Xue Xiangyang - Fudan University

•

2 likes•1,027 views

This document summarizes the research topics and laboratories of the School of Computer Science at FDU, led by Professor Xiangyang Xue. The school's research includes natural language processing, multimodal dialogue, image classification, and cross-media search. Key laboratories study intelligent media computing, databases, software engineering, and information security. Application areas mentioned include interactive TV, education/gaming robots, and assistant technologies for future smart homes.

Research of Intelligent Media Computing
and its Application
Dr. Xiangyang XUE
Professor & Vice Dean, School of
Computer Science

Outline

 Introduction of School of Computer Science
 Research Topics in our Laboratory
 RT1 Natural Language Processing
 RT2 Multimodal Dialog
 RT3 Image Classification
 RT4 Cross-Media Search

 Assistant Living Technologies in Future Home
 APP1 IPTV ~ video search engine
 APP2 Robot ~ multimodal dialog

2009-5-21 2 FDU - Xiangyang XUE

School – Staff Members & Students

Staff Members

 Totally 160 staff members
 19 full professors
 39 associate professors Students（full time）

 Undergraduates: 1100
 Master students: 400
 PhD Students: 170

2009-5-21 3 FDU - Xiangyang XUE

School – Research Areas

OS: virtualization
Multimedia
Software Engineering
Computer vision
Database

Machine Learning
Compiler

NLP & IR
CSCW

Theory: Complexity, Cryptography & Algorithms

2009-5-21 4 FDU - Xiangyang XUE

School – Research Labs

Shanghai Key Laboratory for
Intelligent Information Processing

 Laboratory of Intelligent Media Computing
 Laboratory of Database Technology

 Laboratory of System Software and Software
Engineering
 Laboratory of Information Security
 Laboratory of Embedded System

2009-5-21 5 FDU - Xiangyang XUE

People in our Laboratory
Dr Xipeng QIU
Lab of
Dr Xuanjing
HUANG
Intelligent
Media Computing
Text

Dr Yuefei GUO Dr Yaqian ZHOU Dr Cheng JIN

Image
Machine
Dr Yuejie ZHANG Video
Learning

Dr Mingmin
CHI
Dr Xiangyang XUE

Dr Hong LU

Dr Wei Zhang
Audio
PhD Students：12
Master Students：40

2009-5-21 Dr Wei LI 6 FDU - Xiangyang XUE

Projects & Publications in our Laboratory

 Projects
 Natural Science Foundation of China
 Ministry of Science and Technology
 Science and Technology Commission of Shanghai
Municipality
 Industries
 Publications
 Journals: IEEE TMM, TKDE, TCAS-VT, TIP; Pattern
Recognition, Neural Networks, Information Processing and
Management etc
 Conferences: ACM MM, ICCV, ICML, IJCAI ,ACL, etc

2009-5-21 7 FDU - Xiangyang XUE

RT1 Natural Language Processing

Current Works
Word Syntax Discourse
 Question answering
 Open domain
POS Tag
Named Entity
Recognition  Trec 2008, Top 2

Chinese word  Sentiment analysis
Chunking Coreference
segment
 Product review
Discourse
Parsing
Segment  Trec Blog, Top 5

 Text
summarization
Fundamental researches in NLP
 Information Extraction

2009-5-21 8 FDU - Xiangyang XUE

RT2 Multimodal Dialogue System
Application：Robot

Knowledge
Knowledge Knowledge Device
Knowledge Device API
Sources
Sources Manager Manager
Sources

Dialogue
Dialogue Activity
Manager
Move Tree Tree Device
Devices
Device
s
s
Dialogue
Move
Engine
Multimodal Response
Fusion Generator

NLU Gesture NLG Animation

ASR TTS
2009-5-21 9 FDU - Xiangyang XUE

RT3 Image Classification

Wedding

Activity

Party

Coworker
People

Family

Snake
Animal

Lion

2009-5-21 11 FDU - Xiangyang XUE

RT4 Cross-Media Search for iTV

• Video Shot Boundary Detection
· 镜头1 镜头2

•
· 镜头1 镜头2
Face Detection and Recognition
镜头1 镜头2

镜头1 镜头2

• Video OCR / ASR

Application

• Correlation Analysis

Movie: Royal Casino Role: James Bond

2009-5-21 12 FDU - Xiangyang XUE

Shanghai Industry Intel Developer Forum
Fair 2008 (IDF) 2008

 Surveillance in Home
 Interactive TV
 Education and Gaming for Children
FUWA Robot
 Multimodal HCI/Dialog

