Cutting choreography : redefining dance on screen

[NO ABSTRACT]

A probabilistic framework for extracting narrative act boundaries and semantics in motion pictures

This work constitutes the first attempt to extract the important narrative structure, the 3-Act storytelling paradigm in film. Widely prevalent in the domain of film, it forms the foundation and framework in which a film can be made to function as an effective tool for story telling, and its extraction is a vital step in automatic content management for film data. The identification of act boundaries allows for structuralizing film at a level far higher than existing segmentation frameworks, which include shot detection and scene identification, and provides a basis for inferences about the semantic content of dramatic events in film. A novel act boundary likelihood function for Act 1 and 2 is derived using a Bayesian formulation under guidance from film grammar, tested under many configurations and the results are reported for experiments involving 25 full-length movies. The result proves to be a useful tool in both the automatic and semi-interactive setting for semantic analysis of film, with potential application to analogues occuring in many other domains, including news, training video, sitcoms.

Scene extraction in motion pictures

This paper addresses the challenge of bridging the semantic gap between the rich meaning users desire when they query to locate and browse media and the shallowness of media descriptions that can be computed in today's content management systems. To facilitate high-level semantics-based content annotation and interpretation, we tackle the problem of automatic decomposition of motion pictures into meaningful story units, namely scenes. Since a scene is a complicated and subjective concept, we first propose guidelines from fill production to determine when a scene change occurs. We then investigate different rules and conventions followed as part of Fill Grammar that would guide and shape an algorithmic solution for determining a scene. Two different techniques using intershot analysis are proposed as solutions in this paper. In addition, we present different refinement mechanisms, such as film-punctuation detection founded on Film Grammar, to further improve the results. These refinement techniques demonstrate significant improvements in overall performance. Furthermore, we analyze errors in the context of film-production techniques, which offer useful insights into the limitations of our method.

Novel approach to determining tempo and dramatic story sections in motion pictures

This paper presents an original computational approach to extraction of movie tempo for deriving story sections and events that convey high level semantics of stories portrayed in motion pictures, thus enabling better video annotation and interpretation systems. This approach, inspired by the existing cinematic conventions known as film grammar, uses the attributes of motion and shot length to define and compute a novel continuous measure of tempo of a movie. Tempo flow plots are derived for several full-length motion pictures and edge detection is performed to extract dramatic story sections and events occurring in the movie, underlined by their unique tempo. The results confirm reliable detection of actual distinct tempo changes and serve as useful index into the dramatic development and narration of the story in motion pictures.

Indexing narrative structure and semantics in motion pictures with a probabilistic framework

This work constitutes the first attempt to extract an important narrative structure, the 3-Act story telling paradigm, in film. This narrative structure is prevalent in the domain of film as it forms the foundation and framework in which the film can be made to function as an effective tool for story telling, and its extraction is a vital step in automatic content management for film data. A novel act boundary likelihood function for Act 1 is derived using a Bayesian formulation under guidance from film grammar, tested under many configurations and the results are reported for experiments involving 25 full length movies. The formulation is shown to be a useful tool in both the automatic and semi-interactive setting for semantic analysis of film.

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.

Film grammar based refinements to extracting scenes in motion pictures

To enable high-level semantic indexing of video, we tackle the problem of automatically structuring motion pictures into meaningful story units, namely scenes. In our recent work, drawing guidance from film grammar, we proposed an algorithmic solution for extracting scenes in motion pictures based on a shot neighborhood color coherence measure. In this paper, we extend our work by presenting various refinement mechanisms, inspired by the knowledge of film devices that are brought to bear while crafting scenes, to further improve the results of the scene detection algorithm. We apply the enhanced algorithm to ten motion pictures and demonstrate the resulting improvements in performance.

Narrativization of actuality : convergence of form and genre in film and television

The thesis concerns the treatment of actuality in film and television, particularly the narrativization of actuality images, and the context of their placement within audio/visual texts. Several instances of the convergence of media form and genre are analyzed, and the conventions of classificatory systems and boundaries that pertain to film and television representations are reconsidered in light of changes in the conventions of genre. The distinction between, and convergence of fictional and non-fictional conventions of narrative are therefore central to the thesis, as are the related issues of viewer response, the nature of subjectivity in the viewer, the connectivity of text and culture, and the relations of actuality to the text. The thesis traces the narrativization of actuality through textual, formal and genre boundaries, adopting a ‘line of flight or deterritorialization’ that enables the thesis to ‘change in nature and connect with other multiplicities.’This line of flight passes through the conventional separation of genre groupings and texts, and, similarly, has been applied in the thesis as a rationale for the diminution of theoretical boundaries. A multiperpectival approach is applied to the permeability of, or transcendent relations of the analysis to the boundaries between genres, between texts and culture, and between actuality and virtual representation. In the thesis there is also a theoretical deterritorialization that consents to a pluralism of theory, which is an approach demonstrated by Deleuze and Guattari in A Thousand Plateaus. The model of multi-perspectivalism adopted in the thesis engages in establishing connections and similarities between theories, rather than emphasizing contradictory and exclusive practices. The Foucauldian notion of the rules of formation in discourse, Nichols’ theories of documentary representation of reality, Bordwell’s schematic interpretation, and several other positions are critiqued, as the line of flight embarked upon in the thesis intersects with, and passes through both textual and theoretical boundaries. The thesis consists of two parts: firstly, a location of theoretical perspective, in which the issues of theory pertaining to actuality and narrative are explicated, and the methodological approach of the thesis is defined. The second part commences with an analysis of the most familiar instances of actuality in film and television, with particular attention to documentary forms. It then engages in the analysis of films that represent actuality but which, in the process of narrativization, display a convergence of genre conventions. The films selected for analysis include Steven Speilberg's Schindler's List, (1993) Oliver Stone's JFK, (1991) and Robert Zemeckis' Forrest Gump, (1994) and Contact, (1996). Hence the thesis is concerned with the application of a pluralist theoretical approach, with, however, an emphasis on the Deleuzo-Guattarian notions of rhizome and assemblage. Within this theoretical frame, the connections between actuality and the audio/visual text are explicated, and the formation of text as ‘a rhizome with the world’, is analyzed across a range of examples.

