P e o p l e A very sparse semantical vector for frame: - PowerPoint PPT Presentation

Jan 09, 2024 •399 likes •634 views

Time Frame Baby Cake People P e o p l e A very sparse semantical vector for frame: Emphasize primary object Vector sparser Overlook small size regional object Vocabulary larger max pooling Only around 40% of Regional Discriminatory power

Time Frame Baby Cake People P e o p l e
A very sparse semantical vector for frame: Emphasize primary object Vector sparser Overlook small size regional object Vocabulary larger
max pooling Only around 40% of Regional Discriminatory power of deep features Information left consistently improves
-Framework-1 -Framework-2
Frame Candidate Objects Selective search On average, each frame has 20 candidate object regions.
Observations - Possible reasons: -Alternative method :
VLAD
Spatial & temporal features clustering Candidate Objects Regional objects Selective search Deep features K-means & VLAD Zhongwen Xu, Yi Yang, Alexander G. Hauptmann (CVPR’15)
Spatial Pyramid Pooling Max pool filter: 7 X 7 6 X 6 5 X 5 2 X 2 Deep Feature Map Extraction Feature 50 descriptors Feature Map 7 X 7 Spatial Pyramid Pooling filter: 50 descriptors VLAD Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun (ECCV’14)
VLAD
PS-10Ex PS-100Ex 45 45 40 40 35 35 30 30 25 25 20 20 MED14-Test (mAP%) MED16-EvalSub MED16-EvalFull MED14-Test (mAP%) MED16-EvalSub MED16-EvalFull (MinfAP200%) (MinfAP200%) (MinfAP200%) (MinfAP200%) CNN-VLAD Object-VLAD CNN-VLAD Object-VLAD
PS-10Ex Concept-Bank_N2 40 Object-VLAD 38 Visual-System 36 (Concept-Bank_N2 + Object-VLAD) 34 32 30 28 26 24 22 20 MED14-Test (mAP%) MED16-EvalSub (MinfAP200%) MED16-EvalFull (MinfAP200%)
MED16-EvalFull-As- MED16-EvalFull (MinfAP200%) MED16-EvalSub (MinfAP200%) MED16-EvalFull (MinfAP200%) ProgressSubset (MinfAP200%) 50 45 41 45 40 39 43 45 35 41 37 30 39 40 35 25 37 20 35 33 35 15 33 31 31 10 29 30 29 5 27 27 0 Team2 VIREO Team3 Team4 Team5 Team6 Team7 Team8 Team9 Team10 Team11 25 25 25 VIREO Team2 Team3 Team4 Team2 VIREO Team3 Team4 Team2 VIREO Team3 Team4
MED16-EvalFull (MinfAP200%) MED16-EvalSub (MinfAP200%) 45 50 40 45 35 40 30 35 30 25 25 20 20 15 15 10 10 5 5 0 0 Team2 VIREO Team4 Team5 Team2 Team3 Team4 Team5 VIREO Team6 Team7 Team8 Team9

Recommend

Parallel Sparse Matrix-Vector and Matrix- Transpose-Vector Multiplication using Compressed Sparse

Parallel Sparse Matrix-Vector and Matrix- Transpose-Vector Multiplication using Compressed Sparse Blocks Aydn Bulu, UCSB Jeremy T. Fineman (MIT) Matteo Frigo (Cilk Arts) John R. Gilbert (UCSB) Charles E. Leiserson (MIT & Cilk Arts) 1

523 views • 21 slides

Exploiting GPU Caches in Sparse Matrix Vector Multiplication Yusuke Nagasaka Tokyo Institute of

Exploiting GPU Caches in Sparse Matrix Vector Multiplication Yusuke Nagasaka Tokyo Institute of Technology Sparse Matrix Generated by FEM, being as the graph data Often require solving sparse linear equation fast Iterative method :

629 views • 30 slides

Lecture 14: Planted Sparse Vector Lecture Outline Part I: Planted Sparse Vector and 2 to 4

Lecture 14: Planted Sparse Vector Lecture Outline Part I: Planted Sparse Vector and 2 to 4 Norm Part II: SOS and 2 to 4 Norm on Random Subspaces Part III: Warmup: Showing 1 Part IV: 4-Norm Analysis Part V:

