Takahiko Furuya,Ryutarou Ohbuchi University of Yamanashi
|
|
- George Boone
- 5 years ago
- Views:
Transcription
1 IEEE 3DV 2014 talk slides: Hashing Cross-Modal Manifold for Scalable Sketch-based 3D Model Retrieval (Poster : 3-29) Takahiko Furuya,Ryutarou Ohbuchi University of Yamanashi
2 Introduction 3D models are widely used. Mechanical CAD, Games, 3D range scanners, 3D printers, User generated. Trimble 3D warehouse,... 3D model retrieval is essential. Ease of use. Efficiency. High retrieval accuracy. 2015/3/13 2
3 Introduction 3D models are widely used. Mechanical CAD, Games, 3D range scanners, 3D printers, User generated. Trimble 3D warehouse,... 3D model retrieval is essential. Ease of use. Sketch-based query Efficiency. Binary features High retrieval accuracy. Better feature similarities 2015/3/13 3
4 Why sketch-based? Keywords Accessible for most people. 3D models lack keyword tags. 3D model Sufficiently accurate for certain applications. 3D models often unavailable. 2D sketch Accessible for most people. Intuitively specify 2D shape. Inaccurate. Inefficient. human search 2015/3/13 4
5 Cross-modal matching problem Approach 1 : Image feature-based comparison. Renders 3D models into lines. e.g., Suggestive contour [DeCarlo03], Adopted by most ([Yoon10], [Shao11], [Eitz12], ). feature comparison 2D sketch 2D sketch-like images 2015/3/13 5
6 Cross-modal matching problem Approach 1 : Image feature-based comparison. Time-consuming for large-scale database. 100K models 20 views = 2M comparisons per query 20 views 100K 3D models 20 views sketch query 2015/3/13 6
7 Cross-modal matching problem Approach 1 : Image feature-based comparison. Can t handle abstraction, semantic influence and noise. feature comparison 2D sketch 2D sketch-like image 2015/3/13 7
8 Cross-modal matching problem Approach 2 : Semantic label-based comparison. human human label-based comparison 2D sketch 3D model 2015/3/13 8
9 Cross-modal matching problem Approach 2 : Semantic label-based comparison. Learning sparse labeling is difficult. human chair human? 2D sketches 3D models chair 2015/3/13 9
10 Our approach Efficiently & effectively combine features and labels. Matching by image feature-based similarity. Matching by semantic label-based similarity. human human 2015/3/13 10
11 Outline Our previous work Cross-Domain Manifold Ranking [Furuya13] Algorithm for cross-modal similarity metric learning Proposed method Experiments and results Conclusion and future work 2015/3/13 11
12 Our previous work : Cross-Domain Manifold Ranking (CDMR) Ranking by diffusion distance on a Cross-Modal Manifold (CMM) [Furuya13]. sketch-sketch feature similarity sketch-3d model feature similarity 3D model-3d model feature similarity query semantic label similarity 2D sketch domain 3D model domain 2015/3/13 12
13 Our previous work : Cross-Domain Manifold Ranking (CDMR) Ranking by diffusion distance on a Cross-Modal Manifold (CMM) [Furuya13]. Relevance diffusion by Manifold Ranking [Zhou03] query 2D sketch domain 3D model domain 2015/3/13 13
14 Our previous work : Cross-Domain Manifold Ranking (CDMR) Lack of scalability. Costly relevance diffusion per query. Insufficient accuracy. Outdated visual features. BF-fGALIF [Eitz12] BF-fGALIF [Eitz12] BF-DSIFT [Furuya09] 2015/3/13 14
15 Our previous work : Cross-Domain Manifold Ranking (CDMR) Lack of scalability. Costly relevance diffusion per query. Hashing CMM (comparison by binary codes) Insufficient accuracy. Better features Outdated visual features. BF-fGALIF [Eitz12] BF-fGALIF [Eitz12] BF-DSIFT [Furuya09] 2015/3/13 15
16 Outline Our previous work Proposed method Cross-Modal Manifold Hashing (CMMH) algorithm Experiments and results Conclusion and future work 2015/3/13 16
17 Proposed method Cross-Modal Manifold Hashing (CMMH) Accuracy: better features Improved visual features (efficient for large-scale CMM) Efficiency: hashing CMM Manifold learning + hashing (Laplacian Eigenmaps (LE) [Belkin03] + Iterative Quantization (ITQ) [Gong12]) LE ITQ CMM flattend CMM (real-valued space) hashed CMM (Hamming space) 2015/3/13 17
18 Proposed method Cross-Modal Manifold Hashing (CMMH) Hashes the CMM to generate compact binary codes. 1. Generates the CMM. 2. Flattens the CMM by Laplacian Eigenmaps (LE). 3. Hashes the flattened CMM by Iterative Quantization (ITQ). feature similarity (weight [0,1]) feature similarity (weight [0,1]) feature similarity (weight [0,1]) 2D sketch domain label similarity (weight 1) 3D model domain 2015/3/13 18
19 Proposed method Cross-Modal Manifold Hashing (CMMH) Hashes the CMM to generate compact binary codes. 1. Generates the CMM. 2. Flattens the CMM by Laplacian Eigenmaps (LE). 3. Hashes the flattened CMM by Iterative Quantization (ITQ). CMM (e.g., 10K sketches + 100K 3D models) flattend CMM (e.g., 512 dim. real-valued space) 2015/3/13 19