2009-5-21 13 FDU - Xiangyang XUE

Assistant Living Technologies in Future Home
2009-5-21 14 FDU - Xiangyang XUE

The presentation was delivered by FORTH at the 3rd International Workshop on the role of Semantic Web in Provenance Management 2012 (SWPM2012) in Heraklion, Greece on 28th of May 2012. Abstract: Workflow systems can produce very large amounts of provenance information. In this paper we introduce provenance-based inference rules as a means to reduce the amount of provenance information that has to be stored, and to ease quality control (e.g., corrections). We motivate this kind of (provenance) inference and identify a number of basic inference rules over a conceptual model appropriate for representing provenance. The proposed inference rules concern the interplay between (i) actors and carried out activities, (ii) activities and devices that were used for such activities, and, (iii) the presence of information objects and physical things at events. However, since a knowledge base is not static but it changes over time for various reasons, we also study how we can satisfy change requests while supporting and respecting the aforementioned inference rules. Towards this end, we elaborate on the specification of the required change operations.

Ross Tredinnick - Rebecca J. Holz Research Data Management Talk 4/16/2013

rossTnick

Efficient implementations of machine vision algorithms using a dynamically ty...

Jan Wedekind

Current machine vision systems (or at least their performance critical parts) are predominantly implemented using statically typed programming languages such as C, C++, or Java. Statically typed languages however are unsuitable for development and maintenance of large scale systems. When choosing a programming language, dynamically typed languages are usually not considered due to their lack of support for high-performance array operations. This thesis presents efficient implementations of machine vision algorithms with the (dynamically typed) Ruby programming language. The Ruby programming language was used, because it has the best support for meta-programming among the currently popular programming languages. Although the Ruby programming language was used, the approach presented in this thesis could be applied to any programming language which has equal or stronger support for meta-programming (e.g. Racket (former PLT Scheme)). A Ruby library for performing I/O and array operations was developed as part of this thesis. It is demonstrated how the library facilitates concise implementations of machine vision algorithms commonly used in industrial automation. I.e. this thesis is about a different way of implementing machine vision systems. The work could be applied to prototype and in some cases implement machine vision systems in industrial automation and robotics. The development of real-time machine vision software is facilitated as follows 1. A JIT compiler is used to achieve real-time performance. It is demonstrated that the Ruby syntax is sufficient to integrate the JIT compiler transparently. 2. Various I/O devices are integrated for seamless acquisition, display, and storage of video and audio data. In combination these two developments preserve the expressiveness of the Ruby programming language while providing good run-time performance of the resulting implementation. To validate this approach, the performance of different operations is compared with the performance of equivalent C/C++ programs.

Designing Experiment Agnostic Remote Laboratories

Pablo Orduña

Information technologybikram ...

Vdfp audio and video fingerprinting

WietskevdHeuvel

P-Plan

dgarijo

Provenance models are crucial for describing experimental results in science. The W3C Provenance Working Group has recently released the PROV family of specifications for provenance on the Web. While provenance focuses on what is executed, it is important in science to publish the general methods that describe scientific processes at a more abstract and general level. In this paper, we propose P-PLAN, an extension of PROV to represent plans that guid-ed the execution and their correspondence to provenance records that describe the execution itself. We motivate and discuss the use of P-PLAN and PROV to publish scientific workflows as Linked Data.

The digital universe is booming, especially metadata and user-generated data. This raises strong challenges in order to identify the relevant portions of data which are relevant for a particular problem and to deal with the lifecycle of data. Finer grain problems include data evolution and the potential impact of change in the applications relying on the data, causing decay. The management of scientific data is especially sensitive to this. We present the Research Objects concept as the means to indentify and structure relevant data in scientific domains, addressing data as first-class citizens. We also identify and formally represent the main reasons for decay in this domain and propose methods and tools for their diagnosis and repair, based on provenance information. Finally, we discuss on the application of these concepts to the broader domain of the Web of Data: Data with a Purpose.