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

This paper presents a new study on the application of the framework of Computational Media Aesthetics to the problem of automated understanding of film. Leveraging Film Grammar as the means to closing the "semantic gap" in media analysis, we examine film rhythm, a powerful narrative concept used to endow structure and form to the film compositionally and enhance its lyrical quality experientially. The novelty of this paper lies in the specification and investigation of the rhythmic elements that are present in two cinematic devices; namely motion and editing patterns, and their potential usefulness to automated content annotation and management systems. In our rhythm model, motion behavior is classified as being either nonexistent, fluid or staccato for a given shot. Shot neighborhoods in movies are then grouped by proportional makeup of these motion behavioral classes to yield seven high-level rhythmic arrangements that prove to be adept at indicating likely scene content (e.g. dialogue or chase sequence) in our experiments. The second part of our investigation presents a computational model to detect editing patterns as either metric, accelerated, decelerated or free. Details of the algorithm for the extraction of these classes are presented, along with experimental results on real movie data. We show with an investigation of combined rhythmic patterns that, while 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/editing rhythms can allow us to determine that the content has changed and hypothesize as to why this is so. We present three 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 five motion pictures.

Toward automatic extraction of expressive elements from motion pictures : tempo

This paper addresses the challenge of bridging the semantic gap that exists between the simplicity of features that can be currently computed in automated content indexing systems and the richness of semantics in user queries posed for media search and retrieval. It proposes a unique computational approach to extraction of expressive elements of motion pictures for deriving high-level semantics of stories portrayed, thus enabling rich video annotation and interpretation. This approach, motivated and directed by the existing cinematic conventions known as film grammar, as a first step toward demonstrating its effectiveness, uses the attributes of motion and shot length to define and compute a novel measure of tempo of a movie. Tempo flow plots are defined and derived for a number of full-length movies and edge analysis is performed leading to the extraction of dramatic story sections and events signaled by their unique tempo. The results confirm tempo as a useful high-level semantic construct in its own right and a promising component of others such as rhythm, tone or mood of a film. In addition to the development of this computable tempo measure, a study is conducted as to the usefulness of biasing it toward either of its constituents, namely, motion or shot length. Finally, a refinement is made to the shot length normalizing mechanism, driven by the peculiar characteristics of shot length distribution exhibited by movies. Results of these additional studies, and possible applications and limitations are discussed.

Towards automatic extraction of expressive elements from motion pictures : tempo

This paper proposes a unique computational approach to extraction of expressive elements of motion pictures for deriving high level semantics of stories portrayed, thus enabling better video annotation and interpretation systems. This approach, motivated and directed by the existing cinematic conventions known as film grammar, as a first step towards demonstrating its effectiveness, uses the attributes of motion and shot length to define and compute a novel measure of tempo of a movie. Tempo flow plots are defined and derived for four full-length movies and edge analysis is performed leading to the extraction of dramatic story sections and events signaled by their unique tempo. The results confirm tempo as a useful attribute in its own right and a promising component of semantic constructs such as tone or mood of a film.

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 Australian Broadcasting Corporation’s multiplatform projects : industrial logics of children’s content provision in the digital television era

This paper traces the development of children’s multiplatform commissioning at the Australian Broadcasting Corporation (ABC) in the context of the digitalisation of Australian television. Whilst recent scholarship has focussed on ‘post-broadcast’ or ‘second-shift’ industrial practices, designed to engage view(s)ers with proprietary media brands, less attention has been focussed on children’s and young adults’ television in a public service context. Further, although multiplatform projects in the United States and Britain have been the subject of considerable analysis, less work has attempted to contextualise cultural production in smaller media markets. The paper explores two recent multiplatform projects through textual analysis, empirical research (consisting of interviews with key industry personnel) and an investigation of recent policy documents. The authors argue that the ABC’s mixed diet of children’s programming, featuring an educative or social developmental agenda, is complemented by its appeals to audience ‘participation’, with the Corporation maintaining public service values alongside the need to expand audience reach and the legitimacy of its brand. It finds that the ABC’s historical platform infrastructure, across radio, television and online, have allowed it to move beyond a market failure model to exploit multiplatform synergies competitively in the distribution of Australian children’s content to audiences on-demand.

Responding to human full-body gestures embedded in motion data streams.

 This research created a neural-network enabled artificially intelligent performing agent that was able to learn to dance and recognise movement through a rehearsal and performance process with a human dancer. The agent exhibited emergent dance behaviour and successfully engaged in a live, semi-improvised dance performance with the human dancer.