20 Proposed method Cross-Modal Manifold Hashing (CMMH) Hashes the CMM to generate compact binary codes. 1. Generates the CMM. 2. Flattens the CMM by Laplacian Eigenmaps (LE). 3. Hashes the flattened CMM by Iterative Quantization (ITQ). CMM (e.g., 10K sketches + 100K 3D models) Randomized SVD [Halko11] for LE on large CMM. (7 minutes to flatten the CMM by using GPU). flattend CMM (e.g., 512 dim. real-valued space) 2015/3/13 20
21 Proposed method Cross-Modal Manifold Hashing (CMMH) Hashes the CMM to generate compact binary codes. 1. Generates the CMM. 2. Flattens the CMM by Laplacian Eigenmaps (LE). 3. Hashes the flattened CMM by Iterative Quantization (ITQ). rotate and hash (1011) (0010) (1110) flattened CMM (real-valued space) hashed CMM (Hamming space) binary codes (e.g., 512 bit) 2015/3/13 21
22 Proposed method Improved feature similarity sketch-to-sketch sketch-to-3d model 3D model-to-3d model SV-MGALIF bsv-mgalif SV-DSIFT + LL-MO1SIFT [Furuya14] 2D sketch domain 3D model domain 2015/3/13 22
23 Proposed method Improved feature similarity sketch-to-sketch sketch-to-3d model 3D model-to-3d model SV-MGALIF must be efficient for large-scale DB bsv-mgalif SV-DSIFT + LL-MO1SIFT [Furuya14] 2D sketch domain 3D model domain 2015/3/13 23
24 Proposed method Improved sketch-to-3d-model similarity bsv-mgalif Multi-scale GALIF + Super Vector (SV) for accuracy. ITQ hashing for efficiency. 2D sketch 3D model multi-view rendering view 1 view 20 MGALIF extraction SV aggregation ~70K dim bit KPCA + ITQ hashing Hamming distance computation 2015/3/ distance
25 Outline Our previous work Proposed method Cross-Modal Manifold Hashing (CMMH) algorithm Experiments and results Conclusion and future work 2015/3/13 25
26 Experiments Evaluate accuracy and efficiency. Visual features for CMM. New Feature Set (NFS) SV-MGALIF bsv-mgalif SV-DSIFT + LL-MO1SIFT VS BF-fGALIF BF-fGALIF BF-DSIFT Cross-modal similarity metric learning algorithms. CMMH Old Feature Set (OFS) [Furuya13] CDMR [Furuya13] VS 2015/3/13 26
27 Experiments Small-scale benchmark database S-PSB [Eitz12] Test set (90 categories) 907 sketches 907 models Training set (92 categories) 907 sketches 907 models human pig human pig 2015/3/13 27
28 Experiments Medium-scale benchmark database SHREC2014 sketch-based 3D shape retrieval (SH14) [Li14] Test set (171 categories) 5,130 sketches 4,494 models 8,987 models Training set (171 categories) 8,550 sketches 4,493 models ant duck ant duck randomly split 10-fold validation 2015/3/13 28
29 Experiments Large-scale benchmark database SH14X (100K 3D models) Test set (171 categories) 5,130 sketches 8,987 models 91,013 imposters (same as SH14) (same as SH14) randomly transformed SH14 3D models 100K models 2015/3/13 29
30 Experimental results Effectiveness of new visual features (S-PSB) Proposed visual features (NFS) are more accurate MAP 50.0 [%] OFS NFS BF-fGALIF CDMR CMMH (512bit) bsv-mgalif CDMR CMMH (512bit) unsupervised semi-supervised /3/13 30
31 Experimental results Efficiency of CMMH CMMH is efficient even for 100K-model database. About 1 second per query. Less than 1 GByte memory footprint. CDMR has a large memory footprint. Comparison of efficiency for SH14X. Algorithms Computation time per query [s] Memory footprint for retrieval [GBytes] CDMR CMMH (512 bit) measured by using two Intel Xeon E CPUs 256 GB RAM, Nvidia GeForce GTX 770 GPU 2015/3/13 31
32 Experimental results Comparison with other retrieval algorithms (SH14) More accurate than state-of-the-arts MAP 30.0[%] BoF-JESC [Zou14] SBR-VC [Li14] unsupervised semi-supervised OPHOG [Tatsuma14] 6.1 SCMR-OPHOG [Tatsuma14] CDMR [Furuya13] CMMH (512bit) /3/13 32
33 Conclusion and Future work Conclusion Efficient & accurate sketch-based 3D model retrieval. Cross-Modal Manifold Hashing (CMMH) Future work About 1 second to query 100K-model database. More accurate than state-of-the-arts. Further improvement in retrieval accuracy. Evaluation using realistic large-scale database. No imposters. Poster : /3/13 33
Sketch-based 3D model retrieval utilizing adaptive view clustering and semantic information
Multimed Tools Appl (2017) 76:26603 26631 DOI 10.1007/s11042-016-4187-3 Sketch-based 3D model retrieval utilizing adaptive view clustering and semantic information Bo Li 1 Yijuan Lu 2 Henry Johan 3 Ribel
More informationSketch-based 3D Shape Retrieval using Convolutional Neural Networks
Sketch-based 3D Shape Retrieval using Convolutional Neural Networks Fang Wang 1 Le Kang 2 Yi Li 1 1 NICTA and ANU 2 ECE, University of Maryland at College Park 1 {fang.wang, yi.li}@cecs.anu.edu.au, 2 lekang@umiacs.umd.edu
