Supplemental Material for Can Visual Recognition Benefit from Auxiliary Information in Training?
|
|
- Osborne Cain
- 5 years ago
- Views:
Transcription
1 Supplemental Material for Can Visual Recognition Benefit from Auxiliary Information in Training? Qilin Zhang, Gang Hua, Wei Liu 2, Zicheng Liu 3, Zhengyou Zhang 3 Stevens Institute of Technolog, Hoboken, NJ 2 IBM Thomas J. Watson Research Center, Yorktown Heights, NY 3 Microsoft Research, Redmond, WA In this supplemental material, we present the proof of Proposition in Section and additional experimental results with the the RGBD Object dataset [] in Section 2. Proof of Proposition In this section, we present the proof of the Proposition for Paper 498. First, the existence of the upper bound is proven in Section., then the proof that the sequence f(w(s)), s =, 2, is monotonic is presented in Section.2. With the Bolzano-Weiersass theorem and the conclusions of Section. and Section.2, the Proposition is proven.. Proof of the existence of the upper bound C u From the consaint in Eq. (6) of the paper: [( τ j ) n ] R jr Tj τ j I n W j = I, () W T j where τ j denotes the pre-specified regularization parameter, 0 < τ j < (j =, 2,, J), we have ( ) ( τ j ) n WT j R j R T j W j τ j ( Wj T ) W j = n, (2) and therefore ) (W j T R j R T j W j In addition, we have ) (W j T R j R T k W k [ ) (W j T R j R T j W j 2 [ ] 2 τ j τ k τ j, 0 < τ j <, j =, 2,, J. (3) )] (W k T R k R T k W k (4) <, (5)
2 2 Q. Zhang, G. Hua, W. Liu, Z. Liu, Z. Zhang where the inequality (4) follows the property (B T A) 2 [ (A T A) (B T B) ], (6) which comes from the fact that ( (A B) T (A B) ) ) 0, because the maix (A B) T (A B) 0. Since (W j T R jr T k W k is bounded,, g(x) = x or x 2, we have ( )) g (W j T R j R T k W k [ ] 2 <. (7) 4 τ j τ k Considering c = 0 or, we have j k ( ( )) c g n WT j R j R T k W k 4n [ ] 2 <, (8) τ j τ k which shows that the sequence f(w(s)), s =, 2, is upper bounded by C u = 4n j k [ ] 2 <. (9) τ j τ k j k.2 Proof that the sequence f(w(s)), s =, 2, is monotonically increasing In this section, the monotonic property of the sequence f(w(s)), s =, 2, is presented. Following [2 4], we first present a Lemma, and then prove that f(w(s)) f(w(s )), s =, 2,, (0) where s is the iteration index, s =, 2,. Define the function r(y j, Y k ) def = ( n YT j Y k) = ( n WT j R jr T k W k ), therefore, f(w (s),, W J (s)) = j,,k j Using this notation, we have the following Lemma: Lemma. Define f j (W j ) def = j c g [ r(r T j W j, Y k (s )) ] s.t. W T j N j W j = I, c g[r(y j (s), Y k (s))]. () k=j c g [ r(r T j W j, Y k (s)) ] (2)
3 Visual Recognition with Auxiliary Information in Training 3 then f j (W j (s)) f j (W j (s )), j =,, J. (3) Proof. We prove Lemma in two cases, i.e., g(x) = x 2 and g(x) = x. Case : when g(x) = x 2, we have f j (W j ) in the following form, j ) 2 f j (W j ) = c (r(r T j W j, Y k (s )) which can be written as f j (W j (s)) = n where θ (s) k=j j (W j(s) T R j Y k (s )) n k=j = n j W j (s) T R j are defined as θ (s) = c (r(r T j W j, Y k (s))) 2, (4) (W j(s) T R j Y k (s)) (5) Y k(s ) k=j Y k(s), (6) { r (Y j (s), Y k (s )) if k =,, j r (Y j (s), Y k (s)) if k = j,, J. (7) ( j Note that in Eq. (6), the term c θ (s) Y k(s ) ) J k=j c θ (s) Y k(s) is equivalent to the definition of Z j (s), hence f j (W j ) can be simplified as n (WT j R jz j (s)). Considering the following optimization problem: whose solution is exactly we have max Wj n (WT j R j Z j (s)), s.t. W T j N j W j = I, (8) ( W j (s ) = N j R j Z j (s) [Z j (s) T R T j N j R j Z j (s)] /2), (9) (W j (s) T R j Z j (s)) (W j (s ) T R j Z j (s)). (20)
4 4 Q. Zhang, G. Hua, W. Liu, Z. Liu, Z. Zhang Similarly, the following equations can be obtained: j f j (W j (s)) = r(y j(s), Y k (s )) j r(y j(s ), Y k (s )) k=j k=j r(y j(s), Y k (s)) r(y j(s ), Y k (s)). (2) Considering that c is either 0 or, we hence have c = c 2. Applying the Cauchy-Schwartz inequality, we have j f j (W j (s)) c 2 θ (s) r(y j(s ), Y k (s )) j ( c θ (s) ) 2 k=j c ( ) 2 θ (s) j c (r(y j (s ), Y k (s ))) 2 = j c (r(y j (s), Y k (s ))) 2 j c (r(y j (s ), Y k (s ))) 2 = f j (W j (s)) k=j k=j k=j k=j c 2 θ (s) r(y j(s ), Y k (s)) c (r(y j (s ), Y k (s))) 2 c (r(y j (s), Y k (s))) 2 c (r(y j (s ), Y k (s))) 2 f j (W j (s )). (22) We immediately have f j (W j (s)) f j (W j (s )). This concludes the case scenario. Case 2: when g(x) = x, we have j f j (W j ) = c r(r T j W j, Y k (s )) k=j c r(r T j W j, Y k (s)). (23) Therefore, we can have exactly the same equation as Eq. (6), except that θ (s) for all the cases. The same equation as in Eq. (20) can be obtained, which directly implies that f j (W j (s)) f j (W j (s )). This concludes both the case 2 scenario and the entire proof of Lemma.