566 views • 54 slides

Chapter 6: Vector Semantics, Part II Tf-idf and PPMI are sparse representations tf-idf and PPMI

Dan Jurafsky and James Martin Speech and Language Processing Chapter 6: Vector Semantics, Part II Tf-idf and PPMI are sparse representations tf-idf and PPMI vectors are long (length |V|= 20,000 to 50,000) sparse (most elements are

1.14k views • 46 slides

Benchmarking Sparse Matrix-Vector Multiply In 5 Minutes Hormozd Gahvari, Mark Hoemmen, James

Benchmarking Sparse Matrix-Vector Multiply In 5 Minutes Hormozd Gahvari, Mark Hoemmen, James Demmel, and Kathy Yelick January 21, 2007 Outline What is Sparse Matrix-Vector Multiply (SpMV)? Why benchmark it? How to benchmark it?

431 views • 31 slides

The Sparse Vector Technique and online query answering

The Sparse Vector Technique and online query answering CompSci 590.03 Instructor: Ashwin Machanavajjhala Lecture 11: 590.03 Fall 16 1 Offline QA

477 views • 27 slides

Exploiting Matrix Reuse and Data Locality in Sparse Matrix-Vector and Matrix-Transpose-Vector

Matrix reuse and data locality in parallel y = A z and z = A T x Exploiting Matrix Reuse and Data Locality in Sparse Matrix-Vector and Matrix-Transpose-Vector Multiplication on Many-Core Architectures Kadir Akbudak Ozan Karsavuran 1 (speaker)

822 views • 15 slides

Vector FPGA Acceleration of 1-D DWT Computations using Sparse Matrix Skeletons Sidharth

Vector FPGA Acceleration of 1-D DWT Computations using Sparse Matrix Skeletons Sidharth Maheshwari, Gourav Modi, Siddhartha , Nachiket Kapre School of Computer Science and Engineering Nanyang Technological University Matrix-Form 1-D DWT

500 views • 16 slides

Op#miza#on of Block Sparse Matrix- Vector Mul#plica#on on Shared

Op#miza#on of Block Sparse Matrix- Vector Mul#plica#on on Shared Memory Architectures Ryan Eberhardt, Mark Hoemmen Sandia Na#onal Laboratories Sandia National Laboratories is a

725 views • 31 slides

Vector'Semantics Dense%Vectors% Dan%Jurafsky Sparse'versus'dense'vectors PPMI%vectors%are

Vector'Semantics Dense%Vectors% Dan%Jurafsky Sparse'versus'dense'vectors PPMI%vectors%are long (length%|V|=%20,000%to%50,000) sparse' (most%elements%are%zero) Alternative:%learn%vectors%which%are short (length%200F1000)

508 views • 48 slides

Performance Optimizations and Bounds for Sparse Matrix-Vector Multiply Richard Vuduc, James

Performance Optimizations and Bounds for Sparse Matrix-Vector Multiply Richard Vuduc, James Demmel, Katherine Yelick Shoaib Kamil, Rajesh Nishtala, Benjamin Lee Wednesday, November 20, 2002 Berkeley Benchmarking and OPtimization (BeBOP)

679 views • 51 slides

WHICH QUANTIFIERS ARE LOGICAL? A COMBINED SEMANTICAL AND INFERENTIAL CRITERION Solomon Feferman

WHICH QUANTIFIERS ARE LOGICAL? A COMBINED SEMANTICAL AND INFERENTIAL CRITERION Solomon Feferman For the Constructive in Logic and Applications conference in honor of the 60th birthday of Sergei Artemov May 23 May 25, 2012 Graduate Center,

549 views • 37 slides

A Sparse Modeling Approach to Speech Recognition Based on Relevance Vector Machines Jon Hamaker

A Sparse Modeling Approach to Speech Recognition Based on Relevance Vector Machines Jon Hamaker and Joseph Picone Aravind Ganapathiraju hamaker@isip.msstate.edu aganapathiraju@conversay.com Institute for Signal and Information Processing