More informationSHREC 14 Track: Extended Large Scale Sketch-Based 3D Shape Retrieval
Eurographics Workshop on 3D Object Retrieval (214) B. Bustos, H. Tabia, J.P. Vandeborre, and R. Veltkamp (Editors) SHREC 14 Track: Extended Large Scale Sketch-Based 3D Shape Retrieval B. Li 1, Y. Lu 1,
More informationSqueezing Bag-of-Features for Scalable and Semantic 3D Model Retrieval
Squeezing Bag-of-Features for Scalable and Semantic 3D Model Retrieval Ryutarou Ohbuchi 1, Masaki Tezuka 2, Takahiko Furuya 3, Takashi Oyobe 4 Department of Computer Science and Engineering, University
More informationDiffusion-on-Manifold Aggregation of Local Features for Shape-based 3D Model Retrieval
Diffusion-on-Manifold Aggregation of Local Features for Shape-based 3D Model Retrieval Takahiko Furuya University of Yamanashi 4-3-11 Takeda, Kofu-shi Yamanashi-ken, 0-8511, Japan +81-55-220-85 g13dm003at
More informationAn Unsupervised Approach for Comparing Styles of Illustrations
Takahiko Furuya, Shigeru Kuriyama, and Ryutarou Ohbuchi, An Unsupervised Approach for Comparing Styles of Illustrations, Oral paper, Proc. 13th Int l Workshop on Content-Based Multimedia Indexing (CBMI)
More informationRandomized Sub-Volume Partitioning for Part-Based 3D Model Retrieval
Eurographics Workshop on 3D Object Retrieval (2015) I. Pratikakis, M. Spagnuolo, T. Theoharis, L. Van Gool, and R. Veltkamp (Editors) Randomized Sub-Volume Partitioning for Part-Based 3D Model Retrieval
More informationAccurate Aggregation of Local Features by using K-sparse Autoencoder for 3D Model Retrieval
Accurate Aggregation of Local Features by using K-sparse Autoencoder for 3D Model Retrieval Takahiko Furuya University of Yamanashi 4-3-11 Takeda, Kofu-shi Yamanashi-ken, 400-8511, Japan +81-55-220-8570
More informationL10 Layered Depth Normal Images. Introduction Related Work Structured Point Representation Boolean Operations Conclusion
L10 Layered Depth Normal Images Introduction Related Work Structured Point Representation Boolean Operations Conclusion 1 Introduction Purpose: using the computational power on GPU to speed up solid modeling
More informationSupervised Hashing for Image Retrieval via Image Representation Learning
Supervised Hashing for Image Retrieval via Image Representation Learning Rongkai Xia, Yan Pan, Cong Liu (Sun Yat-Sen University) Hanjiang Lai, Shuicheng Yan (National University of Singapore) Finding Similar
More informationAccelerating Bag-of-Features SIFT Algorithm for 3D Model Retrieval
Accelerating Bag-of-Features SIFT Algorithm for 3D Model Retrieval Ryutarou Ohbuchi, Takahiko Furuya 4-3-11 Takeda, Kofu-shi, Yamanashi-ken, 400-8511, Japan ohbuchi@yamanashi.ac.jp, snc49925@gmail.com
More informationSKETCH-BASED 3D model retrieval, which takes a handdrawn
966 IEEE SIGNAL PROCESSING LETTERS, VOL 21, NO 8, AUGUST 2014 Viewpoint-Aware Representation for Sketch-Bed 3D Model Retrieval Changqing Zou, Changhu Wang, Member, IEEE, Yafei Wen, Lei Zhang, Senior Member,
More informationLarge-Scale Face Manifold Learning
Large-Scale Face Manifold Learning Sanjiv Kumar Google Research New York, NY * Joint work with A. Talwalkar, H. Rowley and M. Mohri 1 Face Manifold Learning 50 x 50 pixel faces R 2500 50 x 50 pixel random
More informationRongrong Ji (Columbia), Yu Gang Jiang (Fudan), June, 2012
Supervised Hashing with Kernels Wei Liu (Columbia Columbia), Jun Wang (IBM IBM), Rongrong Ji (Columbia), Yu Gang Jiang (Fudan), and Shih Fu Chang (Columbia Columbia) June, 2012 Outline Motivations Problem
More informationA Semantic Tree-Based Approach for Sketch-Based 3D Model Retrieval
2016 23rd International Conference on Pattern Recognition (ICPR) Cancún Center, Cancún, México, December 4-8, 2016 A Semantic Tree-Based Approach for Sketch-Based 3D Model Retrieval Bo Li 1,2 1 School
More informationAccelerating Reinforcement Learning in Engineering Systems
Accelerating Reinforcement Learning in Engineering Systems Tham Chen Khong with contributions from Zhou Chongyu and Le Van Duc Department of Electrical & Computer Engineering National University of Singapore
More informationHashing with Graphs. Sanjiv Kumar (Google), and Shih Fu Chang (Columbia) June, 2011
Hashing with Graphs Wei Liu (Columbia Columbia), Jun Wang (IBM IBM), Sanjiv Kumar (Google), and Shih Fu Chang (Columbia) June, 2011 Overview Graph Hashing Outline Anchor Graph Hashing Experiments Conclusions
More informationLarge-scale visual recognition Efficient matching
Large-scale visual recognition Efficient matching Florent Perronnin, XRCE Hervé Jégou, INRIA CVPR tutorial June 16, 2012 Outline!! Preliminary!! Locality Sensitive Hashing: the two modes!! Hashing!! Embedding!!
