A combined method for mitigating sparsity problem in tag recommendation

Tag recommendation is a specific recommendation task for recommending metadata (tag) for a web resource (item) during user annotation process. In this context, sparsity problem refers to situation where tags need to be produced for items with few annotations or for user who tags few items. Most of the state of the art approaches in tag recommendation are rarely evaluated or perform poorly under this situation. This paper presents a combined method for mitigating sparsity problem in tag recommendation by mainly expanding and ranking candidate tags based on similar items’ tags and existing tag ontology. We evaluated the approach on two public social bookmarking datasets. The experiment results show better accuracy for recommendation in sparsity situation over several state of the art methods.

Visual front-end wars : Viola-Jones face detector vs Fourier Lucas-Kanade

The performance of visual speech recognition (VSR) systems are significantly influenced by the accuracy of the visual front-end. The current state-of-the-art VSR systems use off-the-shelf face detectors such as Viola- Jones (VJ) which has limited reliability for changes in illumination and head poses. For a VSR system to perform well under these conditions, an accurate visual front end is required. This is an important problem to be solved in many practical implementations of audio visual speech recognition systems, for example in automotive environments for an efficient human-vehicle computer interface. In this paper, we re-examine the current state-of-the-art VSR by comparing off-the-shelf face detectors with the recently developed Fourier Lucas-Kanade (FLK) image alignment technique. A variety of image alignment and visual speech recognition experiments are performed on a clean dataset as well as with a challenging automotive audio-visual speech dataset. Our results indicate that the FLK image alignment technique can significantly outperform off-the shelf face detectors, but requires frequent fine-tuning.

Detecting anomalous events at railway level crossings

Collisions between pedestrians and vehicles continue to be a major problem throughout the world. Pedestrians trying to cross roads and railway tracks without any caution are often highly susceptible to collisions with vehicles and trains. Continuous financial, human and other losses have prompted transport related organizations to come up with various solutions addressing this issue. However, the quest for new and significant improvements in this area is still ongoing. This work addresses this issue by building a general framework using computer vision techniques to automatically monitor pedestrian movements in such high-risk areas to enable better analysis of activity, and the creation of future alerting strategies. As a result of rapid development in the electronics and semi-conductor industry there is extensive deployment of CCTV cameras in public places to capture video footage. This footage can then be used to analyse crowd activities in those particular places. This work seeks to identify the abnormal behaviour of individuals in video footage. In this work we propose using a Semi-2D Hidden Markov Model (HMM), Full-2D HMM and Spatial HMM to model the normal activities of people. The outliers of the model (i.e. those observations with insufficient likelihood) are identified as abnormal activities. Location features, flow features and optical flow textures are used as the features for the model. The proposed approaches are evaluated using the publicly available UCSD datasets, and we demonstrate improved performance using a Semi-2D Hidden Markov Model compared to other state of the art methods. Further we illustrate how our proposed methods can be applied to detect anomalous events at rail level crossings.

Electrospraying of polymers with therapeutic molecules : state of the art

The encapsulation and release of bioactive molecules from polymeric vehicles represents the holy grail of drug and growth factor delivery therapies, whereby sustained and controlled release is crucial in eliciting a positive therapeutic effect. To this end, electrospraying is rapidly emerging as a popular technology for the production of polymeric particles containing bioactive molecules. Compared with traditional emulsion fabrication techniques, electrospraying has the potential to reduce denaturation of protein drugs and affords tighter regulation over particle size distribution and morphology. In this article, we review the importance of the electrospraying parameters that enable reproducible tailoring of the particles' physical and in vitro drug release characteristics, along with discussion of existing in vivo data. Controlled morphology and monodispersity of particles can be achieved with electrospraying, with high encapsulation efficiencies and without unfavorable denaturation of bioactive molecules throughout the process. Finally, the combination of electrospraying with electrospun scaffolds, with an emphasis on tissue regeneration is reviewed, depicting a technique in its relative infancy but holding great promise for the future of regenerative medicine.

Gestural, emergent and expressive : three research themes for haptic interaction

Drawing on three case studies of work in the fields of participatory design, interaction design and electronic arts, we reflect on the implications of these studies for haptic interface research. We propose three themes: gestural; emergent; and expressive; as signposts for a program of research into haptic interaction that could point the way towards novel approaches to haptic interaction and move us from optic to haptic ways of seeing.

The paradox of autistic art

Certain autistic children whose linguistic ability is virtually nonexistent can draw natural scenes from memory with astonishing accuracy. In particular their drawings display convincing perspective. In contrast, normal children of the same preschool age group and even untrained adults draw primitive schematics or symbols of objects which they can verbally identify. These are usually conceptual outlines devoid of detail. It is argued that the difference between autistic child artists and normal individuals is that autistic artists make no assumptions about what is to be seen in their environment. They have not formed mental representations of what is significant and consequently perceive all details as equally important. Equivalently, they do not impose visual or linguistic schema -- a process necessary for rapid conceptualisation in a dynamic existence, especially when the information presented to the eye is incomplete.

The heterogeneous cluster ensemble method using hubness for clustering text documents

We propose a cluster ensemble method to map the corpus documents into the semantic space embedded in Wikipedia and group them using multiple types of feature space. A heterogeneous cluster ensemble is constructed with multiple types of relations i.e. document-term, document-concept and document-category. A final clustering solution is obtained by exploiting associations between document pairs and hubness of the documents. Empirical analysis with various real data sets reveals that the proposed meth-od outperforms state-of-the-art text clustering approaches.

