Efficient subwindow search with submodular score functions

Subwindow search aims to find the optimal subimage which maximizes the score function of an object to be detected. After the development of the branch and bound (B&B) method called Efficient Subwindow Search (ESS), several algorithms (IESS [2], AESS [2], ARCS [3]) have been proposed to improve the performance of ESS. For nn images, IESS's time complexity is bounded by O(n³) which is better than ESS, but only applicable to linear score functions. Other work shows that Monge properties can hold in subwindow search and can be used to speed up the search to O(n³), but only applies to certain types of score functions. In this paper we explore the connection between submodular functions and the Monge property, and prove that sub-modular score functions can be used to achieve O(n³) time complexity for object detection. The time complexity can be further improved to be sub-cubic by applying B&B methods on row interval only, when the score function has a multivariate submodular bound function. Conditions for sub-modularity of common non-linear score functions and multivariate submodularity of their bound functions are also provided, and experiments are provided to compare the proposed approach against ESS and ARCS for object detection with some nonlinear score functions.

Efficient algorithms for subwindow search in object detection and localization

Recently, a simple yet powerful branch-and-bound method called Efficient Subwindow Search (ESS) was developed to speed up sliding window search in object detection. A major drawback of ESS is that its computational complexity varies widely from O(n²) to O(n⁴) for n × n matrices. Our experimental experience shows that the ESS's performance is highly related to the optimal confidence levels which indicate the probability of the object's presence. In particular, when the object is not in the image, the optimal subwindow scores low and ESS may take a large amount of iterations to converge to the optimal solution and so perform very slow. Addressing this problem, we present two significantly faster methods based on the linear-time Kadane's Algorithm for 1D maximum subarray search. The first algorithm is a novel, computationally superior branchand- bound method where the worst case complexity is reduced to O(n³). Experiments on the PASCAL VOC 2006 data set demonstrate that this method is significantly and consistently faster (approximately 30 times faster on average) than the original ESS. Our second algorithm is an approximate algorithm based on alternating search, whose computational complexity is typically O(n²). Experiments shows that (on average) it is 30 times faster again than our first algorithm, or 900 times faster than ESS. It is thus wellsuited for real time object detection.

Exploiting monge structures in optimum subwindow search

Optimum subwindow search for object detection aims to find a subwindow so that the contained subimage is most similar to the query object. This problem can be formulated as a four dimensional (4D) maximum entry search problem wherein each entry corresponds to the quality score of the subimage contained in a subwindow. For n x n images, a naive exhaustive search requires O(n⁴) sequential computations of the quality scores for all subwindows. To reduce the time complexity, we prove that, for some typical similarity functions like Euclidian metric, χ² metric on image histograms, the associated 4D array carries some Monge structures and we utilise these properties to speed up the optimum subwindow search and the time complexity is reduced to O(n³). Furthermore, we propose a locally optimal alternating column and row search method with typical quadratic time complexity O(n²). Experiments on PASCAL VOC 2006 demonstrate that the alternating method is significantly faster than the well known efficient subwindow search (ESS) method whilst the performance loss due to local maxima problem is negligible.

A hybrid cuckoo search and variable neighborhood descent for single and multiobjective scheduling problems

Cuckoo search (CS) is a relatively new meta-heuristic that has proven its strength in solving continuous optimization problems. This papers applies cuckoo search to the class of sequencing problems by hybridizing it with a variable neighborhood descent local search for enhancing the quality of the obtained solutions. The Lévy flight operator proposed in the original CS is modified to address the discrete nature of scheduling problems. Two well-known problems are used to demonstrate the effectiveness of the proposed hybrid CS approach. The first is the NP-hard single objective problem of minimizing the weighted total tardiness time (Formula presented.) and the second is the multiobjective problem of minimizing the flowtime ¯ and the maximum tardiness Tmaxfor single machine (Formula presented.). For the first problem, computational results show that the hybrid CS is able to find the optimal solutions for all benchmark test instances with 40, 50, and 100 jobs and for most instances with 150, 200, 250, and 300 jobs. For the second problem, the hybrid CS generated solutions on and very close to the exact Pareto fronts of test instances with 10, 20, 30, and 40 jobs. In general, the results reveal that the hybrid CS is an adequate and robust method for tackling single and multiobjective scheduling problems.

In search of peaceful playgrounds

Recess is often thought of as a time to escape from the classroom, from work and from the constant gaze of the teacher. It was a peaceful and joyous time when most children occupied themselves in active play and the odd incident was quickly resolved with the help of the teacher on 'yard duty'. Not so any more. The playground is now a 'problem' in many schools largely because of the bullying behaviour occurring there. This paper discusses the relative merits of the strategies schools are implementing in an effort to deal with the bullying behaviour and suggests that more thought might be given to improving the playground environment itself as a way of addressing the problems.

