Research Overview Big Data Large Structured into multiple vertical - - PDF document

research overview
SMART_READER_LITE
LIVE PREVIEW

Research Overview Big Data Large Structured into multiple vertical - - PDF document

To create the largest structured domain object database in Asia for rapid & rich mobile search Research Overview Big Data Large Structured into multiple vertical Database of application domains (structured) Media Objects For machine


slide-1
SLIDE 1

To create the largest structured domain object database in Asia for rapid & rich mobile search

Research Overview

2

Big Data

(structured)

Search

(Real World Objects)

  • Structured into multiple vertical

application domains

  • For machine learning & testing

Large Database of Media Objects

  • Fast & rich in content
  • Real‐time & contextual

consumer behaviour analysis

Next‐ Generation Object Search

  • Scalable media search,

processing, & delivery

  • Testbed for experimentation

Media Cloud Platform

slide-2
SLIDE 2

Object Categorisation

  • 2D (Planar) objects: Logos, book

covers, CD covers, labels, coins

  • 3D rigid objects: Cars, hardware,

product packages

  • Deformable objects: Clothes,

shoes, bags, toys

  • Faces: Genders, age groups,

profiles, ethnicity, sentiment

  • Landmark & Scenery

3

Solution Architecture

4

Visual Object Database Infrastructure Cloud Algorithm SDK API API API API Media Analysis Rigid Object Search Media Processing Deformable Object Retrieval Consumer Analysis API Tools Applications Smart Advertising Education Tourism Digital Archive Smart Surveillance E‐Commerce Transportation/Logistics

slide-3
SLIDE 3

ROSE Partner Ecosystem

5

Commercial Partners NTU/PKU Joint‐Lab Large‐Scale Object Dataset & Analytics Mobile Search with Contextual Mobility Media Cloud Platform Research Partners Technology Partners

Supported by Green Expo Technology

Collaboration with Partners

6

Top University in China

  • Structured

Object Database

  • Object Search
  • Media Cloud

Platform #1 Internet Company in Asia

  • Mobile Visual

Search

  • Face Recognition
  • Landmark

Search & Streetview Maps Leading Solution Provider in China

  • Media Cloud

Platform

  • Scalable Media

Search (Faces, Products, Logos)

slide-4
SLIDE 4

Collaboration with Partners

7

A*Star – UIUC Research Centre

  • Joint

Development

  • Shared

Resources

  • Co‐

Supervision of Students

Virtual Expo Platform

  • Logo Search
  • Product

Search

  • Face

Recognition

  • Sentiment

Analysis

Mobile Tradeshow Assistant

  • Mobile Object

Search

  • Sentiment

Analysis

  • Video

Analytics

Contextual Advertising

  • Visual Object

Search

  • Face

Recognition

  • GPU

Computing

Green Expo Technology Green Expo Technology

ROSE Lab: Key Milestones

8 Dec 2012

Grant: IDM Futures Grant: Cloud Computing

Mar 2013 Jul 2013 Aug 2013 Oct 2013

2 SINGA PhD Students RCA Signed

MOU Signed Feb 2013

RCA Signed Visit by Mayor, Jinan City, China RCA Signed Media Exploits 2013

Jan 2014

Grant: Visual Opinion Computation

Nov 2013

Official launch

MOU Signed MOU Signed

Green Expo Technology

Feb 2014

MPEG CDVS Draft Int’l Std

Apr 2014 May 2014

Grant: Deep Learning for Fashion Retrieval Released

WeChat Image Platform

RCA Signed

Sep 2014

Launch: WeMage Challenge 2014

slide-5
SLIDE 5

RESEARCH OVERVIEW

9

P3: Media Cloud Platform P1: Structured Object Database P2: Engines Search Object Big Data Search Cloud Computing

P1: Structured Object Database

  • Large‐scale domain object database and analytics

– Two‐layer data solutions: collected and on‐demand – Large‐scale data structure, tagging, indexing, mining and storage – Collect and link multi‐modal data to facilitate fast mobile search on object database