2013-01-17 Research Object

Stian Soiland-Reyes

Deroure Repo3guestd9aa5

Deroure Repo3guru122

Book of abstract volume 8 no 9 ijcsis december 2010Oladokun Sulaiman

EGIforum-Amsterdam-15-Sep2010

Alex Hardisty

Semantics is not a luxuryPaolo Ciccarese

Jubatus: Realtime deep analytics for BIgData@Rakuten Technology Conference 2012

Preferred Networks

Currently, we face new challenges in realtime analytics of BigData, such as social monitoring, M2M sensor, online advertising optimization, smart energy management and security monitoring. To analyze these data, scalable machine learning technologies are essential. Jubatus is the open source platform for online distributed machine learning on the data streams of BigData. we explain the inside technologies of Jubatus and show how jubatus can achieve realtime analytics in various problems.

Initial steps towards a production platform for DNA sequence analysis on the ...

Barbera van Schaik

Xu Xing: EasyGenomics – Next Generation Bioinformatics on the Cloud

GigaScience, BGI Hong Kong

Open Data: Ready Set Go

Paul Groth

International Collaboration

National Science and Technology Development Agency (NSTDA) - Thailand

MayaNASAPMC

What's hot

Will RSpec help us to do better science

maxott

discopen

Jisc

CambridgeIP Fact-based Strategy Development: Accelerating your out-licensing

CambridgeIP Ltd

AI and Machine Learning PG program

MamathaSharma4

VBPR 1st seminarAhmed Abd El-Fattah

Paper talk: Idcc 11

Paolo Missier

Semantic Model-driven Engineering

Steffen Staab

Accelrys Announces Experiment Knowledge Base (EKB) for Enterprise Lab Management

BIOVIA

Collaboration and Sharing

Jisc

Scientific data management from the lab to the web

Jose Manuel Gómez-Pérez

2013-01-17 Research Object

Stian Soiland-Reyes

What's hot (11)

Will RSpec help us to do better science

discopen

CambridgeIP Fact-based Strategy Development: Accelerating your out-licensing

AI and Machine Learning PG program

VBPR 1st seminar

Paper talk: Idcc 11

Semantic Model-driven Engineering

Accelrys Announces Experiment Knowledge Base (EKB) for Enterprise Lab Management

Collaboration and Sharing

Scientific data management from the lab to the web

2013-01-17 Research Object

Similar to Xue Xiangyang - Fudan University

Deroure Repo3guestd9aa5

Deroure Repo3guru122

Book of abstract volume 8 no 9 ijcsis december 2010Oladokun Sulaiman

EGIforum-Amsterdam-15-Sep2010

Alex Hardisty

Semantics is not a luxuryPaolo Ciccarese

Jubatus: Realtime deep analytics for BIgData@Rakuten Technology Conference 2012

Preferred Networks

Initial steps towards a production platform for DNA sequence analysis on the ...

Barbera van Schaik

Xu Xing: EasyGenomics – Next Generation Bioinformatics on the Cloud

GigaScience, BGI Hong Kong

Open Data: Ready Set Go

Paul Groth

International Collaboration

National Science and Technology Development Agency (NSTDA) - Thailand

MayaNASAPMC

pythonUnit_1forprogrammin launguage.pptx

bharathece1

IRJET- Design and Development of Tesseract-OCR Based Assistive System to Conv...

IRJET Journal

The LEGO Maturity & Capability Model Approach

Luigi Buglione

“Maturity model” (MM) (based on Crosby’s original idea) has been one of the main buzzwords over the past 20 years. A variety of MMs have been created in several application domains, from Software Engineering to Contract Management. Despite several models intending to cover the same domain, their PRMs (Process Reference Models) typically have different scopes, do not always cover the same set of processes, or have different levels of depth, or do not express the same level of granularity when describing concepts. Thus some important questions from the MM users’ viewpoint arise: how to choose the right models for our needs? After selecting those models, how to build a new, tailored MM based on several sources and customized to a specific domain? This paper motivates these important questions and proposes a way to choose, combine and adapt the contents from multiple MMs within a generic-domain approach we call ‘LEGO’ (Living EnGineering prOcess), based upon the well-known kids’ toy that stimulates creativity through combining different bricks. We present three case studies, one of them based upon the development of the Medi SPICE model, illustrating how the proposed approach may be used to develop MCM (Maturity & Capabilty Models) in this context.

HHS Fusion Form

Heather Blanchard

NLP on Hadoop: A Distributed Framework for NLP-Based Keyword and Keyphrase Ex...

