verification in MPEG DASH chicagokayaker Adaptive HTTP Streaming solutions are phasing out traditional online video distribution solutions such as progressive download. MPEG DASH is an open standardized solution that has been developed to minimize solution fragmentation and to ensure quick market adoption. However, the openness of the standard loosens the grip of content providers on the client behavior and may threaten the success of the whole ecosystem. This paper proposes a content fingerprinting and verification mechanism for restricting the client’s playback behavior in such an open environment by using a very light weight Eigen thumbnail appearance differential fingerprinting. Simulation results demonstrate the effectiveness of the proposed solution. Keywords—MPEG DASH; Video Fingerprinting; Playback Verification; Eigen Appearance; <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/pv2013-140622173250-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Adaptive HTTP Streaming solutions are phasing out traditional online video distribution solutions such as progressive download. MPEG DASH is an open standardized solution that has been developed to minimize solution fragmentation and to ensure quick market adoption. However, the openness of the standard loosens the grip of content providers on the client behavior and may threaten the success of the whole ecosystem. This paper proposes a content fingerprinting and verification mechanism for restricting the client’s playback behavior in such an open environment by using a very light weight Eigen thumbnail appearance differential fingerprinting. Simulation results demonstrate the effectiveness of the proposed solution. Keywords—MPEG DASH; Video Fingerprinting; Playback Verification; Eigen Appearance;

Light Weight Fingerprinting for Video Playback Verification in MPEG DASH from United States Air Force Academy