More informationLarge scale Imaging on Current Many- Core Platforms
Large scale Imaging on Current Many- Core Platforms SIAM Conf. on Imaging Science 2012 May 20, 2012 Dr. Harald Köstler Chair for System Simulation Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen,
More informationModern GPUs (Graphics Processing Units)
Modern GPUs (Graphics Processing Units) Powerful data parallel computation platform. High computation density, high memory bandwidth. Relatively low cost. NVIDIA GTX 580 512 cores 1.6 Tera FLOPs 1.5 GB
More informationLarge scale object/scene recognition
Large scale object/scene recognition Image dataset: > 1 million images query Image search system ranked image list Each image described by approximately 2000 descriptors 2 10 9 descriptors to index! Database
More informationPreparation Meeting. Recent Advances in the Analysis of 3D Shapes. Emanuele Rodolà Matthias Vestner Thomas Windheuser Daniel Cremers
Preparation Meeting Recent Advances in the Analysis of 3D Shapes Emanuele Rodolà Matthias Vestner Thomas Windheuser Daniel Cremers What You Will Learn in the Seminar Get an overview on state of the art
More informationGraph Partitioning for Scalable Distributed Graph Computations
Graph Partitioning for Scalable Distributed Graph Computations Aydın Buluç ABuluc@lbl.gov Kamesh Madduri madduri@cse.psu.edu 10 th DIMACS Implementation Challenge, Graph Partitioning and Graph Clustering
More informationlearning stage (Stage 1), CNNH learns approximate hash codes for training images by optimizing the following loss function:
1 Query-adaptive Image Retrieval by Deep Weighted Hashing Jian Zhang and Yuxin Peng arxiv:1612.2541v2 [cs.cv] 9 May 217 Abstract Hashing methods have attracted much attention for large scale image retrieval.
More informationImproving 3D Shape Retrieval Methods based on Bag-of Feature Approach by using Local Codebooks
Improving 3D Shape Retrieval Methods based on Bag-of Feature Approach by using Local Codebooks El Wardani Dadi 1,*, El Mostafa Daoudi 1 and Claude Tadonki 2 1 University Mohammed First, Faculty of Sciences,
More informationPacketShader: A GPU-Accelerated Software Router
PacketShader: A GPU-Accelerated Software Router Sangjin Han In collaboration with: Keon Jang, KyoungSoo Park, Sue Moon Advanced Networking Lab, CS, KAIST Networked and Distributed Computing Systems Lab,
More informationIsometric Mapping Hashing
Isometric Mapping Hashing Yanzhen Liu, Xiao Bai, Haichuan Yang, Zhou Jun, and Zhihong Zhang Springer-Verlag, Computer Science Editorial, Tiergartenstr. 7, 692 Heidelberg, Germany {alfred.hofmann,ursula.barth,ingrid.haas,frank.holzwarth,
More informationDeep Aggregation of Local 3D Geometric Features for 3D Model Retrieval
FURUYA AND OHBUCHI: DEEP AGGREGATION OF LOCAL 3D FEATURES 1 Deep Aggregation of Local 3D Geometric Features for 3D Model Retrieval Takahiko Furuya 1 takahikof AT yamanashi.ac.jp Ryutarou Ohbuchi 1 ohbuchi
More informationWarped parallel nearest neighbor searches using kd-trees
Warped parallel nearest neighbor searches using kd-trees Roman Sokolov, Andrei Tchouprakov D4D Technologies Kd-trees Binary space partitioning tree Used for nearest-neighbor search, range search Application:
More informationSemi-supervised Data Representation via Affinity Graph Learning
1 Semi-supervised Data Representation via Affinity Graph Learning Weiya Ren 1 1 College of Information System and Management, National University of Defense Technology, Changsha, Hunan, P.R China, 410073
More informationNon-rigid 3D Model Retrieval Using Set of Local Statistical Features
Non-rigid 3D Model Retrieval Using Set of Local Statistical Features Yuki Ohkita, Yuya Ohishi, University of Yamanashi Kofu, Yamanashi, Japan {g09mk004, g11mk008}at yamanashi.ac.jp Takahiko Furuya Nisca
More informationHeat Diffusion Long-Short Term Memory Learning for 3D Shape Analysis
Heat Diffusion Long-Short Term Memory Learning for 3D Shape Analysis Fan Zhu, Jin Xie, and Yi Fang* NYU Multimedia and Visual Computing Lab, Department of Electrical and Computer Engineering, New York
More informationHashing with Binary Autoencoders
Hashing with Binary Autoencoders Ramin Raziperchikolaei Electrical Engineering and Computer Science University of California, Merced http://eecs.ucmerced.edu Joint work with Miguel Á. Carreira-Perpiñán
More informationThe Most User-Friendly 3D scanner
The Most User-Friendly 3D scanner The Solutionix C500 is optimized for scanning small- to medium-sized objects. With dual 5.0MP cameras, the C500 provides excellent data quality at a high resolution. In