5 Visual Recognition with Auxiliary Information in Training 5 With the conclusion in Lemma, we proceed with the proof that the sequence f(w(s)), s =, 2, is monotonically increasing. Consider the following subaction [f j (W j (s )) f j (W j (s))] j= = j j= j= k=j j c g j= j j= = 2 [ c g n W j(s ) T R j R T k W k (s ) c g n W j(s ) T R j R T k W k (s) n W j(s) T R j R T k W k (s ) c g n W j(s ) T R j R T k W k (s ) j,,k j j,,k j c g [ ( ) ] n W j(s ) T R j R T k W k (s ) c g [ ( ) ] ] n W j(s) T R j R T k W k (s) 0. (24) The last equation in Eq. (24) follows the Lemma. This implies that f(w (s),, W J (s)) f(w (s ),, W J (s )) (25) i.e., f(w(s)) f(w(s )), s =, 2,. (26) Using Eq. (8), Eq. (26), the bounded sequence f(w(s)), s =, 2, is monotonically increasing. According to the Bolzano-Weiersass theorem, the sequence will converge, i.e., Proposition is proven. 2 Additional Experimental Results With the same RGBD Object dataset and experimental settings from [] and [5], we have also conducted additional experiments with the state-of-the-art HMPbased features [5]. These additional results are summarized in Table 2 (too many enies to fit in a single page). As is seen in Table 2, the overall recognition accuracy improves significantly across all methods, as compared to the EMK-based features []. In a large portion of the categories, perfect recognition is achieved even with the naive baseline
6 6 Q. Zhang, G. Hua, W. Liu, Z. Liu, Z. Zhang Table. Accuracy Table Part for the Multi-View RGBD Object Instance recognition with HMP features, the highest and second highest values are colored red and blue, respectively. The remaining part is in Table 2. Category SVM SVM2K KCCA KCCA RGCCA RGCCA RGCCA L L AL DCCA apple ball banana bell pepper binder bowl calculator camera cap cellphone cereal box coffee mug comb dry battery flashlight food bag food box food can food cup food jar garlic glue stick greens hand towel instant noodles keyboard kleenex lemon light bulb lime marker mushroom notebook onion orange peach pear pitcher plate pliers potato rubber eraser scissors shampoo soda can
7 Visual Recognition with Auxiliary Information in Training 7 Table 2. Continued from Table : Accuracy Table Part 2 for the Multi-View RGBD Object Instance recognition with HMP features, the highest and second highest values are colored red and blue, respectively. Category SVM SVM2K KCCA KCCAL RGCCA RGCCAL RGCCAAL DCCA sponge stapler tomato tooth brush tooth paste water bottle average SVM algorithm, However, the advantage of the proposed method is revealed in some of the challenging categories. Overall, with the HMP-based features, KCCAL and the RGCCAL algorithms cannot match the SVM baseline, and the SVM2K and KCCA algorithms are only marginally better than the baseline. The RGCCA and RGCCAAL algorithms offer some improvements, while the proposed DCCA algorithm achieves the highest overall recognition accuracy. Considering there are more than 3,000 testing samples, the two percent performance improvement means correctly classifying an additional amount of more than 200 samples. References. Lai, K., Bo, L., Ren, X., Fox, D.: A large-scale hierarchical multi-view rgb-d object dataset. In: Robotics and Automation (ICRA), 20 IEEE International Conference on, IEEE (20) Tenenhaus, A., Tenenhaus, M.: Regularized generalized canonical correlation analysis. Psychomeika 76 (20) Tenenhaus, A.: Kernel generalized canonical correlation analysis. Actes des 42è journées de Statistique (200) 4. Hanafi, M.: Pls path modelling: computation of latent variables with the estimation mode b. Computational Statistics 22 (2007) Bo, L., Ren, X., Fox, D.: Unsupervised feature learning for rgb-d based object recognition. ISER, June (202)
Multi-View Visual Recognition of Imperfect Testing Data
Multi-View Visual Recognition of Imperfect Testing Data MM'15, October 26 30, 2015, Brisbane, Australia Qilin Zhang Stevens Institute of Technology 1 Castle Point Terrace Hoboken, NJ, USA, 07030 Gang Hua
More informationMulti-View Visual Recognition of Imperfect Testing Data
Multi-View Visual Recognition of Imperfect Testing Data Qilin Zhang 1 1 Stevens Institute of Technology 1 Castle Point Terrace Hoboken, NJ, USA, 07030 qzhang5@stevens.edu Gang Hua 1,2 2 Microsoft Research
More informationPoint Cloud Object Recognition using 3D Convolutional Neural Networks
Point Cloud Object Recognition using 3D Convolutional Neural Networks Marcelo Borghetti Soares Knowledge Technology Department of Informatics University of Hamburg Vogt-Koelln-Str. 30, 22527 Hamburg, Germany
More informationConvolutional-Recursive Deep Learning for 3D Object Classification
Convolutional-Recursive Deep Learning for 3D Object Classification Richard Socher, Brody Huval, Bharath Bhat, Christopher D. Manning, Andrew Y. Ng NIPS 2012 Iro Armeni, Manik Dhar Motivation Hand-designed