  • Domains

– eCommerce & Contextual Advertising – Tourism & Transport – Life Style & Hobbies

10

P3: Media Cloud Platform

P1: Structure d Object Database

P2: Engines Search Object

slide-6
SLIDE 6

Large‐Scale Structured Object Database

mCommerce & Digital Advertising

Handbag Shoes Clothes Book cover Trademark & Logo

Tourism & Transport

Landmark Place of interest Road signs

Lifestyle & Hobbies

Fish Fruit Cat Car

50M structured objects (clean)

‐ 1,000,000 2,000,000 3,000,000 4,000,000 5,000,000 6,000,000 7,000,000 8,000,000 eCommerce & Digital Advertising Tourism Lifestyle & Hobbies #Images

Structured Object Database (Apr 2014)

P2: Object Search

  • Scalable Object Search

– Efficient context‐aware, goal‐driven mobile object search – User‐contributed live data search through social networks – Develop real‐time location‐ and situation‐based data analytics on user’s preferences and behaviour

12

P3: Media Cloud Platform P1: Structured Object Database

P2: Engines Search Object

slide-7
SLIDE 7

Whole Image Retrieval

……

Query Database Ranked Images

+ =

Visual Object Search

……

Query Database

+ =

Ranked Detections from Cluttered Images

slide-8
SLIDE 8

Branded Bag Recognition

  • For people, use bag image to find bag

Street Scene Online shops

M40249 TWD: $3800

LV Artsy mm USD: 100 Wholesale fashion USD:110

Artsy MM m40249

Identifying people Retrieving images of a person

Face Recognition & Retrieval

slide-9
SLIDE 9

P3: Media Cloud Platform

  • Testbed

– Design an innovative multimedia cloud platform as a test‐bed for large‐scale applications

  • GPUs

– For accelerating machine learning and object search

  • Media Processing Technologies

– Develop new media processing technologies in transcoding, visual analytics and quality assessment

17

P3: Media Cloud Platform

P1: Structured Object Database P2: Engines Search Object

ROSE Lab Physical Infrastructure

18

IT Cloud

  • P3 Cloud cluster

– 7x Dell R720 2U server without GPU – 84x Intel SNB Processor @2.3GHz – 434GB RAM @ 1600MHz

  • Network Infrastructure

– 1x CISCO Catalyst 3750‐x Layer‐3 Switch, 48 port (with 1 Gbps link to NTU Campus Network) – 5x CISCO Catalyst 3560‐x Layer‐2 IP‐based Switch, 48 port

HPC Cloud

  • GPU Cloud Cluster

– 1x Dell R720 2U server with 2x K20m GPU – 3x Dell R720 2U server with 1x K20m GPU – 1x Dell R720 2U server with 1x Intel Xeon Phil MIC

Big Data

  • P1 Database cluster

– 1x HP Proliant 2U server – 1x JBOD Storage Chasis – 1x D‐Link NAS with 16TB storage

  • Storage Cluster

– 4x Novatte 12‐Bay Storage Server – Up to 160TB Storage Capacity

Experimental Zone

  • P2 Development cluster

– 1x HP Proliant 2U server

  • Experimental GPU Platform

– GPU Workstations: 2 x Titan Black, 2 x GTX770

slide-10
SLIDE 10

ROSE Systems Infographic

19

Servers & Storage

  • 23 Servers &

Workstations

  • 135TB Storage

CPUs

  • 41 CPUs
  • 244 Physical

cores

  • 488 Hyper‐

threaded Logical cores

GPUs

  • Includes Tesla K20 &

K40, Titan Black, GTX770, GTX645,…

  • 37 GPUs
  • 42,048 CUDA

cores

ROSE Lab ‐ Summary

20

Capacity & Capability

18 RSEs 32 PhD Students 83 Students Trained

Intellectual Property

1 Draft International

Standard

1 Provisional Patent 4 Technology Disclosures 28 Publications

Industry Engagement

$7.1M Co‐Funding 7 Partners 19 Projects 2 Products & Services

slide-11
SLIDE 11

Thank You

rose.ntu.edu.sg/index.html

21