]]> 950 8 https://cdn.slidesharecdn.com/ss_thumbnails/pv2013-140622173250-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Subspace Indexing on Grassmannian Manifold for Large Scale Visual Identification /slideshow/subspace-indexing-on-grassmannian-manifold-for-large-scale-visual-identification/11394551 ibm-grassmann-talk-1-7-120202183218-phpapp02
In large scale visual pattern recognition applications, when the subject set is large the traditional linear models like PCA/LDA/LPP, become inadequate in capturing the non-linearity and local variations of visual appearance manifold. Kernelized solutions can alleviate the problem to certain degree, but faces a computational complexity challenge of solving eigen or QP problems of size n x n for number of training samples n. In this work, we developed a novel solution to this problem by applying a data partition first and obtain a rich set of local data patch models, then the hierarchical structure of this rich set of models are computed with subspace clustering on Grassmanian manifold, via a VQ like algorithm with data partition locality constraint. At query time, a probe image is projected to the data space partition first to obtain the probe model, and the optimal local model is computed by traversing the model hierarchical tree. Simulation results demonstrated the effectiveness of this solution in computational efficiency and recognition accuracy, with applications in large subject set face recognition and image retrieval. [Bio] Zhu Li is currently a Senior Staff Researcher and Media Analytics & Processing Group Lead with the Media Networking Lab, Core Networks Research, FutureWei (Huawei) Technology USA, at Bridgewater, New Jersey. He received his PhD in Electrical & Computer Engineering from Northwestern University, Evanston in 2004. He was an Assistant Professor with the Dept of Computing, The Hong Kong Polytechnic University from 2008 to 2010, and a Senior Research Engineer, Senior Staff Research Engineering, and then Principal Staff Research Engineer with the Multimedia Research Lab (MRL), Motorola Labs, Schaumburg, Illinois, from 2000 to 2008. His research interests include audio-visual analytics and machine learning with its application in large scale video repositories annotation, search and recommendation, as well as video adaptation, source-channel coding and distributed optimization issues of the wireless video networks. He has 21 issued or pending patents, 70+ publications in book chapters, journals, conference proceedings and standards contributions in these areas. He is an IEEE senior member, elected Vice Chair of the IEEE Multimedia Communication Technical Committee (MMTC) 2008~2010, co-editor for the Springer-Verlag book on "Intelligent Video Communication: Techniques and Applications". He served on numerous conference and workshop TPCs and was symposium co-chair at IEEE ICC'2008, and on Best Paper Award Committee for IEEE ICME 2010. He received the Best Poster Paper Award from IEEE Int'l Conf on Multimedia & Expo (ICME) at Toronto, 2006, and the Best Paper Award from IEEE Int'l Conf on Image Processing (ICIP) at San Antonio, 2007. ]]>
In large scale visual pattern recognition applications, when the subject set is large the traditional linear models like PCA/LDA/LPP, become inadequate in capturing the non-linearity and local variations of visual appearance manifold. Kernelized solutions can alleviate the problem to certain degree, but faces a computational complexity challenge of solving eigen or QP problems of size n x n for number of training samples n. In this work, we developed a novel solution to this problem by applying a data partition first and obtain a rich set of local data patch models, then the hierarchical structure of this rich set of models are computed with subspace clustering on Grassmanian manifold, via a VQ like algorithm with data partition locality constraint. At query time, a probe image is projected to the data space partition first to obtain the probe model, and the optimal local model is computed by traversing the model hierarchical tree. Simulation results demonstrated the effectiveness of this solution in computational efficiency and recognition accuracy, with applications in large subject set face recognition and image retrieval. [Bio] Zhu Li is currently a Senior Staff Researcher and Media Analytics & Processing Group Lead with the Media Networking Lab, Core Networks Research, FutureWei (Huawei) Technology USA, at Bridgewater, New Jersey. He received his PhD in Electrical & Computer Engineering from Northwestern University, Evanston in 2004. He was an Assistant Professor with the Dept of Computing, The Hong Kong Polytechnic University from 2008 to 2010, and a Senior Research Engineer, Senior Staff Research Engineering, and then Principal Staff Research Engineer with the Multimedia Research Lab (MRL), Motorola Labs, Schaumburg, Illinois, from 2000 to 2008. His research interests include audio-visual analytics and machine learning with its application in large scale video repositories annotation, search and recommendation, as well as video adaptation, source-channel coding and distributed optimization issues of the wireless video networks. He has 21 issued or pending patents, 70+ publications in book chapters, journals, conference proceedings and standards contributions in these areas. He is an IEEE senior member, elected Vice Chair of the IEEE Multimedia Communication Technical Committee (MMTC) 2008~2010, co-editor for the Springer-Verlag book on "Intelligent Video Communication: Techniques and Applications". He served on numerous conference and workshop TPCs and was symposium co-chair at IEEE ICC'2008, and on Best Paper Award Committee for IEEE ICME 2010. He received the Best Poster Paper Award from IEEE Int'l Conf on Multimedia & Expo (ICME) at Toronto, 2006, and the Best Paper Award from IEEE Int'l Conf on Image Processing (ICIP) at San Antonio, 2007. ]]> Thu, 02 Feb 2012 18:32:15 GMT /slideshow/subspace-indexing-on-grassmannian-manifold-for-large-scale-visual-identification/11394551 chicagokayaker@slideshare.net(chicagokayaker) Subspace Indexing on Grassmannian Manifold for Large Scale Visual Identification chicagokayaker In large scale visual pattern recognition applications, when the subject set is large the traditional linear models like PCA/LDA/LPP, become inadequate in capturing the non-linearity and local variations of visual appearance manifold. Kernelized solutions can alleviate the problem to certain degree, but faces a computational complexity challenge of solving eigen or QP problems of size n x n for number of training samples n. In this work, we developed a novel solution to this problem by applying a data partition first and obtain a rich set of local data patch models, then the hierarchical structure of this rich set of models are computed with subspace clustering on Grassmanian manifold, via a VQ like algorithm with data partition locality constraint. At query time, a probe image is projected to the data space partition first to obtain the probe model, and the optimal local model is computed by traversing the model hierarchical tree. Simulation results demonstrated the effectiveness of this solution in computational efficiency and recognition accuracy, with applications in large subject set face recognition and image retrieval. [Bio] Zhu Li is currently a Senior Staff Researcher and Media Analytics & Processing Group Lead with the Media Networking Lab, Core Networks Research, FutureWei (Huawei) Technology USA, at Bridgewater, New Jersey. He received his PhD in Electrical & Computer Engineering from Northwestern University, Evanston in 2004. He was an Assistant Professor with the Dept of Computing, The Hong Kong Polytechnic University from 2008 to 2010, and a Senior Research Engineer, Senior Staff Research Engineering, and then Principal Staff Research Engineer with the Multimedia Research Lab (MRL), Motorola Labs, Schaumburg, Illinois, from 2000 to 2008. His research interests include audio-visual analytics and machine learning with its application in large scale video repositories annotation, search and recommendation, as well as video adaptation, source-channel coding and distributed optimization issues of the wireless video networks. He has 21 issued or pending patents, 70+ publications in book chapters, journals, conference proceedings and standards contributions in these areas. He is an IEEE senior member, elected Vice Chair of the IEEE Multimedia Communication Technical Committee (MMTC) 2008~2010, co-editor for the Springer-Verlag book on "Intelligent Video Communication: Techniques and Applications". He served on numerous conference and workshop TPCs and was symposium co-chair at IEEE ICC'2008, and on Best Paper Award Committee for IEEE ICME 2010. He received the Best Poster Paper Award from IEEE Int'l Conf on Multimedia & Expo (ICME) at Toronto, 2006, and the Best Paper Award from IEEE Int'l Conf on Image Processing (ICIP) at San Antonio, 2007. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ibm-grassmann-talk-1-7-120202183218-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /> In large scale visual pattern recognition applications, when the subject set is large the traditional linear models like PCA/LDA/LPP, become inadequate in capturing the non-linearity and local variations of visual appearance manifold. Kernelized solutions can alleviate the problem to certain degree, but faces a computational complexity challenge of solving eigen or QP problems of size n x n for number of training samples n. In this work, we developed a novel solution to this problem by applying a data partition first and obtain a rich set of local data patch models, then the hierarchical structure of this rich set of models are computed with subspace clustering on Grassmanian manifold, via a VQ like algorithm with data partition locality constraint. At query time, a probe image is projected to the data space partition first to obtain the probe model, and the optimal local model is computed by traversing the model hierarchical tree. Simulation results demonstrated the effectiveness of this solution in computational efficiency and recognition accuracy, with applications in large subject set face recognition and image retrieval. [Bio] Zhu Li is currently a Senior Staff Researcher and Media Analytics & Processing Group Lead with the Media Networking Lab, Core Networks Research, FutureWei (Huawei) Technology USA, at Bridgewater, New Jersey. He received his PhD in Electrical & Computer Engineering from Northwestern University, Evanston in 2004. He was an Assistant Professor with the Dept of Computing, The Hong Kong Polytechnic University from 2008 to 2010, and a Senior Research Engineer, Senior Staff Research Engineering, and then Principal Staff Research Engineer with the Multimedia Research Lab (MRL), Motorola Labs, Schaumburg, Illinois, from 2000 to 2008. His research interests include audio-visual analytics and machine learning with its application in large scale video repositories annotation, search and recommendation, as well as video adaptation, source-channel coding and distributed optimization issues of the wireless video networks. He has 21 issued or pending patents, 70+ publications in book chapters, journals, conference proceedings and standards contributions in these areas. He is an IEEE senior member, elected Vice Chair of the IEEE Multimedia Communication Technical Committee (MMTC) 2008~2010, co-editor for the Springer-Verlag book on "Intelligent Video Communication: Techniques and Applications". He served on numerous conference and workshop TPCs and was symposium co-chair at IEEE ICC'2008, and on Best Paper Award Committee for IEEE ICME 2010. He received the Best Poster Paper Award from IEEE Int'l Conf on Multimedia & Expo (ICME) at Toronto, 2006, and the Best Paper Award from IEEE Int'l Conf on Image Processing (ICIP) at San Antonio, 2007.

