Preference networks : probabilistic models for recommendation systems

Recommender systems are important to help users select relevant and personalised information over massive amounts of data available. We propose an unified framework called Preference Network (PN) that jointly models various types of domain knowledge for the task of recommendation. The PN is a probabilistic model that systematically combines both content-based filtering and collaborative filtering into a single conditional Markov random field. Once estimated, it serves as a probabilistic database that supports various useful queries such as rating prediction and top-N recommendation. To handle the challenging problem of learning large networks of users and items, we employ a simple but effective pseudo-likelihood with regularisation. Experiments on the movie rating data demonstrate the merits of the PN.

Probabilistic models over ordered partitions with applications in document ranking and collaborative filtering

Ranking is an important task for handling a large amount of content. Ideally, training data for supervised ranking would include a complete rank of documents (or other objects such as images or videos) for a particular query. However, this is only possible for small sets of documents. In practice, one often resorts to document rating, in that a subset of documents is assigned with a small number indicating the degree of relevance. This poses a general problem of modelling and learning rank data with ties. In this paper, we propose a probabilistic generative model, that models the process as permutations over partitions. This results in super-exponential combinatorial state space with unknown numbers of partitions and unknown ordering among them. We approach the problem from the discrete choice theory, where subsets are chosen in a stagewise manner, reducing the state space per each stage significantly. Further, we show that with suitable parameterisation, we can still learn the models in linear time. We evaluate the proposed models on two application areas: (i) document ranking with the data from the recently held Yahoo! challenge, and (ii) collaborative filtering with movie data. The results demonstrate that the models are competitive against well-known rivals.

Role of shot length in characterizing tempo and dramatic story sections in motion pictures

Motivated by existing cinematic conventions known as film grammar, we proposed a computational approach to determine tempo as a high-level movie content descriptor as well as means for deriving dramatic story sections and events occurring in movies. Movie tempo is extracted from two easily computed aspects in our approach: shot length and motion. Story sections and events are generally associated with changes in tempo, and are thus identified by edges located in the tempo function. In this paper, we analyze our initial founding of the tempo function on the basis that the distribution of both shot length and motion in movies is normal. Given that the distribution of shot length is approximately Weibull as confirmed in our experiments, we examine the impact of modelling and modifying the contributions of shot length to tempo. We derive an appropriate normalization function that faithfully encapsulates the role of shot length in tempo perception, and analyze the changes to the story sections identified in films.

Analysis of environmental sounds as indexical signs in film

In this paper, we investigate the problem of classifying a subset of environmental sounds in movie audio tracks that indicate specific indexical semiotic use. These environmental sounds are used to signify and enhance events occurring in film scenes. We propose a classification system for detecting the presence of violence and car chase scenes in film by classifying ten various environmental sounds that form the constituent audio events of these scenes using a number of old and new audio features. Experiments with our classification system on pure test sounds resulted in a correct event classification rate of 88.9%. We also present the results of the classifier on the mixed audio tracks of several scenes taken from The Mummy and Lethal Weapon 2. The classification of sound events is the first step towards determining the presence of the complex sound scenes within film audio and describing the thematic content of the scenes.

Determining dramatic intensification via flashing lights in movies

Movie directors and producers worldwide, in their quest to narrate a good story that warrants repeated audience viewing, use many cinematic elements to intensify and clarify the viewing experience. One such element that directors manipulate is lighting. In this paper we examine one aspect of lighting, namely flashing lights, and its role as an intensifier of dramatic effects in film. We present an algorithm for robust extraction of flashing lights and a simple mechanism to group detected flashing lights into flashing light scenes and analyze the role of these segments in story narration. In addition, we demonstrate how flashing lights detection can improve the performance of shot-based video segmentation. Experiments on a number of video sequences extracted from real movies yields good results. Our technique detects 90.4% of flashing lights. The detected flashing lights correctly eliminates 92.7% of false cuts in these sequences. In addition, data support is compiled to demonstrate the association between flashing light scenes and certain dramatic intensification events such as supernatural power, crisis or excitement.

Dynamic shot suggestion filtering for home video based on user performance

This paper presents novel additions to our existing amateur media creation framework. The framework provides at-capture guidance to enable the home movie maker to realize their aesthetic and narrative goals and automation of post-production editing. A common problem with the amateur filming context is its contingent nature, which often results in the failure to gain footage vital to the user's goals, even with at-capture software embedding. Accordingly, we have modelled minimizing the difference between target and captured footage at a given time during filming as a probability distribution divergence problem. We apply two policies of feedback to the user on their performance, passive communication via a suggestion desirability measure, and active filtering of undesirable suggestions. We demonstrate the framework using each policy with a simulation of various user and filming situations with promising results.

Finding the beat : an analysis of the rhythmic elements of motion pictures

This paper forms a continuation of our work focused on exploiting film grammar for the task of automated film understanding. We examine film rhythm, a powerful narrative concept used to endow structure and form to the film compositionally and to enhance its lyrical quality experientially. Of the many, often complex, cinematic devices contributing to film rhythm, this paper investigates the rhythmic elements that are present in edited sequences of shots, and presents a novel computational model to detect shot structural rhythm as either metric, accelerated, decelerated, or free. Details of the algorithm for the extraction of these editing rhythm classes are presented, along with experimental results on real movie data. Following this we study the usefulness of combining the rhythmic patterns induced through both motion and editing in film. We show that, whilst detailed content identification via rhythm types alone is not possible by virtue of the fact that film is not codified to this level in terms of rhythmic elements, analysis of the combined motion/shot rhythm can allow us to determine that the content has changed and hypothesize as to why this is so. We present 3 such categories of change and demonstrate their efficacy for capturing useful film elements (e.g., scene change precipitated by plot event), by providing data support from 5 motion pictures.

