Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Lexing Xie
Professor, Computer Science, the Australian National University.
I lead the ANU Computational Media Lab - http://cm.cecs.anu.edu.au
I am leading the Humansing Machine Intelligence Project since Dec 2021.
Contact: my firstname dot lastname at anu dot edu dot au
News about the Computation Media lab is here ... older news is archived here.
Research Overview
My research focus broadly on innovative design and use of machine learning algorithms, especially on large-scale graph data and collective behaviour. Several areas of recent work include:
  • Popularity in social media -- understanding, predicting, and optimization.
  • Multimedia knowledge graphs, vision and language.
  • Humanising machine intelligence.
    • Details can be found from the sample projects below and the list of publications.
    Selected Recent Projects
    Estimating Attention Flow in Online Video Networks
    Siqi Wu, Marian-Andrei Rizoiu, Lexing Xie
    CSCW '19, ACM Conference on Computer-Supported Cooperative Work and Social Computing, Austin TX, Nov 2019 (Honourable Mention)
    abstract| paper+supplement| slides | data+code|
    Influence Flowers of Academic Entities
    Minjeong Shin, Alexander Soen, Benjamin T. Readshaw, Stephen M. Blackburn, Mitchell Whitelaw, Lexing Xie
    VAST '19, IEEE Conference on Visual Analytics Science & Technology, Vancouver, Oct 2019.
    abstract| paper+supplement| slides | web + interactive figures| code|
    SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text
    Alexander Mathews, Lexing Xie, Xuming He
    CVPR '18, Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018.
    abstract| paper+supplement| slides | data+code|
    Expecting to be HIP: Hawkes Intensity Processes for Social Media Popularity
    Marian-Andrei Rizoiu, Lexing Xie, Scott Sanner, Manuel Cebrian, Honglin Yu, Pascal van Hentenryck
    WWW '17, 26th International Conference on World Wide Web, Perth, Australia, 2017.
    abstract| paper+supplement| slides | data+code|
    Feature Driven and Point Process Approaches for Popularity Prediction
    Swapnil Mishra, Marian-Andrei Rizoiu, Lexing Xie
    CIKM '16, 25th ACM International Conference on Information and Knowledge Management, Indianapolis, IN, USA, 2016.
    abstract| paper+supplement| blog post | data+code|
    SentiCap: Generating Image Descriptions with Sentiments
    Alexander Mathews, Lexing Xie, Xuming He
    AAAI 2016, Feb 2016
    paper+supplement| data | project | slides|
    Evolution of Privacy Loss in Wikipedia
    Marian-Andrei Rizoiu, Lexing Xie, Tiberio Caetano and Manuel Cebrian
    WSDM 2016, Feb 2016
    paper+supplement| data | slides| poster
    The Lifecyle of a Youtube Video: Phases, Content and Popularity
    Honglin Yu, Lexing Xie, Scott Sanner
    ICWSM 2015, May 2015 (full paper)
    pdf| data + code | slides| poster
    Choosing Basic-Level Concept Names using Visual and Language Context
    Alexander Mathews, Lexing Xie, Xuming He
    IEEE WACV 2015, Jan 2015
    pdf| dataset| poster
    Picture Tags and World Knowledge: Learning Tag Relations from Visual Semantic Sources
    Lexing Xie, Xuming He
    ACM Multimedia 2013, Oct 2013 (full paper)
    pdf| project page| slides
    Event Diffusion Patterns in Social Media (2012)
    Minkyoung Kim, Lexing Xie, Peter Christen
    Intl. Conf. on Weblogs and Social Media (ICWSM), 8 pages, Dublin, Ireland, June 2012
    abstract |pdf
    Visual Memes in Social Media: Tracking Real-world News in YouTube Videos (2011)
    Lexing Xie, Apostol Natsev, Matthew Hill, John Kender, John R Smith
    ACM Multimedia 2011 and ICWSM 2011
    project page |TMM'13 paper |MM'11 paper
    ImageHive: Interactive Content-Aware Image Summarization (2012)
    Li Tan, Yangqiu Song, Shixia Liu, Lexing Xie,
    IEEE Computer Graphics and Applications, pp. 46-55, January/February, 2012
    abstract |pdf
    Probabilistic Visual Concept Trees (2010)
    Lexing Xie, Rong Yan, Jelena Tešić, Apostol Natsev, John R Smith
    ACM Multimedia 2010, pp. 867-870
    abstract |pdf