More information(Deep) Learning for Robot Perception and Navigation. Wolfram Burgard
(Deep) Learning for Robot Perception and Navigation Wolfram Burgard Deep Learning for Robot Perception (and Navigation) Lifeng Bo, Claas Bollen, Thomas Brox, Andreas Eitel, Dieter Fox, Gabriel L. Oliveira,
More informationarxiv: v2 [cs.cv] 18 Aug 2015
Multimodal Deep Learning for Robust RGB-D Object Recognition Andreas Eitel Jost Tobias Springenberg Luciano Spinello Martin Riedmiller Wolfram Burgard arxiv:57.682v2 [cs.cv] 8 Aug 25 Abstract Robust object
More informationAalborg Universitet. Published in: International Joint Conference on Computational Intelligence
Aalborg Universitet Depth Value Pre-Processing for Accurate Transfer Learning Based RGB-D Object Recognition Aakerberg, Andreas; Nasrollahi, Kamal; Rasmussen, Christoffer Bøgelund; Moeslund, Thomas B.
More informationPerceiving the 3D World from Images and Videos. Yu Xiang Postdoctoral Researcher University of Washington
Perceiving the 3D World from Images and Videos Yu Xiang Postdoctoral Researcher University of Washington 1 2 Act in the 3D World Sensing & Understanding Acting Intelligent System 3D World 3 Understand
More information3D Object Recognition and Scene Understanding from RGB-D Videos. Yu Xiang Postdoctoral Researcher University of Washington
3D Object Recognition and Scene Understanding from RGB-D Videos Yu Xiang Postdoctoral Researcher University of Washington 1 2 Act in the 3D World Sensing & Understanding Acting Intelligent System 3D World
More informationMI2LS: Multi-Instance Learning from Multiple Information Sources
MI2LS: Multi-Instance Learning from Multiple Information Sources Dan Zhang 1, Jingrui He 2, Richard Lawrence 3 1 Facebook Incorporation, Menlo Park, CA 2 Stevens Institute of Technology Hoboken, NJ 3 IBM
More informationECSE 626 Course Project : A Study in the Efficient Graph-Based Image Segmentation
ECSE 626 Course Project : A Study in the Efficient Graph-Based Image Segmentation Chu Wang Center for Intelligent Machines chu.wang@mail.mcgill.ca Abstract In this course project, I will investigate into
More informationComputer Vision Group Prof. Daniel Cremers. 13. Online Learning
Prof. Daniel Cremers 13. Motivation So far, we have handled offline learning methods, but very often data is observed in an ongoing process Therefore, it would be good to adapt the learned models with
More informationCHALLENGES. for school and home. Kaitlynn Alb
STEM CHALLENGES for school and home Kaitlynn Alb ani STEM Challenge Rules. Be Creative. Have Fun. Learn! a ball of yarn? Create something from a ball of yarn (any size or brand)! You can use any other
More informationRGB-D Object Recognition and Pose Estimation based on Pre-trained Convolutional Neural Network Features
RGB-D Object Recognition and Pose Estimation based on Pre-trained Convolutional Neural Network Features Max Schwarz, Hannes Schulz, and Sven Behnke Abstract Object recognition and pose estimation from
More informationA Scalable Tree-based Approach for Joint Object and Pose Recognition
A Scalable Tree-based Approach for Joint Object and Pose Recognition Kevin Lai Liefeng Bo Computer Science & Engineering University of Washington Seattle, WA 98195, USA Xiaofeng Ren Dieter Fox Intel Labs
More informationDepth Kernel Descriptors for Object Recognition
Depth Kernel Descriptors for Object Recognition Liefeng Bo, Xiaofeng Ren, Dieter Fox Abstract Consumer depth cameras, such as the Microsoft Kinect, are capable of providing frames of dense depth values
More informationA General Greedy Approximation Algorithm with Applications
A General Greedy Approximation Algorithm with Applications Tong Zhang IBM T.J. Watson Research Center Yorktown Heights, NY 10598 tzhang@watson.ibm.com Abstract Greedy approximation algorithms have been
More informationMATH 54 - LECTURE 10
MATH 54 - LECTURE 10 DAN CRYTSER The Universal Mapping Property First we note that each of the projection mappings π i : j X j X i is continuous when i X i is given the product topology (also if the product
More informationSeparating Objects and Clutter in Indoor Scenes
Separating Objects and Clutter in Indoor Scenes Salman H. Khan School of Computer Science & Software Engineering, The University of Western Australia Co-authors: Xuming He, Mohammed Bennamoun, Ferdous
More informationSigned domination numbers of a graph and its complement
Discrete Mathematics 283 (2004) 87 92 www.elsevier.com/locate/disc Signed domination numbers of a graph and its complement Ruth Haas a, Thomas B. Wexler b a Department of Mathematics, Smith College, Northampton,
More informationMath 0420 Homework 3. Scratch Work:For c > 0, according to the definition of limit, we want to find δ to bound the term x c by ɛ.we have: x c.