Subspace Indexing on Grassmannian Manifold for Large Scale Visual Identification from United States Air Force Academy

]]> 2270 7 https://cdn.slidesharecdn.com/ss_thumbnails/ibm-grassmann-talk-1-7-120202183218-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplicate Detection and Localization /slideshow/scaled-eigen-appearance-and-likelihood-prunning-for-large-scale-video-duplicate-detection-and-localization/11260467 likelihood-prunning-v1-5-120125155204-phpapp02
]]>
]]> Wed, 25 Jan 2012 15:52:02 GMT /slideshow/scaled-eigen-appearance-and-likelihood-prunning-for-large-scale-video-duplicate-detection-and-localization/11260467 chicagokayaker@slideshare.net(chicagokayaker) Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplicate Detection and Localization chicagokayaker <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/likelihood-prunning-v1-5-120125155204-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" />

Scaled Eigen Appearance and Likelihood Prunning for Large Scale Video Duplicate Detection and Localization from United States Air Force Academy

]]> 344 2 https://cdn.slidesharecdn.com/ss_thumbnails/likelihood-prunning-v1-5-120125155204-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://cdn.slidesharecdn.com/profile-photo-chicagokayaker-48x48.jpg?cb=1594527986 Experienced researcher in Multimedia Computing and Communication with proven track record in leading research effort, attracting external funding, generating IPR, and delivering algorithm and solutions with business impact. Specialties: Image/Video Analytics, MPEG Visual Descriptor Standardization, Large Scale Visual Repository Search and Recommendation, Machine Learning, Optimization; Video Adaptation, Wireless Video Networking. l.web.umkc.edu/lizhu https://cdn.slidesharecdn.com/ss_thumbnails/lec08-161108175346-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/lec08-feature-aggregation-ii-fisher-vector-akula-and-super-vector/68419291 Lec-08 Feature Aggrega... https://cdn.slidesharecdn.com/ss_thumbnails/lec07-aggregation-and-retrieval-system-161108175053-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/lec07-aggregationandretrievalsystem/68419143 Lec07 aggregation-and-... https://cdn.slidesharecdn.com/ss_thumbnails/lec11-object-re-id-161108174931-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/lec11-objectreid/68418996 Lec11 object-re-id