More informationLearning Barycentric Representations of 3D Shapes for Sketch-based 3D Shape Retrieval
Learning Barycentric Representations of 3D Shapes for Sketch-based 3D Shape Retrieval Jin Xie, Guoxian Dai, Fan Zhu, and Yi Fang NYU Multimedia and Visual Computing Lab Department of Electrical and Computer
More informationLearning to generate 3D shapes
Learning to generate 3D shapes Subhransu Maji College of Information and Computer Sciences University of Massachusetts, Amherst http://people.cs.umass.edu/smaji August 10, 2018 @ Caltech Creating 3D shapes
More informationImproving Memory Space Efficiency of Kd-tree for Real-time Ray Tracing Byeongjun Choi, Byungjoon Chang, Insung Ihm
Improving Memory Space Efficiency of Kd-tree for Real-time Ray Tracing Byeongjun Choi, Byungjoon Chang, Insung Ihm Department of Computer Science and Engineering Sogang University, Korea Improving Memory
More informationSkeleton Based As-Rigid-As-Possible Volume Modeling
Skeleton Based As-Rigid-As-Possible Volume Modeling Computer Science Department, Rutgers University As-rigid-as-possible (ARAP) shape modeling is a popular technique to obtain natural deformations. There
More informationAdaptive Binary Quantization for Fast Nearest Neighbor Search
IBM Research Adaptive Binary Quantization for Fast Nearest Neighbor Search Zhujin Li 1, Xianglong Liu 1*, Junjie Wu 1, and Hao Su 2 1 Beihang University, Beijing, China 2 Stanford University, Stanford,
More informationA Mathematical Framework for Efficient Closed-Form Single Scattering. Vincent Pegoraro Mathias Schott Philipp Slusallek
A Mathematical Framework for Efficient Closed-Form Single Scattering Vincent Pegoraro Mathias Schott Philipp Slusallek Outline 1. Introduction 2. Related Work 3. Air-Light Integral 4. Complexity Reduction
More information3D Sketch-based 3D Model Retrieval with Convolutional Neural Network
2016 23rd International Conference on Pattern Recognition (ICPR) Cancún Center, Cancún, México, December 4-8, 2016 3D Sketch-based 3D Model Retrieval with Convolutional Neural Network Yuxiang Ye Department
More informationLecture 24: Image Retrieval: Part II. Visual Computing Systems CMU , Fall 2013
Lecture 24: Image Retrieval: Part II Visual Computing Systems Review: K-D tree Spatial partitioning hierarchy K = dimensionality of space (below: K = 2) 3 2 1 3 3 4 2 Counts of points in leaf nodes Nearest
More informationApproximate Search and Data Reduction Algorithms
Approximate Search and Data Reduction Algorithms Research Questions Kyle Porter NTNU Gjøvik Outline of Presentation Introduction: Problems General Goals Research Questions Brief theoretical/practical background
More informationProgressive Generative Hashing for Image Retrieval
Progressive Generative Hashing for Image Retrieval Yuqing Ma, Yue He, Fan Ding, Sheng Hu, Jun Li, Xianglong Liu 2018.7.16 01 BACKGROUND the NNS problem in big data 02 RELATED WORK Generative adversarial
More informationMotivation and basic concepts Storage Principle Query Principle Index Principle Implementation and Results Conclusion
JSON Schema-less into RDBMS Most of the material was taken from the Internet and the paper JSON data management: sup- porting schema-less development in RDBMS, Liu, Z.H., B. Hammerschmidt, and D. McMahon,
More informationAdaptive Hash Retrieval with Kernel Based Similarity
Adaptive Hash Retrieval with Kernel Based Similarity Xiao Bai a, Cheng Yan a, Haichuan Yang a, Lu Bai b, Jun Zhou c, Edwin Robert Hancock d a School of Computer Science and Engineering, Beihang University,
More informationOptimizing Out-of-Core Nearest Neighbor Problems on Multi-GPU Systems Using NVLink
Optimizing Out-of-Core Nearest Neighbor Problems on Multi-GPU Systems Using NVLink Rajesh Bordawekar IBM T. J. Watson Research Center bordaw@us.ibm.com Pidad D Souza IBM Systems pidsouza@in.ibm.com 1 Outline
More informationLearning Low-rank Transformations: Algorithms and Applications. Qiang Qiu Guillermo Sapiro
Learning Low-rank Transformations: Algorithms and Applications Qiang Qiu Guillermo Sapiro Motivation Outline Low-rank transform - algorithms and theories Applications Subspace clustering Classification
More informationSIMPLY RHINO PNY NVIDIA Quadro Rhino v6 WIP Tests. Contents
SIMPLY RHINO PNY NVIDIA Quadro Rhino v6 WIP Tests Contents 01 Disclaimer 3 02 Introduction 3 03 Hardware and Settings 3 04 Testing Improvements from Rhino v5 to Rhino v6 4 05 Testing Outline scores for
More informationover Multi Label Images
IBM Research Compact Hashing for Mixed Image Keyword Query over Multi Label Images Xianglong Liu 1, Yadong Mu 2, Bo Lang 1 and Shih Fu Chang 2 1 Beihang University, Beijing, China 2 Columbia University,