Math 0420 Homework 3 Eercise 311 Find the it or prove the it does not eit (a) for c 0 Solution: First, we might guess that the it is c Scratch Work:For c > 0, according to the definition of it, we want
More informationNotes slides from before lecture. CSE 21, Winter 2017, Section A00. Lecture 10 Notes. Class URL:
Notes slides from before lecture CSE 21, Winter 2017, Section A00 Lecture 10 Notes Class URL: http://vlsicad.ucsd.edu/courses/cse21-w17/ Notes slides from before lecture Notes February 13 (1) HW5 is due
More informationSOME PROPERTIES OF TRIGONOMETRIC FUNCTIONS. 5! x7 7! + = 6! + = 4! x6
SOME PROPERTIES OF TRIGONOMETRIC FUNCTIONS PO-LAM YUNG We defined earlier the sine cosine by the following series: sin x = x x3 3! + x5 5! x7 7! + = k=0 cos x = 1 x! + x4 4! x6 6! + = k=0 ( 1) k x k+1
More information3D Object Recognition and Scene Understanding. Yu Xiang University of Washington
3D Object Recognition and Scene Understanding Yu Xiang University of Washington 1 2 Image classification tagging/annotation Room Chair Fergus et al. CVPR 03 Fei-Fei et al. CVPRW 04 Chua et al. CIVR 09
More informationLearning complex object-class models in natural conditions. Dan Levi
Learning complex object-class models in natural conditions by Dan Levi A dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy in Computer Science and Applied
More informationBounds on the signed domination number of a graph.
Bounds on the signed domination number of a graph. Ruth Haas and Thomas B. Wexler September 7, 00 Abstract Let G = (V, E) be a simple graph on vertex set V and define a function f : V {, }. The function
More informationLecture 15: The subspace topology, Closed sets
Lecture 15: The subspace topology, Closed sets 1 The Subspace Topology Definition 1.1. Let (X, T) be a topological space with topology T. subset of X, the collection If Y is a T Y = {Y U U T} is a topology
More informationAM 221: Advanced Optimization Spring 2016
AM 221: Advanced Optimization Spring 2016 Prof. Yaron Singer Lecture 2 Wednesday, January 27th 1 Overview In our previous lecture we discussed several applications of optimization, introduced basic terminology,
More informationSolution to Graded Problem Set 4
Graph Theory Applications EPFL, Spring 2014 Solution to Graded Problem Set 4 Date: 13.03.2014 Due by 18:00 20.03.2014 Problem 1. Let V be the set of vertices, x be the number of leaves in the tree and
More informationNEW STABILITY RESULTS FOR ADVERSARIAL QUEUING
NEW STABILITY RESULTS FOR ADVERSARIAL QUEUING ZVI LOTKER, BOAZ PATT-SHAMIR, AND ADI ROSÉN Abstract. We consider the model of adversarial queuing theory for packet networks introduced by Borodin et al.