Paolo Nesi

Abstract—The recent growth of the World Wide Web at increasing rate and speed and the number of online available resources populating Internet represent a massive source of knowledge for various research and business interests. Such knowledge is, for the most part, embedded in the textual content of web pages and documents, which is largely represented as unstructured natural language formats. In order to automatically ingest and process such huge amounts of data, single-machine, non-distributed architectures are proving to be inefficient for tasks like Big Data mining and intensive text processing and analysis. Current Natural Language Processing (NLP) systems are growing in complexity, and computational power needs have been significantly increased, requiring solutions such as distributed frameworks and parallel computing programming paradigms. This paper presents a distributed framework for executing NLP related tasks in a parallel environment. This has been achieved by integrating the APIs of the widespread GATE open source NLP platform in a multi-node cluster, built upon the open source Apache Hadoop file system. The proposed framework has been evaluated against a real corpus of web pages and documents.

Acknowledge 03 Ramit Geert Thienpontimec.archive

Aalto stanford webinar-on collaborative working ennvironments 2013

Matti Vartiainen

Open hpi semweb-06-part2Nadine Ludwig

Semantic Web powering Enterprise and Web Applications

Amit Sheth

Similar to Xue Xiangyang - Fudan University (20)

Deroure Repo3

Book of abstract volume 8 no 9 ijcsis december 2010

EGIforum-Amsterdam-15-Sep2010

Semantics is not a luxury

Jubatus: Realtime deep analytics for BIgData@Rakuten Technology Conference 2012

Initial steps towards a production platform for DNA sequence analysis on the ...

Xu Xing: EasyGenomics – Next Generation Bioinformatics on the Cloud

Open Data: Ready Set Go

International Collaboration

Maya

pythonUnit_1forprogrammin launguage.pptx

IRJET- Design and Development of Tesseract-OCR Based Assistive System to Conv...

The LEGO Maturity & Capability Model Approach

HHS Fusion Form

NLP on Hadoop: A Distributed Framework for NLP-Based Keyword and Keyphrase Ex...

Acknowledge 03 Ramit Geert Thienpont

Aalto stanford webinar-on collaborative working ennvironments 2013

Open hpi semweb-06-part2

Semantic Web powering Enterprise and Web Applications

More from Seismonaut

Hvordan sælger man kreativitet uden for vores egne cirkler?

Seismonaut

Headstart Morgenseminar: Growth Hacking

Seismonaut

Headstart Morgenseminar: Growth Hacking

Seismonaut

Claus Hovge Andersen talte om growth hacking i NORDJYSKE medier til Headstarts morgenseminar d. 20. april 2017. Claus Hovge Andersen har arbejdet med digitale medier de sidste 18 år, og har blandt andet arbejdet med ecommerce, mobil teknologi og de sidste ti år med digitale forretningsmodeller hos blandt andet Bilbasen.dk, dba.dk, eBay Classifieds. De seneste 6 år har Claus Hovge Andersen arbejdet med digital transformation i mediebranchen, herunder tidligere Jyllands-Posten og nu i NORDJYSKE Medier. Og udover dette har Claus Hovge Andersen siddet i bestyrelsen for flere digitale virksomheder som jobzonen.dk, bilzonen.dk og Watch Medier. Er p.t. aktiv i bestyrelser for flere internetvirksomheder.

Headstart Morgenseminar: Growth Hacking

Seismonaut

Serieiværksætter Thomas Madsen-Mygdal fortalte om vækst til Headstarts morgenseminar d. 20. april 2017. Thomas Madsen-Mygdal er en dansk designer og iværksætter med en lang og imponerende historik. Thomas var frontløber for internettet, hvor han som medstifter af den første kommercielle danske internetvirksomhed, Mondo, var med til at bringe internettet til Danmark. Senere var Thomas med til at lave virksomheden Podio, som forandrede måden folk arbejder på. I dag står Thomas i spidsen for TwentyThree, som arbejder med at ændre måden virksomheder kommunikerer via video. Thomas er ligeledes igangsætter og bestyrelsesformand for startup organisationen #CPHFTW. Derudover har han også modtaget IT-Branchens og FDIHs ærespriser.

Headstart Morgenseminar: Working as a Network

Seismonaut

Sælg en oplevelse - om markedsføring af NorthSide på sociale medier

Seismonaut

Headstart Network morgenseminar 13/9 2016: Hvad er tillid?