The social network virtual design studio : integrated design learning using blended learning environments

Online communications, multimedia, mobile computing and face-to-face learning create blended learning environments to which some Virtual Design Studios (VDS) have reacted to. Social Networks (SN), as instruments for communication, have provided a potentially fruitful operative base for VDS. These technologies transfer communication, leadership, democratic interaction, teamwork, social engagement and responsibility away from the design tutors to the participants. The implementation of Social Network VDS (SNVDS) moved the VDS beyond its conventional realm and enabled students to develop architectural design that is embedded into a community of learners and expertise both online and offline. Problem-based learning (PBL) becomes an iterative and reflexive process facilitating deep learning. The paper discusses details of the SNVDS, its pedagogical implications to PBL, and presents how the SNVDS is successful in enabling architectural students to collaborate and communicate design proposals that integrate a variety of skills, deep learning, knowledge and construction with a rich learning experience.

How social is the virtual design studio? A case study of a third year design studio

With the advent of social networks, it became apparent that the social aspect of designing and learning plays a crucial role in students’ education. Technologies and skills are the base on which learners interact. The ease of communication, leadership opportunity, democratic interaction, teamwork, and the sense of community are some of the aspects that are now in the centre of design interaction. The paper examines Virtual Design Studios (VDS) that used media-rich platforms and analyses the influence the social aspect plays in solving all problems on the sample of a design studio at Deakin University. It studies the effectiveness of the generated social intelligence and explores the facilitation of students’ self-directed learning. Hereby the paper studies the construction of knowledge via social interaction and how blended learning environments foster motivation and information exchange. It presents its finding based on VDS that were held over the past three years.

Cinema of Australia and New Zealand

From The Story of the Kelly Gang in 1906 to the Lord of the Rings trilogy, Australia and New Zealand have made a unique impact on international cinema. This book celebrates the commercially successful narrative feature films produced by these film cultures as well as key documentaries, shorts and independent films. This coverage also invokes issues involving national identity, race, history and the ability of two small film cultures to survive the economic and cultural threat from Hollywood. Chapters on well-known films, and directors, such as The Year of Living Dangerously (Peter Weir, 1982), The Piano (Jane Campion, 1993), Fellowship of the Ring (Peter Jackson, 2001) and Rabbit Proof Fence (Philip Noyce, 2002) are included with less celebrated, but equally important, films and filmmakers such as Jedda (Charles Chauvel, 1955), They're a Weird Mob (Michael Powell, 1966), Vigil (Vincent Ward, 1984) and The Goddess of 1967 (Clara Law, 2000)

American beauty recycled : the celebrity machine

This work examines the 'machine' of celebrity suggesting that the value assigned to celebrity and the function of celebrity n our society has to do with surplus desire and fluid identity. This work gtakes the video within the movie American Beauty and reframes i as an installation with gold leaf commenting on the ephemeral and trahs-lie, throw-away nature of celebrity and the way in which celebration can be extracted from the lottery of celebrity production.

Alt.film.au(2) : Blogging at the margins in Australian retrospective 2012

In 1972 Albie Thoms wrote: ‘In Australia it has been impossible to elicit much sympathetic appraisal from critics who seem distressed by the relation of personal film to amateur movies. Even those proselytizing for the New cinema have underrated the personal film as a worthy antidote to the market assumptions of Hollywood.’ (Thoms 1978, p. 146) The question now is, of course, is anything different in 2012? The answer is of course yes and no. Although the politics remains frustratingly familiar the digital has progressed further to the point that where in the 60s every one picked up a guitar, now we pick up a video camera. A postscript relates those films in the program not available for inclusion in the original 90s rant- (i.e. they did not exist) I have further annotated this re-play of old wounds and victories with commentary on some of the films in the screening program.

Virtual design studio within a blended social network

Online interactions, multimedia, mobile computing and face-to-face learning create blended learning environments to which some Virtual Design Studios (VDS) have reacted. Social Networks (SN), as instruments for communication, have provided a potentially fruitful operative base for VDS. These technologies transfer communication, leadership, democratic interaction, teamwork, social engagement and responsibility away from the design tutors to the participants. The implementation of a Social Network VDS (SNVDS) moved the VDS beyond its conventional realm and enabled students to develop architectural design that is embedded into a community of learners and their expertise both online and offline. Problem-based learning (PBL) becomes an iterative and reflexive process facilitating deep learning. The paper discusses details of the SNVDS, its pedagogical implications to PBL, and presents how the SNVDS is successful in empowering architectural students to collaborate and communicate design proposals that integrate a variety of skills, deep learning, knowledge and construction with a rich learning experience.

Glassimations

Short movie that was the outcome of a class I taught at Pilchuck Glass School, USA