A concept-based retrieval method for entity-oriented search

Entity-oriented retrieval aims to return a list of relevant entities rather than documents to provide exact answers for user queries. The nature of entity-oriented retrieval requires identifying the semantic intent of user queries, i.e., understanding the semantic role of query terms and determining the semantic categories which indicate the class of target entities. Existing methods are not able to exploit the semantic intent by capturing the semantic relationship between terms in a query and in a document that contains entity related information. To improve the understanding of the semantic intent of user queries, we propose concept-based retrieval method that not only automatically identifies the semantic intent of user queries, i.e., Intent Type and Intent Modifier but introduces concepts represented by Wikipedia articles to user queries. We evaluate our proposed method on entity profile documents annotated by concepts from Wikipedia category and list structure. Empirical analysis reveals that the proposed method outperforms several state-of-the-art approaches.

Representing and discovering adversarial team behaviors using player roles

In this paper, we describe a method to represent and discover adversarial group behavior in a continuous domain. In comparison to other types of behavior, adversarial behavior is heavily structured as the location of a player (or agent) is dependent both on their teammates and adversaries, in addition to the tactics or strategies of the team. We present a method which can exploit this relationship through the use of a spatiotemporal basis model. As players constantly change roles during a match, we show that employing a "role-based" representation instead of one based on player "identity" can best exploit the playing structure. As vision-based systems currently do not provide perfect detection/tracking (e.g. missed or false detections), we show that our compact representation can effectively "denoise" erroneous detections as well as enabe temporal analysis, which was previously prohibitive due to the dimensionality of the signal. To evaluate our approach, we used a fully instrumented field-hockey pitch with 8 fixed high-definition (HD) cameras and evaluated our approach on approximately 200,000 frames of data from a state-of-the-art real-time player detector and compare it to manually labelled data.

Motion capture and the future of virtual production

Motion capture continues to be adopted across a range of creative fields including, animation, games, visual effects, dance, live theatre and the visual arts. This panel will discuss and showcase the use of motion capture across these creative fields and consider the future of virtual production in the creative industries.

Constructing the shitting citizen : the promise of scatological art as environmental and social activism

Art activism uses visual and performance art to promote social and environmental agendas. In this paper, I explore attempts to raise awareness of sanitation issues at the global, local and personal level using scatological art. I focus on the successes of the open-air public art exhibition set up in the Brisbane (Queensland, Australia) central business district to celebrate World Toilet Day in 2008. The art in this exhibition featured included one hundred toilets decorated to raise awareness of global sanitation issues and the distribution of promotional materials featuring scatological images including postcards and stickers. Given the subject matter and intent, the toilet art and promotional materials presented at the One Hundred Toilet exhibition can be seen as an example of scatological art employed for the purposes of social and environmental activism. Through the One Hundred Toilet exhibition, I consider the political aims and activist potential of using scatological art to progress social and environmental agendas and consider how this kind of ‘shit on show’ approach can contribute to the construction of the shitting citizen; one who is simultaneously responsible for and responsive to managing the waste that they produce and recognising and responding to broader sanitation issues.

Addressing the impediments copyright imposes on the use of patent specifications and prior art documents to improve patent quality

This article considers from an Australian perspective the impediments that copyright law places in the path of those who seek to use patent specifications and non-patent prior art documents in ways that are necessary to the proper functioning of the patent system. Until recently, copyright law in Australia had limited the uses to which members of the public could put patent specifications in that country. Those impediments have been removed as a result of an important legislative change to the way in which copyright in patent specifications can be enforced. The change gives the public a greater freedom to make use of patent specifications than it enjoyed before, and removes unwarranted restrictions upon the ways in which the public can reuse valuable information. However, what the amendment does not address is the impediments copyright imposes on using non-patent prior art documents in ways that advance the public interest.

Copyright in patent specifications and prior art documents: Addressing legitimate rights of user

One of the recent Raising the Bar amendments has removed impediments imposed by copyright law that may have limited the uses to which IP Australia and members of the public could have lawfully put patent specifications without seeking permission from the copyright owner. What the amendment does not do, however, is extend the same protections to those who wish to use prior art documents in ways that benefit the patent system and further the public interest.

The Art of Freestyle

"This book is intended to be instructional, inspirational and of interest to both novice and expert alike. The assumption is made that to even begin to playboat the paddler will already be an intermdiate white water boater familiar with basic strokes and boating skills. For the interested non paddler a glossary of terms is included. Part One gives an overview of the sport and lays the foundations of understanding on which the rest of the book builds, as well as exploring safety issues and exploring key concepts. Part Two describes and coaches the moves which are divided into intermediate and advanced standard. Part Three looks at how to train in order to hone your physical and mental skills and be 'the best you can be'. Never before has so much freestyle, rodeo and playboating information from so many great boaters been gathered together in one place. In a world dominated by the biggest, the fastest, the loudest...the most big headed, this book makes a stand. Whilst of course covering all the latest moves, the authors have not been frightened to start right back at basic concepts. Technical ability is nothing without knowledge, without planning and without stamina. This book tells you the secrets. Freestyle is a thinking person's sport. The authors, the contributors and the book's publisher have an unrivalled breadth of knowledge in this field, so let this book do some of the thinking for you. The full colour format and the emphasis on personal training and coaching make for a particularly easy read. When planning my preparation or training before a competition, I always try to evaluate its potential benefits in terms of how many places it will have helped me move up in the final results. As a general rule in life, any time spent off the water should be viewed with suspicion! However, use this time constructively and absorb the information in this book and you will reap your own rewards. The Art of Freestyle is a book genuinely written by paddlers for paddlers. It is often a hard task to get top athletes to part with their preferred training or competition techniques, but this book is full of such 'Top Tips'. This is not a book written just by its authors, but by a wealth of accomplished paddlers. It is this subtle combination that keeps the reader in the real world...believing in a move, not just imagining it. This is the real world...believe you can do it."--Playak Website