Seismonaut

I den digitale tidsalder er anmeldelser, reviews, likes og kommentarer med til at skabe en ny form for økonomi, hvor tillid er den valuta vi sparer op, rejser rundt på nettet med og betaler for vores ydelser med. Har man kun dårlige anmeldelser med i bagagen, er der ingen der vil handle, men har folk udtalt sig rosende om en, er det nemt at bruge nettets mange sociale platforme. Den transparente virkelighed, som alle uundgåeligt er en del af, skaber nye konsekvenser for både virksomheder og individer. Og det handler ikke bare om deleøkonomi - nej, tænk meget større - det er på mange måder den digitale fremtid for os alle, der er i spil. Men tillid som fænomen er ikke nyt. Så hvad er tillid egentlig? Hvilken betydning har det for vores samfund og økonomi? Og er tilliden i samfundet i forfald eller på vej op? Disse spørgsmål svarede Christian Bjørnskov, professor i økonomi ved Aarhus Universitet, på til Headstarts morgenseminar.

Den digitale Turist - Det ambitiøse værtskab

Seismonaut

Den digitale turist

Seismonaut

Det ambitiøse værtsskab - digitale touchpoints

Seismonaut

Det ambitiøse værtskab - det fysiske møde med gæsten

Seismonaut

Headstart_Creuna_Slides

Seismonaut

Headstart_Envision_Slides

Seismonaut

Veronika Janeckova & Nelson Sachse, Made by many - Headstart d. 2. juni 2015

Seismonaut

Kasper Wodstrup Rost, Delta Projects - Headstart d. 2. juni 2015

Seismonaut

Cerys Hearsey, Post*Shift - Headstart

Seismonaut

We all know that the world is changing quicker than ever before, and that businesses are always looking for new ways to create advantages for themselves. Cerys will explore the market dynamics that are combining to create a volatile, uncertain, complex and ambiguous operating environment for businesses and the new types of organisational risk that these are creating. Then, looking at some of the most innovative businesses in the world, highlight some of the new business models, organisational structures and ways of working that are coming together to help transform companies for the 21st century.

Creative Executive Club - Johanne Bruun Sørensen, Hello Monday

Seismonaut

Johanne Bruun Sørensen fra Hello Monday holdte et inspirerende oplæg på Creative Executive Clubs morgenseminar i Aarhus onsdag d. 15. april 2015. Creative Executive Club morgenseminarer byder på internationale og nationale eksperter, meningsdannere og kreative topledere med viden om vækst, internationalisering og fremtidens ledelses- og organisationsformer i de kreative industrier. Creative Executive Clubs mål er at sætte barren endnu højere i de kreative brancher. Vi skal udvikle stærke forretningsområder og -modeller særligt for de kreative erhverv. Og vi skal gøre det ved at videndele og skabe synergier på tværs af brancher. Creative Executive Club er et samarbejde mellem Erhverv Aarhus og More.Creative.

Creative Executive Club - Stephen Burrell, Kopenhagen Fur

Seismonaut

Stephen Burrell fra Kopenhagen Fur holdte et inspirerende oplæg på Creative Executive Clubs morgenseminar onsdag d. 15. april 2015. Creative Executive Club morgenseminarer byder på internationale og nationale eksperter, meningsdannere og kreative topledere med viden om vækst, internationalisering og fremtidens ledelses- og organisationsformer i de kreative industrier. Creative Executive Clubs mål er at sætte barren endnu højere i de kreative brancher. Vi skal udvikle stærke forretningsområder og -modeller særligt for de kreative erhverv. Og vi skal gøre det ved at videndele og skabe synergier på tværs af brancher. Creative Executive Club er et samarbejde mellem Erhverv Aarhus og More.Creative.

Sociale medier i et offentligt perspektiv 2015

Seismonaut

Digitalisering handler om mennesker

Seismonaut

More from Seismonaut (20)

Hvordan sælger man kreativitet uden for vores egne cirkler?

Headstart Morgenseminar: Growth Hacking

Headstart Morgenseminar: Working as a Network

Sælg en oplevelse - om markedsføring af NorthSide på sociale medier

Headstart Network morgenseminar 13/9 2016: Hvad er tillid?