More informationI How does the formulation (5) serve the purpose of the composite parameterization
Supplemental Material to Identifying Alzheimer s Disease-Related Brain Regions from Multi-Modality Neuroimaging Data using Sparse Composite Linear Discrimination Analysis I How does the formulation (5)
More informationCALCULATING TRANSFORMATIONS OF KINEMATIC CHAINS USING HOMOGENEOUS COORDINATES
CALCULATING TRANSFORMATIONS OF KINEMATIC CHAINS USING HOMOGENEOUS COORDINATES YINGYING REN Abstract. In this paper, the applications of homogeneous coordinates are discussed to obtain an efficient model
More informationAction recognition in videos
Action recognition in videos Cordelia Schmid INRIA Grenoble Joint work with V. Ferrari, A. Gaidon, Z. Harchaoui, A. Klaeser, A. Prest, H. Wang Action recognition - goal Short actions, i.e. drinking, sit
More informationLearning to Grasp Objects: A Novel Approach for Localizing Objects Using Depth Based Segmentation
Learning to Grasp Objects: A Novel Approach for Localizing Objects Using Depth Based Segmentation Deepak Rao, Arda Kara, Serena Yeung (Under the guidance of Quoc V. Le) Stanford University Abstract We
More informationSupplementary Materials to End-to-End Learning of Motion Representation for Video Understanding
Supplementary Materials to End-to-End Learning of Motion Representation for Video Understanding Lijie Fan 2, Wenbing Huang 1, Chuang Gan 3, Stefano Ermon 4, Boqing Gong 1, Junzhou Huang 1 1 Tencent AI
More informationImproving Recognition through Object Sub-categorization
Improving Recognition through Object Sub-categorization Al Mansur and Yoshinori Kuno Graduate School of Science and Engineering, Saitama University, 255 Shimo-Okubo, Sakura-ku, Saitama-shi, Saitama 338-8570,
More informationSeminar on Algorithms and Data Structures: Multiple-Edge-Fault-Tolerant Approximate Shortest-Path Trees [1]
Seminar on Algorithms and Data Structures: Multiple-Edge-Fault-Tolerant Approximate Shortest-Path Trees [1] Philipp Rimle April 14, 2018 1 Introduction Given a graph with positively real-weighted undirected
More informationOffice and School supplies
Office and School supplies Art sets page 02-03 Badge name page 04 Calculators page 05-08 Erasers for blackboards page 09 Carbon paper page 10 Folders page 11 Glues page 12 Covers page 13-14 Correctors
More informationJoint Object Recognition and Pose Estimation using a Nonlinear View-Invariant Latent Generative Model
Joint Object Recognition and Pose Estimation using a Nonlinear View-Invariant Latent Generative Model Amr Bakry* Tarek Elgaaly* Mohamed Elhoseiny Ahmed Elgammal Rutgers University {amrbakry, elgaaly, elhoseiny,
More informationA Survey on Postive and Unlabelled Learning
A Survey on Postive and Unlabelled Learning Gang Li Computer & Information Sciences University of Delaware ligang@udel.edu Abstract In this paper we survey the main algorithms used in positive and unlabeled
More informationAXIOMS FOR THE INTEGERS
AXIOMS FOR THE INTEGERS BRIAN OSSERMAN We describe the set of axioms for the integers which we will use in the class. The axioms are almost the same as what is presented in Appendix A of the textbook,
More informationAdapting Deep Networks Across Domains, Modalities, and Tasks Judy Hoffman!
Adapting Deep Networks Across Domains, Modalities, and Tasks Judy Hoffman! Eric Tzeng Saurabh Gupta Kate Saenko Trevor Darrell Recent Visual Recognition Progress ImageNet Performance 100 Accuracy 95 90
More informationMixture Models and EM
Table of Content Chapter 9 Mixture Models and EM -means Clustering Gaussian Mixture Models (GMM) Expectation Maximiation (EM) for Mixture Parameter Estimation Introduction Mixture models allows Complex
More information* (4.1) A more exact setting will be specified later. The side lengthsj are determined such that
D D Chapter 4 xtensions of the CUB MTOD e present several generalizations of the CUB MTOD In section 41 we analyze the query algorithm GOINGCUB The difference to the CUB MTOD occurs in the case when the
More informationLearning Semantic Environment Perception for Cognitive Robots
Learning Semantic Environment Perception for Cognitive Robots Sven Behnke University of Bonn, Germany Computer Science Institute VI Autonomous Intelligent Systems Some of Our Cognitive Robots Equipped
More informationM3P1/M4P1 (2005) Dr M Ruzhansky Metric and Topological Spaces Summary of the course: definitions, examples, statements.
M3P1/M4P1 (2005) Dr M Ruzhansky Metric and Topological Spaces Summary of the course: definitions, examples, statements. Chapter 1: Metric spaces and convergence. (1.1) Recall the standard distance function
More informationarxiv: v1 [cs.cv] 30 Sep 2016
A deep representation for depth images from synthetic data Fabio Maria Carlucci 1 and Paolo Russo 1 and Barbara Caputo 1 arxiv:169.9713v1 [cs.cv] 3 Sep 216 Abstract Convolutional Neural Networks (CNNs)
More informationA Network Coloring Game
A Network Coloring Game Kamalika Chaudhuri, Fan Chung 2, and Mohammad Shoaib Jamall 2 Information Theory and Applications Center, UC San Diego kamalika@soe.ucsd.edu 2 Department of Mathematics, UC San
More informationLECTURES 3 and 4: Flows and Matchings
LECTURES 3 and 4: Flows and Matchings 1 Max Flow MAX FLOW (SP). Instance: Directed graph N = (V,A), two nodes s,t V, and capacities on the arcs c : A R +. A flow is a set of numbers on the arcs such that
More informationAlphabetic Minimax Trees of Degree at Most t*
Claremont Colleges Scholarship @ Claremont All HMC Faculty Publications and Research HMC Faculty Scholarship 1-1-1986 Alphabetic Minimax Trees of Degree at Most t* D. Coppersmith IBM Thomas J. Watson Research
More information. Tutorial Class V 3-10/10/2012 First Order Partial Derivatives;...
