My Previous Research on Object Segmentation amp; Recognition我对目标分割与识别的研究；.pptVIP

What is Tensor? Definition of Mode-k Product Definition of Mode-k Flattening Data Representation in Dimensionality Reduction Why Represent Objects as Tensors instead of Vectors? Natural Representation Gray-level Images (2D structure) Videos (3D structure) Gabor-filtered Images (3D structure) Enhance Learnability in Real Application Curse of Dimensionality (Gabor-filtered image: 100*100*40 - Vector: 400,000) Small sample size problem (less than 5,000 images in common face databases) Reduce Computation Cost Concurrent Subspace Analysis as an Example(Criterion: Optimal Reconstruction) Tensorization - New Research Direction Our Extensions: 1) Supervised Learning with Rank-(R1, R2,… Rn) Decomposition (DATER): CVPR 2005 and T-IP 2007 2) Supervised Learning with Rank-1 Decomposition and Adaptive Margin (RPAM): CVPR 2006 and T-SMC-B (To appear) 3) Application in Human Gait Recognition (CSA-2+DATER-2): T-CSVT 2006 D. Tao, S. Maybank, et al.’s Extensions : 1)Incremental Learning with Tensor Representation: ACM SIGKDD 2006 2)Tensorized SVM and Minimax Probability Machines: ICDM 2005 G. Dai and D. Yeung’s Extensions: Tensorized NPE (Neighborhood Preserving Embedding), LPP (Locality Preserving Projections) and LDE (Local Discriminant Embedding): AAAI 2006 Graph Embedding Framework Graph Embedding Framework-Continued Tensorization A General Framework for Dimensionality Reduction New Dimensionality Reduction Algorithm: Marginal Fisher Analysis Motivations-Continued Classification Accuracy * * * 2 Element Rearrangement for Tensor based Subspace Learning * Dong XU School of Computer Engineering Nanyang Technological University Tensors are arrays of numbers which transform in certain ways under coordinate transformations. Vector Matrix 3rd-order Tensor Notation: Product for two Matrices Original Matrix