Den digitale Turist - Det ambitiøse værtskab

Den digitale turist

Det ambitiøse værtsskab - digitale touchpoints

Det ambitiøse værtskab - det fysiske møde med gæsten

Headstart_Creuna_Slides

Headstart_Envision_Slides

Veronika Janeckova & Nelson Sachse, Made by many - Headstart d. 2. juni 2015

Kasper Wodstrup Rost, Delta Projects - Headstart d. 2. juni 2015

Cerys Hearsey, Post*Shift - Headstart

Creative Executive Club - Johanne Bruun Sørensen, Hello Monday

Creative Executive Club - Stephen Burrell, Kopenhagen Fur

Sociale medier i et offentligt perspektiv 2015

Digitalisering handler om mennesker

Recently uploaded

Securing your Kubernetes cluster_ a step-by-step guide to success !

KatiaHIMEUR1

Today, after several years of existence, an extremely active community and an ultra-dynamic ecosystem, Kubernetes has established itself as the de facto standard in container orchestration. Thanks to a wide range of managed services, it has never been so easy to set up a ready-to-use Kubernetes cluster. However, this ease of use means that the subject of security in Kubernetes is often left for later, or even neglected. This exposes companies to significant risks. In this talk, I'll show you step-by-step how to secure your Kubernetes cluster for greater peace of mind and reliability.

Introduction to CHERI technology - Cybersecurity

mikeeftimakis1

GraphRAG is All You need? LLM & Knowledge Graph

Guy Korland

Guy Korland, CEO and Co-founder of FalkorDB, will review two articles on the integration of language models with knowledge graphs. 1. Unifying Large Language Models and Knowledge Graphs: A Roadmap. https://arxiv.org/abs/2306.08302 2. Microsoft Research's GraphRAG paper and a review paper on various uses of knowledge graphs: https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/

Communications Mining Series - Zero to Hero - Session 1

DianaGray10

This session provides introduction to UiPath Communication Mining, importance and platform overview. You will acquire a good understand of the phases in Communication Mining as we go over the platform with you. Topics covered: • Communication Mining Overview • Why is it important? • How can it help today’s business and the benefits • Phases in Communication Mining • Demo on Platform overview • Q/A

Video Streaming: Then, Now, and in the Future

Alpen-Adria-Universität

In his public lecture, Christian Timmerer provides insights into the fascinating history of video streaming, starting from its humble beginnings before YouTube to the groundbreaking technologies that now dominate platforms like Netflix and ORF ON. Timmerer also presents provocative contributions of his own that have significantly influenced the industry. He concludes by looking at future challenges and invites the audience to join in a discussion.

GridMate - End to end testing is a critical piece to ensure quality and avoid...

ThomasParaiso2

GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...

Neo4j

Dr. Sean Tan, Head of Data Science, Changi Airport Group Discover how Changi Airport Group (CAG) leverages graph technologies and generative AI to revolutionize their search capabilities. This session delves into the unique search needs of CAG’s diverse passengers and customers, showcasing how graph data structures enhance the accuracy and relevance of AI-generated search results, mitigating the risk of “hallucinations” and improving the overall customer journey.

LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...

DanBrown980551

Do you want to learn how to model and simulate an electrical network from scratch in under an hour? Then welcome to this PowSyBl workshop, hosted by Rte, the French Transmission System Operator (TSO)! During the webinar, you will discover the PowSyBl ecosystem as well as handle and study an electrical network through an interactive Python notebook. PowSyBl is an open source project hosted by LF Energy, which offers a comprehensive set of features for electrical grid modelling and simulation. Among other advanced features, PowSyBl provides: - A fully editable and extendable library for grid component modelling; - Visualization tools to display your network; - Grid simulation tools, such as power flows, security analyses (with or without remedial actions) and sensitivity analyses; The framework is mostly written in Java, with a Python binding so that Python developers can access PowSyBl functionalities as well. What you will learn during the webinar: - For beginners: discover PowSyBl's functionalities through a quick general presentation and the notebook, without needing any expert coding skills; - For advanced developers: master the skills to efficiently apply PowSyBl functionalities to your real-world scenarios.