Tutorial Class V 3-10/10/2012 1 First Order Partial Derivatives; Tutorial Class V 3-10/10/2012 1 First Order Partial Derivatives; 2 Application of Gradient; Tutorial Class V 3-10/10/2012 1 First Order
More informationMISCELLANEOUS SHAPES
MISCELLANEOUS SHAPES 4.1. INTRODUCTION Five generic shapes of polygons have been usefully distinguished in the literature: convex, orthogonal, star, spiral, and monotone. 1 Convex polygons obviously do
More informationFunctions. How is this definition written in symbolic logic notation?
functions 1 Functions Def. Let A and B be sets. A function f from A to B is an assignment of exactly one element of B to each element of A. We write f(a) = b if b is the unique element of B assigned by
More informationOn the Max Coloring Problem
On the Max Coloring Problem Leah Epstein Asaf Levin May 22, 2010 Abstract We consider max coloring on hereditary graph classes. The problem is defined as follows. Given a graph G = (V, E) and positive
More informationThe Connectivity and Diameter of Second Order Circuit Graphs of Matroids
Graphs and Combinatorics (2012) 28:737 742 DOI 10.1007/s00373-011-1074-6 ORIGINAL PAPER The Connectivity and Diameter of Second Order Circuit Graphs of Matroids Jinquan Xu Ping Li Hong-Jian Lai Received:
More informationA FRAMEWORK OF EXTRACTING MULTI-SCALE FEATURES USING MULTIPLE CONVOLUTIONAL NEURAL NETWORKS. Kuan-Chuan Peng and Tsuhan Chen
A FRAMEWORK OF EXTRACTING MULTI-SCALE FEATURES USING MULTIPLE CONVOLUTIONAL NEURAL NETWORKS Kuan-Chuan Peng and Tsuhan Chen School of Electrical and Computer Engineering, Cornell University, Ithaca, NY
More informationS U N G - E U I YO O N, K A I S T R E N D E R I N G F R E E LY A VA I L A B L E O N T H E I N T E R N E T
S U N G - E U I YO O N, K A I S T R E N D E R I N G F R E E LY A VA I L A B L E O N T H E I N T E R N E T Copyright 2018 Sung-eui Yoon, KAIST freely available on the internet http://sglab.kaist.ac.kr/~sungeui/render
More informationFace Width and Graph Embeddings of face-width 2 and 3
Face Width and Graph Embeddings of face-width 2 and 3 Instructor: Robin Thomas Scribe: Amanda Pascoe 3/12/07 and 3/14/07 1 Representativity Recall the following: Definition 2. Let Σ be a surface, G a graph,
More informationConvexization in Markov Chain Monte Carlo
in Markov Chain Monte Carlo 1 IBM T. J. Watson Yorktown Heights, NY 2 Department of Aerospace Engineering Technion, Israel August 23, 2011 Problem Statement MCMC processes in general are governed by non
More informationTHE INSULATION SEQUENCE OF A GRAPH
THE INSULATION SEQUENCE OF A GRAPH ELENA GRIGORESCU Abstract. In a graph G, a k-insulated set S is a subset of the vertices of G such that every vertex in S is adjacent to at most k vertices in S, and
More informationObject Categorization in Clutter using Additive Features and Hashing of Part-graph Descriptors
Object Categorization in Clutter using Additive Features and Hashing of Part-graph Descriptors Zoltan-Csaba Marton, Ferenc Balint-Benczedi, Florian Seidel, Lucian Cosmin Goron, and Michael Beetz Intelligent
More informationDecomposition of log-linear models
Graphical Models, Lecture 5, Michaelmas Term 2009 October 27, 2009 Generating class Dependence graph of log-linear model Conformal graphical models Factor graphs A density f factorizes w.r.t. A if there
More informationQuery Adaptive Similarity Measure for RGB-D Object Recognition
Query Adaptive Similarity Measure for RGB-D Object Recognition Yanhua Cheng 1, Rui Cai 2, Chi Zhang 4, Zhiwei Li 2, Xin Zhao 1, Kaiqi Huang 1,3, Tieniu Tan 1,3, Yong Rui 2 1 CRIPAC&NLPR, CASIA 2 Microsoft
More informationOn the packing chromatic number of some lattices
On the packing chromatic number of some lattices Arthur S. Finbow Department of Mathematics and Computing Science Saint Mary s University Halifax, Canada BH C art.finbow@stmarys.ca Douglas F. Rall Department
More informationLecture-12: Closed Sets
and Its Examples Properties of Lecture-12: Dr. Department of Mathematics Lovely Professional University Punjab, India October 18, 2014 Outline Introduction and Its Examples Properties of 1 Introduction
More informationDEPTH SENSOR BASED OBJECT DETECTION USING SURFACE CURVATURE. A Thesis presented to. the Faculty of the Graduate School
DEPTH SENSOR BASED OBJECT DETECTION USING SURFACE CURVATURE A Thesis presented to the Faculty of the Graduate School at the University of Missouri-Columbia In Partial Fulfillment of the Requirements for
More informationLinear Programming Problems
Linear Programming Problems Two common formulations of linear programming (LP) problems are: min Subject to: 1,,, 1,2,,;, max Subject to: 1,,, 1,2,,;, Linear Programming Problems The standard LP problem