More informationSemi-Supervised Hierarchical Models for 3D Human Pose Reconstruction
Semi-Supervised Hierarchical Models for 3D Human Pose Reconstruction Atul Kanaujia, CBIM, Rutgers Cristian Sminchisescu, TTI-C Dimitris Metaxas,CBIM, Rutgers 3D Human Pose Inference Difficulties Towards
More informationAccelerated Machine Learning Algorithms in Python
Accelerated Machine Learning Algorithms in Python Patrick Reilly, Leiming Yu, David Kaeli reilly.pa@husky.neu.edu Northeastern University Computer Architecture Research Lab Outline Motivation and Goals
More informationPOINT CLOUD DEEP LEARNING
POINT CLOUD DEEP LEARNING Innfarn Yoo, 3/29/28 / 57 Introduction AGENDA Previous Work Method Result Conclusion 2 / 57 INTRODUCTION 3 / 57 2D OBJECT CLASSIFICATION Deep Learning for 2D Object Classification
More informationcustinger - Supporting Dynamic Graph Algorithms for GPUs Oded Green & David Bader
custinger - Supporting Dynamic Graph Algorithms for GPUs Oded Green & David Bader What we will see today The first dynamic graph data structure for the GPU. Scalable in size Supports the same functionality
More informationMPEG-7 Visual shape descriptors
MPEG-7 Visual shape descriptors Miroslaw Bober presented by Peter Tylka Seminar on scientific soft skills 22.3.2012 Presentation Outline Presentation Outline Introduction to problem Shape spectrum - 3D
More informationStudy and implementation of computational methods for Differential Equations in heterogeneous systems. Asimina Vouronikoy - Eleni Zisiou
Study and implementation of computational methods for Differential Equations in heterogeneous systems Asimina Vouronikoy - Eleni Zisiou Outline Introduction Review of related work Cyclic Reduction Algorithm
More informationA GPU-based Approximate SVD Algorithm Blake Foster, Sridhar Mahadevan, Rui Wang
A GPU-based Approximate SVD Algorithm Blake Foster, Sridhar Mahadevan, Rui Wang University of Massachusetts Amherst Introduction Singular Value Decomposition (SVD) A: m n matrix (m n) U, V: orthogonal
More informationEvaluation of GIST descriptors for web scale image search
Evaluation of GIST descriptors for web scale image search Matthijs Douze Hervé Jégou, Harsimrat Sandhawalia, Laurent Amsaleg and Cordelia Schmid INRIA Grenoble, France July 9, 2009 Evaluation of GIST for
More informationTanuj Kr Aasawat, Tahsin Reza, Matei Ripeanu Networked Systems Laboratory (NetSysLab) University of British Columbia
How well do CPU, GPU and Hybrid Graph Processing Frameworks Perform? Tanuj Kr Aasawat, Tahsin Reza, Matei Ripeanu Networked Systems Laboratory (NetSysLab) University of British Columbia Networked Systems
More informationSemantic Segmentation
Semantic Segmentation UCLA:https://goo.gl/images/I0VTi2 OUTLINE Semantic Segmentation Why? Paper to talk about: Fully Convolutional Networks for Semantic Segmentation. J. Long, E. Shelhamer, and T. Darrell,
More informationApproximate Nearest Neighbor Search. Deng Cai Zhejiang University
Approximate Nearest Neighbor Search Deng Cai Zhejiang University The Era of Big Data How to Find Things Quickly? Web 1.0 Text Search Sparse feature Inverted Index How to Find Things Quickly? Web 2.0, 3.0
More informationFast Fuzzy Clustering of Infrared Images. 2. brfcm
Fast Fuzzy Clustering of Infrared Images Steven Eschrich, Jingwei Ke, Lawrence O. Hall and Dmitry B. Goldgof Department of Computer Science and Engineering, ENB 118 University of South Florida 4202 E.
More informationImage Analysis & Retrieval. CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W Lec 18.
Image Analysis & Retrieval CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W 4-5:15pm@Bloch 0012 Lec 18 Image Hashing Zhu Li Dept of CSEE, UMKC Office: FH560E, Email: lizhu@umkc.edu, Ph:
More informationSupervised Hashing for Image Retrieval via Image Representation Learning
Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence Supervised Hashing for Image Retrieval via Image Representation Learning Rongkai Xia 1, Yan Pan 1, Hanjiang Lai 1,2, Cong Liu
More informationGeometry Representations with Unsupervised Feature Learning
Geometry Representations with Unsupervised Feature Learning Yeo-Jin Yoon 1, Alexander Lelidis 2, A. Cengiz Öztireli 3, Jung-Min Hwang 1, Markus Gross 3 and Soo-Mi Choi 1 1 Department of Computer Science
More informationA Taxonomy of Semi-Supervised Learning Algorithms
A Taxonomy of Semi-Supervised Learning Algorithms Olivier Chapelle Max Planck Institute for Biological Cybernetics December 2005 Outline 1 Introduction 2 Generative models 3 Low density separation 4 Graph
More informationHow much data can a BluRay hold?