By Design, not by Accident - Agile Venture Bolzano 2024

Pierluigi Pugliese

FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf

FIDO Alliance

The Future of Platform Engineering

Jemma Hussein Allen

UiPath Test Automation using UiPath Test Suite series, part 4

DianaGray10

Welcome to UiPath Test Automation using UiPath Test Suite series part 4. In this session, we will cover Test Manager overview along with SAP heatmap. The UiPath Test Manager overview with SAP heatmap webinar offers a concise yet comprehensive exploration of the role of a Test Manager within SAP environments, coupled with the utilization of heatmaps for effective testing strategies. Participants will gain insights into the responsibilities, challenges, and best practices associated with test management in SAP projects. Additionally, the webinar delves into the significance of heatmaps as a visual aid for identifying testing priorities, areas of risk, and resource allocation within SAP landscapes. Through this session, attendees can expect to enhance their understanding of test management principles while learning practical approaches to optimize testing processes in SAP environments using heatmap visualization techniques What will you get from this session? 1. Insights into SAP testing best practices 2. Heatmap utilization for testing 3. Optimization of testing processes 4. Demo Topics covered: Execution from the test manager Orchestrator execution result Defect reporting SAP heatmap example with demo Speaker: Deepak Rai, Automation Practice Lead, Boundaryless Group and UiPath MVP

GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...

Neo4j

Sudheer Mechineni, Head of Application Frameworks, Standard Chartered Bank Discover how Standard Chartered Bank harnessed the power of Neo4j to transform complex data access challenges into a dynamic, scalable graph database solution. This keynote will cover their journey from initial adoption to deploying a fully automated, enterprise-grade causal cluster, highlighting key strategies for modelling organisational changes and ensuring robust disaster recovery. Learn how these innovations have not only enhanced Standard Chartered Bank’s data infrastructure but also positioned them as pioneers in the banking sector’s adoption of graph technology.

Epistemic Interaction - tuning interfaces to provide information for AI support

Alan Dix

Paper presented at SYNERGY workshop at AVI 2024, Genoa, Italy. 3rd June 2024 https://alandix.com/academic/papers/synergy2024-epistemic/ As machine learning integrates deeper into human-computer interactions, the concept of epistemic interaction emerges, aiming to refine these interactions to enhance system adaptability. This approach encourages minor, intentional adjustments in user behaviour to enrich the data available for system learning. This paper introduces epistemic interaction within the context of human-system communication, illustrating how deliberate interaction design can improve system understanding and adaptation. Through concrete examples, we demonstrate the potential of epistemic interaction to significantly advance human-computer interaction by leveraging intuitive human communication strategies to inform system design and functionality, offering a novel pathway for enriching user-system engagements.

FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf

FIDO Alliance

Elizabeth Buie - Older adults: Are we really designing for our future selves?

Nexer Digital

FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf

FIDO Alliance

Generative AI Deep Dive: Advancing from Proof of Concept to Production

Aggregage

PCI PIN Basics Webinar from the Controlcase Team

ControlCase

20240607 QFM018 Elixir Reading List May 2024

Matthew Sinclair

Recently uploaded (20)

Securing your Kubernetes cluster_ a step-by-step guide to success !

Introduction to CHERI technology - Cybersecurity

GraphRAG is All You need? LLM & Knowledge Graph

Communications Mining Series - Zero to Hero - Session 1

Video Streaming: Then, Now, and in the Future

GridMate - End to end testing is a critical piece to ensure quality and avoid...

GraphSummit Singapore | Enhancing Changi Airport Group's Passenger Experience...

LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...

By Design, not by Accident - Agile Venture Bolzano 2024

FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf

The Future of Platform Engineering

UiPath Test Automation using UiPath Test Suite series, part 4

GraphSummit Singapore | Graphing Success: Revolutionising Organisational Stru...

Epistemic Interaction - tuning interfaces to provide information for AI support

FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf

Elizabeth Buie - Older adults: Are we really designing for our future selves?

FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf

Generative AI Deep Dive: Advancing from Proof of Concept to Production

PCI PIN Basics Webinar from the Controlcase Team

20240607 QFM018 Elixir Reading List May 2024

Xue Xiangyang - Fudan University

1. Research of Intelligent Media Computing and its Application Dr. Xiangyang XUE Professor & Vice Dean, School of Computer Science

2. Outline  Introduction of School of Computer Science  Research Topics in our Laboratory  RT1 Natural Language Processing  RT2 Multimodal Dialog  RT3 Image Classification  RT4 Cross-Media Search  Assistant Living Technologies in Future Home  APP1 IPTV ~ video search engine  APP2 Robot ~ multimodal dialog 2009-5-21 2 FDU - Xiangyang XUE