More informationEmbedding High-Level Information into Low Level Vision: Efficient Object Search in Clutter
Embedding High-Level Information into Low Level Vision: Efficient Object Search in Clutter Ching L. Teo, Austin Myers, Cornelia Fermüller, Yiannis Aloimonos Abstract The ability to search visually for
More informationSOCIAL MEDIA MINING. Data Mining Essentials
SOCIAL MEDIA MINING Data Mining Essentials Dear instructors/users of these slides: Please feel free to include these slides in your own material, or modify them as you see fit. If you decide to incorporate
More informationMinimal Universal Bipartite Graphs
Minimal Universal Bipartite Graphs Vadim V. Lozin, Gábor Rudolf Abstract A graph U is (induced)-universal for a class of graphs X if every member of X is contained in U as an induced subgraph. We study
More informationLatent variable transformation using monotonic B-splines in PLS Path Modeling
Latent variable transformation using monotonic B-splines in PLS Path Modeling E. Jakobowicz CEDRIC, Conservatoire National des Arts et Métiers, 9 rue Saint Martin, 754 Paris Cedex 3, France EDF R&D, avenue
More informationRGB-D Multi-View Object Detection with Object Proposals and Shape Context
2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Daejeon Convention Center October 9-14, 2016, Daejeon, Korea RGB-D Multi-View Object Detection with Object Proposals and
More informationSupplementary Materials for A Comparison of Optimization Methods and Software for Large-scale L1-regularized Linear Classification
Supplementary Materials for A Comparison of Optimization Methods and Software for Large-scale L1-regularized Linear Classification Guo-Xun Yuan, Kai-Wei Chang, Cho-Jui Hsieh and Chih-Jen Lin Department
More informationHamiltonian cycles in bipartite quadrangulations on the torus
Hamiltonian cycles in bipartite quadrangulations on the torus Atsuhiro Nakamoto and Kenta Ozeki Abstract In this paper, we shall prove that every bipartite quadrangulation G on the torus admits a simple
More informationScan Scheduling Specification and Analysis
Scan Scheduling Specification and Analysis Bruno Dutertre System Design Laboratory SRI International Menlo Park, CA 94025 May 24, 2000 This work was partially funded by DARPA/AFRL under BAE System subcontract
More information25 Oxford Street, Trenton, New Jersey
SUPPLY LIST PreK 1 Construction Paper Multi Color 9x12 1 pack 2 Dixon Ticonderoga My First Pencil 4 count 1 pack 3 Large Erasers 4 4 Two pocket plastic folders with prongs 2 5 Plastic Supply Box (snap
More informationSolutions to Assignment# 4
Solutions to Assignment# 4 Liana Yepremyan 1 Nov.12: Text p. 651 problem 1 Solution: (a) One example is the following. Consider the instance K = 2 and W = {1, 2, 1, 2}. The greedy algorithm would load
More informationSurface Oriented Traverse for Robust Instance Detection in RGB-D
Surface Oriented Traverse for Robust Instance Detection in RGB-D Ruizhe Wang Gérard G. Medioni Wenyi Zhao Abstract We address the problem of robust instance detection in RGB-D image in the presence of
More informationParameter Estimation with MOCK algorithm
Parameter Estimation with MOCK algorithm Bowen Deng (bdeng2) November 28, 2015 1 Introduction Wine quality has been considered a difficult task that only few human expert could evaluate. However, it is
More informationWarning! Construction Zone: Building Solids from Nets
Brief Overview: Warning! Construction Zone: Building Solids from Nets In this unit the students will be examining and defining attributes of solids and their nets. The students will be expected to have
More informationSome Coupled Fixed Point Theorems on Quasi-Partial b-metric Spaces
International Journal of Mathematical Analysis Vol. 9, 2015, no. 6, 293-306 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/10.12988/ijma.2015.412388 Some Coupled Fixed Point Theorems on Quasi-Partial b-metric
More informationA Distributed Algorithm for the Replica Placement Problem
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS A Distributed Algorithm for the Replica Placement Problem Sharrukh Zaman, Student Member, IEEE, and Daniel Grosu, Senior Member, IEEE Abstract Caching
More informationThe clique number of a random graph in (,1 2) Let ( ) # -subgraphs in = 2 =: ( ) We will be interested in s.t. ( )~1. To gain some intuition note ( )
The clique number of a random graph in (,1 2) Let () # -subgraphs in = 2 =:() We will be interested in s.t. ()~1. To gain some intuition note ()~ 2 =2 and so ~2log. Now let us work rigorously. () (+1)
More informationApplying Supervised Learning
Applying Supervised Learning When to Consider Supervised Learning A supervised learning algorithm takes a known set of input data (the training set) and known responses to the data (output), and trains