202 views • 16 slides

Optimizations & Bounds for Sparse Symmetric Matrix-Vector Multiply Berkeley Benchmarking and

Optimizations & Bounds for Sparse Symmetric Matrix-Vector Multiply Berkeley Benchmarking and Optimization Group (BeBOP) http://bebop.cs.berkeley.edu Benjamin C. Lee, Richard W. Vuduc, James W. Demmel, Katherine A. Yelick University of

612 views • 30 slides

The Sparse Matrix Vector Product on High-End GPUs SIAM Conference on Parallel Processing for

The Sparse Matrix Vector Product on High-End GPUs SIAM Conference on Parallel Processing for Scientific Computing (PP20) February 12 - 15, 2020 Hyatt Regency Seattle | Seattle, Washington, U.S. Hartwig Anzt, Terry Cojean, Yuhsiang M. Tsai

796 views • 26 slides

A structure-driven performance analysis of sparse matrix-vector multiplication Prabhjot Sandhu ,

A structure-driven performance analysis of sparse matrix-vector multiplication Prabhjot Sandhu , Clark Verbrugge, and Laurie Hendren Sable Research Group McGill University 23 April 2020 Outline Introduction 1 Experimental Design 2 Research

796 views • 38 slides

Semantical evaluations as monadic second-order compatible structure transformations Bruno

Semantical evaluations as monadic second-order compatible structure transformations Bruno Courcelle Universit Bordeaux 1, LaBRI (based in part on joint work with T. Knapik, Universit de La Runion, France) Summary 1.Introduction

795 views • 35 slides

Sparse Matrix Partitioning, Reordering and Vector Multiplication Albert-Jan Yzelman, Utrecht

Sparse Matrix Partitioning, Reordering and Vector Multiplication Sparse Matrix Partitioning, Reordering and Vector Multiplication Albert-Jan Yzelman, Utrecht University (NL) May, 2010 Albert-Jan Yzelman, Utrecht University (NL) Sparse Matrix

1.26k views • 97 slides

Experiments in Value Function Approximation with Sparse Support Vector Regression Tobias Jung and

Experiments in Value Function Approximation with Sparse Support Vector Regression Tobias Jung and Thomas Uthmann { tjung,uthmann } @informatik.uni-mainz.de Fachbereich Mathematik & Informatik Johannes Gutenberg-Universit at Mainz, Germany

438 views • 17 slides

Optimizing Sparse Matrix Vector Multiplication on Emerging Multicores Orhan Kislal, Wei Ding,

Optimizing Sparse Matrix Vector Multiplication on Emerging Multicores Orhan Kislal, Wei Ding, Mahmut Kandemir Ilteris Demirkiran The Pennsylvania State University University Embry-Riddle Aeronautical University Park, Pennsylvania, USA San

727 views • 23 slides

Performance Models for Evaluation and Automatic Tuning of Symmetric Sparse Matrix-Vector Multiply

Performance Models for Evaluation and Automatic Tuning of Symmetric Sparse Matrix-Vector Multiply University of California, Berkeley Berkeley Benchmarking and Optimization Group (BeBOP) http://bebop.cs.berkeley.edu Benjamin C. Lee, Richard W.

691 views • 32 slides

Tuning Sparse Matrix Vector Multiplication for multi-core SMPs Samuel Williams 1,2 , Richard Vuduc

BIPS BIPS C O M P U T A T I O N A L R E S E A R C H D I V I S I O N Tuning Sparse Matrix Vector Multiplication for multi-core SMPs Samuel Williams 1,2 ,

425 views • 41 slides

Surfin ng the f frame n et A frame is a complex condition on its

1. Frames 2. Shifting 3. Metonymy 4. Word formation 5. Conclusion 2 Whats a frame? Surfin ng the f frame n et A frame is a complex condition on its potential

162 views • 13 slides

Sparse Matrices Example Of Sparse Matrices diagonal tridiagonal sparse many elements are

Sparse Matrices Example Of Sparse Matrices diagonal tridiagonal sparse many elements are zero lower triangular (?) dense few elements are zero These are structured sparse matrices. May be mapped into a 1D array so that a mapping

391 views • 6 slides