Methodological and conceptual issues in the search for a relationship between animal body-size distributions and benthic habitat architecture

Benthic ecologists have studied the distribution of animal body sizes because it is a form of ‘taxon-free’ classification that may be a useful metric for describing variation within and between ecological communities. In particular, the idea that the allometry of physiological and life-history traits may control species composition and relative abundances implies a functional link between body-size distributions and communities. The physical structure of aquatic habitats has often been cited as the mechanism by which habitat may determine body-size distributions in communities. However, further progress is hindered by a lack of theoretical clarity regarding the mechanisms that connect body size to the characteristics of ecological communities, leading to methods that may obscure interesting trends in body-size data. This review examines the methodological and conceptual issues hindering progress in the search for a relationship between animal body size and habitat architecture and suggests ways to resolve these issues. Problems are identified with current methods for the measurement of animal body size, the data and measures used to quantify body-size distributions and the methods used to identify patterns therein. Fundamentally, renewed emphasis on the mechanisms by which animal body sizes are influenced by habitat architecture is required to refine methodology and synthesise results from pattern-seeking and mechanistic studies.

Just deserts in post-colonial society : problems in the punishment of indigenous offenders.

Revised version of a paper presented to the Australian and New Zealand Society of Criminology Conference, Sydney, 2-3 October 2003 - disproportionate number of indigenous persons in the criminal justice system - the concept of 'just deserts' in regard to indigenous punishment - legislative reforms are needed to empower the judiciary in the sentencing process - must take account of the historical fact of dispossession - destructive effects on indigenous communities.

Principal selection: homosocialibility, the search for security and the production of normalized principal identities

Researchers investigating the decline of potential applicants for principalships have demonstrated that teachers perceive there to be a significant problem in current selection procedures. This article reports an investigation in two Australian states into principal selection. Drawing on a corpus of interviews, two case studies and administrative guidelines, we highlight five key problems in the interview process: (1) the dependence of selection panels on a written application; (2) the dilemma of experience versus potential; (3) the covert rule about the appointment of preferred applicants; (4) the quandary of panel competency; and (5) the evidence of inconsistency of decisions. We argue that the selection process amounts to a reproductive technology which, in the quest for certainty and safety, results in particular kinds of people being successful. This amounts we suggest, whether the selection process is managed by progressive or conservative personnel, to a form of homosociability the tendency to select people just like oneself.

Partners of problem gamblers who present for counselling: demographic profile and presenting problems

This study examined the characteristics of partners of problem gamblers. The study participants were 440 partners, who sought help in a 12-month period from the publicly-funded Break Even counselling services in the state of Victoria, Australia. The analyses revealed that the partners of problem gamblers were far from an homogenous group, with having to face the consequences of another person's problematic gambling seeming to be the only common characteristic. Almost one-third (29.6%) of clients were male and with the exception of financial problems, which were more likely to be reported by females, the presenting problems were similar. When compared to all Victorians aged 15 years and over, greater proportions of male and female partners of problem gamblers were participants in the labour force.

The BEST plus approach to assisting families recover from youth substance problems

The Best plus program is a whole-of-family therapy option for families to address not only youth substance abuse issues, but also challenging and antisocial adolescent behaviours. It uses an evidence-based strategy that can be implemented widely in the community, and is proving to be a popular and relevant framework for professionals to engage and assist families in reducing adolescent problem behaviours. Evaluations indicate that the program is an effective forum for parents and siblings of adolescent drug abusers to redevelop positive family environments that encourage responsible behaviour and recovery from drug abuse.

Parenting style as a moderator of the effect of temperament on adolescent externalising and internatlising behaviour problems

The direct and interactive effects of temperament and parenting were examined in the prediction of early adolescent externalising behaviour problems (conduct disorder and hyperactivity), internalising problems (depression and anxiety), and substance use, using data on 1,402 13- and 14-year-olds. Significant direct effects were found for four temperament factors (negative reactivity, task persistence, activity, and approach), and four parenting factors (warmth, power assertion, physical punishment, and monitoring). For those high in persistence, low in negative reactivity, or low in activity, problem outcomes were generally very rare, regardless of parenting. Prevalence of behaviour problems was generally elevated among those low in persistence, high in negative reactivity, or high in activity, even in cases where parenting was high in positive qualities such as warmth and monitoring. Prevalence of certain behaviour problems was substantially elevated when low persistence, high negative reactivity, or high activity occurred in combination with lower parental warmth or lower monitoring. The results suggest that parenting can play an important moderating role in the relationship of particular temperament characteristics to behavioural problems. [Author abstract]

The search : version 1

The Search (version 1) is one of a suite of drawings that responds to the work 'Kangaroo Stalking' by S.T.Gill. It also plays with certain ideas or problems in the depiction of landscape more broadly. The exhibition invited SCCA staff to each respond to a particular work within the Deakin collection.

Solving a multiobjective job shop scheduling problem using Pareto Archived Cuckoo Search

This paper investigates a new approach for solving the multiobjective job shop scheduling problem, namely the Cuckoo Search ( CS) approach. The requirement is to schedule jobs on a single machine so that the total material waste is minimised as well as the total tardiness time. The material waste is quantified in terms of saving factors to show the reduction in material that can be achieved when producing two jobs with the same materials in sequence. The estimated saving factor is used to calculate a cost savings for each job based on its material type. A formulation of multiobjective optimisation problems is adopted to generate the set of schedules that maximise the overall cost savings and minimise the total tardiness time. where all trade-offs are considered for the two conflicting objectives. A Pareto Archived Multiobjective Cuckoo Search (PAMOCS) is developed to find the set ofnondominated Pareto optimal solutions. The solution accuracy of PAMOCS is shown by comparing the closeness of the obtained solutions to the true Pareto front generated by the complete enumeration methad. Results shaw that CS is a very effective and promising technique to solve job shop scheduling problems.