More informationarxiv: v1 [cs.ni] 28 Apr 2015
Succint greedy routing without metric on planar triangulations Pierre Leone, Kasun Samarasinghe Computer Science Department, University of Geneva, Battelle A, route de Drize 7, 1227 Carouge, Switzerland
More informationGREP: Guaranteeing Reliability with Enhanced Protection in NFV
GREP: Guaranteeing Reliability with Enhanced Protection in NFV Jingyuan Fan jfan5@buffalo.edu Xiujiao Gao xiujiaog@buffalo.edu Zilong Ye zilongye@buffalo.edu Kui Ren kuiren@buffalo.edu Chaowen Guan chaoweng@buffalo.edu
More informationA Large Dataset of Object Scans
A Large Dataset of Object Scans Sungjoon Choi 1, Qian-Yi Zhou 2, Stephen Miller 3, and Vladlen Koltun 2 1 Google Inc. 2 Intel Labs 3 Fyusion Inc. Abstract. We have created a dataset of more than ten thousand
More informationFOUR EDGE-INDEPENDENT SPANNING TREES 1
FOUR EDGE-INDEPENDENT SPANNING TREES 1 Alexander Hoyer and Robin Thomas School of Mathematics Georgia Institute of Technology Atlanta, Georgia 30332-0160, USA ABSTRACT We prove an ear-decomposition theorem
More informationThe clique number of a random graph in (,1 2) Let ( ) # -subgraphs in = 2 =: ( ) 2 ( ) ( )
1 The clique number of a random graph in (,1 2) Let () # -subgraphs in = 2 =:() We will be interested in s.t. ()~1. To gain some intuition note ()~ 2 =2 and so ~2log. Now let us work rigorously. () (+1)
More informationColored Point Cloud Registration Revisited Supplementary Material
Colored Point Cloud Registration Revisited Supplementary Material Jaesik Park Qian-Yi Zhou Vladlen Koltun Intel Labs A. RGB-D Image Alignment Section introduced a joint photometric and geometric objective
More informationCHAPTER 6 MODIFIED FUZZY TECHNIQUES BASED IMAGE SEGMENTATION
CHAPTER 6 MODIFIED FUZZY TECHNIQUES BASED IMAGE SEGMENTATION 6.1 INTRODUCTION Fuzzy logic based computational techniques are becoming increasingly important in the medical image analysis arena. The significant
More informationII (Sorting and) Order Statistics
II (Sorting and) Order Statistics Heapsort Quicksort Sorting in Linear Time Medians and Order Statistics 8 Sorting in Linear Time The sorting algorithms introduced thus far are comparison sorts Any comparison
More informationAn Efficient Approximation for the Generalized Assignment Problem
An Efficient Approximation for the Generalized Assignment Problem Reuven Cohen Liran Katzir Danny Raz Department of Computer Science Technion Haifa 32000, Israel Abstract We present a simple family of
More informationELEMENTARY NUMBER THEORY AND METHODS OF PROOF
CHAPTER 4 ELEMENTARY NUMBER THEORY AND METHODS OF PROOF Copyright Cengage Learning. All rights reserved. SECTION 4.8 Application: Algorithms Copyright Cengage Learning. All rights reserved. Application:
More informationLecture notes on the simplex method September We will present an algorithm to solve linear programs of the form. maximize.
Cornell University, Fall 2017 CS 6820: Algorithms Lecture notes on the simplex method September 2017 1 The Simplex Method We will present an algorithm to solve linear programs of the form maximize subject
More informationThe competition numbers of complete tripartite graphs
The competition numbers of complete tripartite graphs SUH-RYUNG KIM Department of Mathematics Education, Seoul National University, 151-742, Korea srkim@snuackr YOSHIO SANO Research Institute for Mathematical
More informationChapter S:V. V. Formal Properties of A*
Chapter S:V V. Formal Properties of A* Properties of Search Space Graphs Auxiliary Concepts Roadmap Completeness of A* Admissibility of A* Efficiency of A* Monotone Heuristic Functions S:V-1 Formal Properties
More informationAutomatic Pouring Robot. Akilah Harris-Williams Adam Olmstead Philip Pratt-Szeliga Will Roantree
Automatic Pouring Robot Akilah Harris-Williams Adam Olmstead Philip Pratt-Szeliga Will Roantree Overview Objective and Motivation Mechanical System Modeling, Simulation and Verification Tilt Pan Pouring
More informationCompact Sets. James K. Peterson. September 15, Department of Biological Sciences and Department of Mathematical Sciences Clemson University
Compact Sets James K. Peterson Department of Biological Sciences and Department of Mathematical Sciences Clemson University September 15, 2017 Outline 1 Closed Sets 2 Compactness 3 Homework Closed Sets
More informationCombinatorial Problems on Strings with Applications to Protein Folding
Combinatorial Problems on Strings with Applications to Protein Folding Alantha Newman 1 and Matthias Ruhl 2 1 MIT Laboratory for Computer Science Cambridge, MA 02139 alantha@theory.lcs.mit.edu 2 IBM Almaden
More information