COMPUTER HARDWARE ICS2O MR. EMMELL HOW MUCH SPACE ON YOUR USB? How much RAM in your phone? How much data can a BluRay hold? 1 THAT WHOLE B/KB/MB/GB/TB THING THAT WHOLE B/KB/MB/GB/TB THING So how many Bytes
More informationFast, Accurate Detection of 100,000 Object Classes on a Single Machine
Fast, Accurate Detection of 100,000 Object Classes on a Single Machine Thomas Dean etal. Google, Mountain View, CA CVPR 2013 best paper award Presented by: Zhenhua Wang 2013.12.10 Outline Background This
More informationParallel Patterns for Window-based Stateful Operators on Data Streams: an Algorithmic Skeleton Approach
Parallel Patterns for Window-based Stateful Operators on Data Streams: an Algorithmic Skeleton Approach Tiziano De Matteis, Gabriele Mencagli University of Pisa Italy INTRODUCTION The recent years have
More informationBit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification
IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification Ruimao Zhang, Liang Lin, Rui Zhang, Wangmeng Zuo,
More informationPhoto-realistic Renderings for Machines Seong-heum Kim
Photo-realistic Renderings for Machines 20105034 Seong-heum Kim CS580 Student Presentations 2016.04.28 Photo-realistic Renderings for Machines Scene radiances Model descriptions (Light, Shape, Material,
More informationSOURCERER: MINING AND SEARCHING INTERNET- SCALE SOFTWARE REPOSITORIES
SOURCERER: MINING AND SEARCHING INTERNET- SCALE SOFTWARE REPOSITORIES Introduction to Information Retrieval CS 150 Donald J. Patterson This content based on the paper located here: http://dx.doi.org/10.1007/s10618-008-0118-x
More informationSearch and Retrieval of Rich Media Objects Supporting Multiple Multimodal Queries
734 IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 14, NO. 3, JUNE 2012 Search and Retrieval of Rich Media Objects Supporting Multiple Multimodal Queries Petros Daras, Member, IEEE, Stavroula Manolopoulou, and
More informationClustering & Dimensionality Reduction. 273A Intro Machine Learning
Clustering & Dimensionality Reduction 273A Intro Machine Learning What is Unsupervised Learning? In supervised learning we were given attributes & targets (e.g. class labels). In unsupervised learning
More informationHere are the general Elgato Game Capture HD60 S System Requirements. 4th generation quad-core Intel Core i5 CPU (i5-4xxx or comparable)
Here are the general Elgato Game Capture HD60 S System Requirements. Windows: Windows 10 (64-bit) 4th generation quad-core Intel Core i5 CPU (i5-4xxx or comparable) Intel HD, NVIDIA GeForce GTX 600 series
More informationCoordinating More Than 3 Million CUDA Threads for Social Network Analysis. Adam McLaughlin
Coordinating More Than 3 Million CUDA Threads for Social Network Analysis Adam McLaughlin Applications of interest Computational biology Social network analysis Urban planning Epidemiology Hardware verification
More informationEnabling Active Storage on Parallel I/O Software Stacks. Seung Woo Son Mathematics and Computer Science Division
Enabling Active Storage on Parallel I/O Software Stacks Seung Woo Son sson@mcs.anl.gov Mathematics and Computer Science Division MSST 2010, Incline Village, NV May 7, 2010 Performing analysis on large
More informationIMAGE MATCHING - ALOK TALEKAR - SAIRAM SUNDARESAN 11/23/2010 1
IMAGE MATCHING - ALOK TALEKAR - SAIRAM SUNDARESAN 11/23/2010 1 : Presentation structure : 1. Brief overview of talk 2. What does Object Recognition involve? 3. The Recognition Problem 4. Mathematical background:
More informationTrafficDB: HERE s High Performance Shared-Memory Data Store Ricardo Fernandes, Piotr Zaczkowski, Bernd Göttler, Conor Ettinoffe, and Anis Moussa
TrafficDB: HERE s High Performance Shared-Memory Data Store Ricardo Fernandes, Piotr Zaczkowski, Bernd Göttler, Conor Ettinoffe, and Anis Moussa EPL646: Advanced Topics in Databases Christos Hadjistyllis
More informationGPU-accelerated 3-D point cloud generation from stereo images
GPU-accelerated 3-D point cloud generation from stereo images Dr. Bingcai Zhang Release of this guide is approved as of 02/28/2014. This document gives only a general description of the product(s) or service(s)
More informationNeural Networks for Machine Learning. Lecture 15a From Principal Components Analysis to Autoencoders
Neural Networks for Machine Learning Lecture 15a From Principal Components Analysis to Autoencoders Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed Principal Components
More informationon learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015
on learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015 Vector visual representation Fixed-size image representation High-dim (100 100,000) Generic, unsupervised: BoW,
More informationLearning to Hash on Structured Data
Learning to Hash on Structured Data Qifan Wang, Luo Si and Bin Shen Computer Science Department, Purdue University West Lafayette, IN 47907, US wang868@purdue.edu, lsi@purdue.edu, bshen@purdue.edu Abstract
More informationJoint Shape Segmentation
Joint Shape Segmentation Motivations Structural similarity of segmentations Extraneous geometric clues Single shape segmentation [Chen et al. 09] Joint shape segmentation [Huang et al. 11] Motivations
More informationA Closer Look at SERVER-SIDE RENDERING. Technology Overview
A Closer Look at SERVER-SIDE RENDERING Technology Overview Driven by server-based rendering, Synapse 5 is the fastest PACS in the medical industry, offering subsecond image delivery and diagnostic quality.