3. School – Staff Members & Students Staff Members  Totally 160 staff members  19 full professors  39 associate professors Students（full time）  Undergraduates: 1100  Master students: 400  PhD Students: 170 2009-5-21 3 FDU - Xiangyang XUE

4. School – Research Areas OS: virtualization Multimedia Software Engineering Computer vision Database Machine Learning Compiler NLP & IR CSCW Theory: Complexity, Cryptography & Algorithms 2009-5-21 4 FDU - Xiangyang XUE

5. School – Research Labs Shanghai Key Laboratory for Intelligent Information Processing  Laboratory of Intelligent Media Computing  Laboratory of Database Technology  Laboratory of System Software and Software Engineering  Laboratory of Information Security  Laboratory of Embedded System 2009-5-21 5 FDU - Xiangyang XUE

6. People in our Laboratory Dr Xipeng QIU Lab of Dr Xuanjing HUANG Intelligent Media Computing Text Dr Yuefei GUO Dr Yaqian ZHOU Dr Cheng JIN Image Machine Dr Yuejie ZHANG Video Learning Dr Mingmin CHI Dr Xiangyang XUE Dr Hong LU Dr Wei Zhang Audio PhD Students：12 Master Students：40 2009-5-21 Dr Wei LI 6 FDU - Xiangyang XUE

7. Projects & Publications in our Laboratory  Projects  Natural Science Foundation of China  Ministry of Science and Technology  Science and Technology Commission of Shanghai Municipality  Industries  Publications  Journals: IEEE TMM, TKDE, TCAS-VT, TIP; Pattern Recognition, Neural Networks, Information Processing and Management etc  Conferences: ACM MM, ICCV, ICML, IJCAI ,ACL, etc 2009-5-21 7 FDU - Xiangyang XUE

8. RT1 Natural Language Processing Current Works Word Syntax Discourse  Question answering  Open domain POS Tag Named Entity Recognition  Trec 2008, Top 2 Chinese word  Sentiment analysis Chunking Coreference segment  Product review Discourse Parsing Segment  Trec Blog, Top 5  Text summarization Fundamental researches in NLP  Information Extraction 2009-5-21 8 FDU - Xiangyang XUE

9. RT2 Multimodal Dialogue System Application：Robot Knowledge Knowledge Knowledge Device Knowledge Device API Sources Sources Manager Manager Sources Dialogue Dialogue Activity Manager Move Tree Tree Device Devices Device s s Dialogue Move Engine Multimodal Response Fusion Generator NLU Gesture NLG Animation ASR TTS 2009-5-21 9 FDU - Xiangyang XUE

10. RT2 Multimodal Dialogue System Application：Robot Knowledge Knowledge Knowledge Device Knowledge Device API Sources Sources Manager Manager Sources Dialogue  NLU Dialogue Activity Manager Move Tree Tree Device Devices Device  Spoken Language s s  Unknown words Dialogue  Ontology Move Engine Multimodal Response  Dialogue Move Engine Fusion Generator  Domain adaptation  Semi-Supervised NLU Gesture NLG Methods Animation ASR TTS 2009-5-21 10 FDU - Xiangyang XUE

11. RT3 Image Classification Wedding Activity Party Coworker People Family Snake Animal Lion 2009-5-21 11 FDU - Xiangyang XUE

12. RT4 Cross-Media Search for iTV • Video Shot Boundary Detection · 镜头1 镜头2 • · 镜头1 镜头2 Face Detection and Recognition 镜头1 镜头2 镜头1 镜头2 • Video OCR / ASR Application • Correlation Analysis Movie: Royal Casino Role: James Bond 2009-5-21 12 FDU - Xiangyang XUE

13. Shanghai Industry Intel Developer Forum Fair 2008 (IDF) 2008  Surveillance in Home  Interactive TV  Education and Gaming for Children FUWA Robot  Multimodal HCI/Dialog 2009-5-21 13 FDU - Xiangyang XUE

14. Assistant Living Technologies in Future Home 2009-5-21 14 FDU - Xiangyang XUE

15. Thank You！ Q/A？

Xue Xiangyang - Fudan University

Recommended

Recommended

More Related Content

What's hot

What's hot (11)

Similar to Xue Xiangyang - Fudan University

Similar to Xue Xiangyang - Fudan University (20)

More from Seismonaut

More from Seismonaut (20)

Recently uploaded

Recently uploaded (20)

Xue Xiangyang - Fudan University