The Computational Media Lab at the ANU focus on computational problems for understanding online media and their interactions with and among humans. We develop core methods in machine learning and optimization, and use them to formulate and solve problems in multimedia understanding and online behavior analysis.

You may be interested in sampling the recent blog posts below, look at our research summary, publications, all past posts, or navigate by categories and tags.


Recent updates

SemStyle: Learning to Caption Images like Romantic Novels Posted on Jun 10, 2018

A new machine learning system that styles your caption like master story-tellers do.

posted by Lexing Xie and Alex Mathews
Fig. 1: Descriptive (blue) and story-like (dark red) image captions created by the SemStyle system. The story-like captions in example (a) is written as a sequence of actions, rather than a static scene description; (b) introduces a new adjective and uses a poetic sentence structure. Styled caption (c) is my favorite failure case -- it violates commonsense but triggers readers' imagination!

Read More

The Layered Cake Structure of a Paper Posted on Mar 25, 2018

The craft of paper writing can be mastered using recipes.

posted by Lexing Xie, additions and edits by Aditya Menon

I like cakes, and I enjoy reading logically lucid research articles. This post argues that research papers can benefit from explicitly thinking about and planning its four logical layers, just like a multi-layered Mille-feuille, or Napoleon cake (image credit: alyonascooking).

Read More

Quick Planning with Action Schema Networks Posted on Feb 26, 2018

How tricks from computer vision and deep learning can be used to accelerate planning algorithms

posted by Sam Toyer and Sylvie Thiébaux
Fig.1: A robot stacking blocks.

Planning algorithms try to find series of actions which enable an intelligent agent to achieve some goal. Such algorithms are used everywhere from manufacturing to robotics to power distribution. In our recent paper at AAAI ‘18, we showed how to use deep learning techniques from vision and natural language processing to teach a planning system to solve entire classes of sophisticated problems by training on a few simple examples.

Read More

Life Outside of Research in 2017 Posted on Dec 21, 2017

Siqi and Alex received sports and community accolades, respectively. The lab enjoyed two outings in town.

posted by Quyu Kong, with edits from Lexing Xie

Sports is a prominent theme in Canberra. This post celebrates two of our competitive athletes, and looks back at two outings when the whole lab flexed our muscles and got a little bit wet.

Read More

Expecting to be HIP (IV) - HIPsters Unite! Posted on Jul 24, 2017

The Hawkes Intensity Process (HIP) inspired a small cascade of puns, and a research-team-in-uniform

posted by Lexing Xie


Read More

FAQ for lab candidates Posted on Jul 20, 2017

read this before you email us

We look for new team members who value curiosity, critical thinking, and diversity in ideas, skills, and cultural perspectives.

Read More

Expecting to be HIP (III) -- Examining the role of promotions Posted on Jun 12, 2017

How much promotion is required, and why should one constantly promote?

posted by Marian-Andrei Rizoiu , edited by Lexing Xie

“The fundamental scarcity in the modern world is the scarcity of attention.” – Herbert A. Simon.

Human attention is a limited resource and influencing the mechanisms governing its allocation is the holy grail of advertisement. Our ICWSM’17 paper applies the recent HIP popularity modeling to further examine popularity under promotion and answer questions such as:

  • How much promotion is required for this item to rise to the top 5% in popularity?
  • How fast will an item respond to a given amount of promotion?
  • Why is constant promotion desirable?

Read More

Expecting to be HIP (II) -- Could this video go viral? Posted on Jun 11, 2017

supplying the missing link between popularity and promotions

posted by Marian-Andrei Rizoiu , edited by Lexing Xie

One major gap in understanding social media is to precisely quantify the relationship between the popularity of an online item and the external promotions it receives. Our recent WWW’17 paper supplies the missing link. We use a mathematical model to describe the continuous interaction between external promotions (e.g. tweets about a video) and popularity dynamics (e.g. daily views). This in turn answers several practical questions:

  • Can we explain the complex multi-phased popularity dynamics widely seen online?
  • Can one predict what could become viral?
  • Can one predict what would not become viral even if heavily promoted?

Read More

Escape from broadcasting: Talk shows as news sources Posted on May 26, 2017

We analyze news sources on YouTube to reveal their roles in broadcasting information.

posted by Siqi Wu, edited by Marian-Andrei Rizoiu and Lexing Xie


We are in an era when information consumption and production are democratized. Regular users not only consume information, but they digest, mutate and produce new information which gets passed on to other users. Prompted by a press inquiry from the Polish online news www.press.pl, we analyze the impact of these emergent sources of information versus traditional media, in the context of politics. More precisely, we study how YouTube videos posted by two traditional news sources (BBC news/UK, ABC news/USA) and two emergent online news sources (The Alex Jones Channel, The Young Turks) are viewed around the time of the US political elections of 2016.

Read More

Expecting to be HIP (I) - Deriving Stochastic Expectations Posted on Jan 16, 2017

This post outlines techniques for computing the expected event rate for Hawkes processes, or the so-called Hawkes Intensity Process (HIP).

posted by Lexing Xie


This post is the first of a series on modeling social media popularity using the Hawkes Intensity Process. “Expecting to be HIP (II)” gives an overview of results and interpretations on a large YouTube video dataset. “Expecting to be HIP (III)” further quantifies the effects and interpretations of promotion.

Read More

Inverting a Random Walk - Problem Settings Posted on Jan 3, 2017

We discuss three approaches for graph inversion from steady state distribution of random walks. This first post compares the problem settings.

posted by Lexing Xie

Markov chains and random walk on graphs are long-standing subjects in applied math and related disciplines. Given a markov chain / transition matrix / graph, properties of the random walk such as steady state distribution, mixing time are well-studied. Only in recent years, however, the inverse problem has started gaining interest – that is, given some measurements after random walk on a graph, infer some version of the graph. This blog post compares three related but different problem settings in recent literature from (Kumar15), (Mackay15) and (Xie13).

Read More

Wombeyan Caves and National Cherry Festival Posted on Dec 15, 2016

We explore Australian caves and cherries in the second half of 2016.

posted by Siqi Wu, with edits from Lexing Xie

Australia has great weather for the ourdoors, no matter it’s winter or summer – that’s what we did, and here’s photo proof.

Read More
Getting in touch:
-- drop a line if you are interested in knowing more about our work, collaborating, or joining us.
We have two PhD openings in 2018: one on Modeling Online Attention and one on Picturing Everyday Knowledge. We are also looking for research fellow candidates with passion and compelling track record.