More informationParallel LZ77 Decoding with a GPU. Emmanuel Morfiadakis Supervisor: Dr Eric McCreath College of Engineering and Computer Science, ANU
Parallel LZ77 Decoding with a GPU Emmanuel Morfiadakis Supervisor: Dr Eric McCreath College of Engineering and Computer Science, ANU Outline Background (What?) Problem definition and motivation (Why?)
More informationEfficient Lists Intersection by CPU- GPU Cooperative Computing
Efficient Lists Intersection by CPU- GPU Cooperative Computing Di Wu, Fan Zhang, Naiyong Ao, Gang Wang, Xiaoguang Liu, Jing Liu Nankai-Baidu Joint Lab, Nankai University Outline Introduction Cooperative
More informationVery fast simulation of nonlinear water waves in very large numerical wave tanks on affordable graphics cards
Very fast simulation of nonlinear water waves in very large numerical wave tanks on affordable graphics cards By Allan P. Engsig-Karup, Morten Gorm Madsen and Stefan L. Glimberg DTU Informatics Workshop
More informationLarge-scale Deep Unsupervised Learning using Graphics Processors
Large-scale Deep Unsupervised Learning using Graphics Processors Rajat Raina Anand Madhavan Andrew Y. Ng Stanford University Learning from unlabeled data Classify vs. car motorcycle Input space Unlabeled
More informationA NOVEL SKETCH-BASED 3D MODEL RETRIEVAL APPROACH BY INTEGRATING PCA-DAISY DESCRIPTOR AND FISHER CODING ALGORITHM
International Journal of Innovative Computing, Information and Control ICIC International c 2017 ISSN 1349-4198 Volume 13, Number 2, April 2017 pp. 411 427 A NOVEL SKETCH-BASED 3D MODEL RETRIEVAL APPROACH
More informationSR-IOV Support for Virtualization on InfiniBand Clusters: Early Experience
SR-IOV Support for Virtualization on InfiniBand Clusters: Early Experience Jithin Jose, Mingzhe Li, Xiaoyi Lu, Krishna Kandalla, Mark Arnold and Dhabaleswar K. (DK) Panda Network-Based Computing Laboratory
More informationShifter: Fast and consistent HPC workflows using containers
Shifter: Fast and consistent HPC workflows using containers CUG 2017, Redmond, Washington Lucas Benedicic, Felipe A. Cruz, Thomas C. Schulthess - CSCS May 11, 2017 Outline 1. Overview 2. Docker 3. Shifter
More informationParallel Architecture & Programing Models for Face Recognition
Parallel Architecture & Programing Models for Face Recognition Submitted by Sagar Kukreja Computer Engineering Department Rochester Institute of Technology Agenda Introduction to face recognition Feature
More informationBag of Words Models. CS4670 / 5670: Computer Vision Noah Snavely. Bag-of-words models 11/26/2013
CS4670 / 5670: Computer Vision Noah Snavely Bag-of-words models Object Bag of words Bag of Words Models Adapted from slides by Rob Fergus and Svetlana Lazebnik 1 Object Bag of words Origin 1: Texture Recognition
More informationLarge-Scale GPU programming
Large-Scale GPU programming Tim Kaldewey Research Staff Member Database Technologies IBM Almaden Research Center tkaldew@us.ibm.com Assistant Adjunct Professor Computer and Information Science Dept. University
More informationCompressed local descriptors for fast image and video search in large databases
Compressed local descriptors for fast image and video search in large databases Matthijs Douze2 joint work with Hervé Jégou1, Cordelia Schmid2 and Patrick Pérez3 1: INRIA Rennes, TEXMEX team, France 2:
More informationOn Level Scheduling for Incomplete LU Factorization Preconditioners on Accelerators
On Level Scheduling for Incomplete LU Factorization Preconditioners on Accelerators Karl Rupp, Barry Smith rupp@mcs.anl.gov Mathematics and Computer Science Division Argonne National Laboratory FEMTEC
More informationRepresentation Learning using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval
Representation Learning using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval Xiaodong Liu 12, Jianfeng Gao 1, Xiaodong He 1 Li Deng 1, Kevin Duh 2, Ye-Yi Wang 1 1
More informationACCELERATION OF IMAGE RESTORATION ALGORITHMS FOR DYNAMIC MEASUREMENTS IN COORDINATE METROLOGY BY USING OPENCV GPU FRAMEWORK
URN (Paper): urn:nbn:de:gbv:ilm1-2014iwk-140:6 58 th ILMENAU SCIENTIFIC COLLOQUIUM Technische Universität Ilmenau, 08 12 September 2014 URN: urn:nbn:de:gbv:ilm1-2014iwk:3 ACCELERATION OF IMAGE RESTORATION
More informationFrom Neural Re-Ranking to Neural Ranking:
From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing Hamed Zamani (1), Mostafa Dehghani (2), W. Bruce Croft (1), Erik Learned-Miller (1), and Jaap Kamps (2)
More information