An annotation-free method for evaluating privacy protection techniques in videos

While several privacy protection techniques are pre- sented in the literature, they are not complemented with an established objective evaluation method for their assess- ment and comparison. This paper proposes an annotation- free evaluation method that assesses the two key aspects of privacy protection that are privacy and utility. Unlike some existing methods, the proposed method does not rely on the use of subjective judgements and does not assume a spe- cific target type in the image data. The privacy aspect is quantified as an appearance similarity and the utility aspect is measured as a structural similarity between the original raw image data and the privacy-protected image data. We performed an extensive experimentation using six challeng- ing datasets (including two new ones) to demonstrate the effectiveness of the evaluation method by providing a per- formance comparison of four state-of-the-art privacy pro- tection techniques.

ANNODA: tool for integrating molecular-biological annotation data

Collecting, analyzing, and making Molecularbiological annotation data accessible in different public data sources is still an ongoing project. Integration of such data from these data sources might lead to valuable biological knowledge. There are numerous annotation data and only some of those are structured. The number and contents of related sources are continuously increasing. In addition, the existing data sources have their own storage structure and implementation. As a result, these could lead to a limitation in the combining of annotation. Here, we proposed a tool, called ANNODA, for integrating Molecular-biological annotation data. Unlike the past work on database interoperation in the bioinformatics community, this database design uses web-links which are very useful for interactive navigation and meanwhile it also supports automated large-scale analysis tasks.

Clustering based multi-label classification for image annotation and retrieval

This paper presents a novel multi-label classification framework for domains with large numbers of labels. Automatic image annotation is such a domain, as the available semantic concepts are typically hundreds. The proposed framework comprises an initial clustering phase that breaks the original training set into several disjoint clusters of data. It then trains a multi-label classifier from the data of each cluster. Given a new test instance, the framework first finds the nearest cluster and then applies the corresponding model. Empirical results using two clustering algorithms, four multi-label classification algorithms and three image annotation data sets suggest that the proposed approach can improve the performance and reduce the training time of standard multi-label classification algorithms, particularly in the case of large number of labels.

Empirical study of multi-label classification methods for image annotation and retrieval

This paper presents an empirical study of multi-label classification methods, and gives suggestions for multi-label classification that are effective for automatic image annotation applications. The study shows that triple random ensemble multi-label classification algorithm (TREMLC) outperforms among its counterparts, especially on scene image dataset. Multi-label k-nearest neighbor (ML-kNN) and binary relevance (BR) learning algorithms perform well on Corel image dataset. Based on the overall evaluation results, examples are given to show label prediction performance for the algorithms using selected image examples. This provides an indication of the suitability of different multi-label classification methods for automatic image annotation under different problem settings.

Media-independent knowledge representation via UMART : unified mental annotation and retrieval tool

Multimedia information is now routinely available in the forms of text, pictures, animation and sound. Although text objects are relatively easy to deal with (in terms of information search and retrieval), other information bearing objects (such as sound, images, animation) are more difficult to index. Our research is aimed at developing better ways of representing multimedia objects by using a conceptual representation based on Schank's conceptual dependencies. Moreover, the representation allows for users' individual interpretations to be embedded in the system. This will alleviate the problems associated with traditional semantic networks by allowing for coexistence of multiple views of the same information. The viability of the approach is tested, and the preliminary results reported.

Segmentation of intentional human gestures for sports video annotation

We present results on the recognition of intentional human gestures for video annotation and retrieval. We define a gesture as a particular, repeatable, human movement having a predefined meaning. An obvious application of the work is in sports video annotation where umpire gestures indicate specific events. Our approach is to augment video with data obtained from accelerometers worn as wrist bands by one or more officials. We present the recognition performance using a Hidden Markov Model approach for gesture modeling with both isolated gestures and gestures segmented from a stream.

Hierarchical recognition of intentional human gestures for sports video annotation

We present a novel technique for the recognition of complex human gestures for video annotation using accelerometers and the hidden Markov model. Our extension to the standard hidden Markov model allows us to consider gestures at different levels of abstraction through a hierarchy of hidden states. Accelerometers in the form of wrist bands are attached to humans performing intentional gestures, such as umpires in sports. Video annotation is then performed by populating the video with time stamps indicating significant events, where a particular gesture occurs. The novelty of the technique lies in the development of a probabilistic hierarchical framework for complex gesture recognition and the use of accelerometers to extract gestures and significant events for video annotation.

EST-PAC HPC - a web portal for high-throughput EST annotation and protein sequence prediction

Expressed Sequence Tags (ESTs) are short DNA sequences generated by sequencing the transcribed cDNAs coming from a gene expression. They can provide significant functional, structural and evolutionary information and thus are a primary resource for gene discovery. EST annotation basically refers to the analysis of unknown ESTs that can be performed by database similarity search for possible identities and database search for functional prediction of translation products. Such kind of annotation typically consists of a series of repetitive tasks which should be automated, and be customizable and amenable to using distributed computing resources. Furthermore, processing of EST data should be done efficiently using a high performance computing platform. In this paper, we describe an EST annotator, EST-PACHPC, which has been developed for harnessing HPC resources potentially from Grid and Cloud systems for high throughput EST annotations. The performance analysis of EST-PACHPC has shown that it provides substantial performance gain in EST annotation.

Can a media annotation tool enhance online engagement with learning? A multi-case work-in-progress report

The paper explores preliminary data of four cases in a larger study investigating the effects on learning of a new educational technology called Media Annotation Tool (MAT). In particular, the paper focuses on learning engagement with MAT and begins to raise questions about what factors promote or enhance engagement. Drawing on the work of Kirkwood (2009), the authors analyse the type of educational technology functions that were expressed through the ways teachers integrated the use of MAT into their curriculum. Another factor explored in the paper is student engagement. Barkley's (2010) theorising on the complexity of student engagement for learning argues that engagement is where motivation and active learning synergistically interact. Examining students reflections on their use of MAT, the authors identify that while MAT offers active learning, motivation for the use of MAT may be a missing factor for some disengaged students. This insight provides further themes to explore in further analysis of the projects data.

The challenges of blended learning using a media annotation tool

Blended learning has been evolving as an important approach to learning and teaching in tertiary education. This approach incorporates learning in both online and face-to-face modes and promotes deep learning by incorporating the best of both approaches. An innovation in blended learning is the use of an online media annotation tool (MAT) in combination with face-to-face classes. This tool allows students to annotate their own or teacher-uploaded video adding to their understanding of professional skills in various disciplines in tertiary education. Examination of MAT occurred in 2011 and included nine cohorts of students using the tool. This article canvasses selected data relating to MAT including insights into the use of blended learning focussing on the challenges of combining face-to-face and online learning using a relatively new online tool.

Analysis and functional annotation of an expressed sequence tag collection for tropical crop sugarcane

To contribute to our understanding of the genome complexity of sugarcane, we undertook a large-scale expressed sequence tag (EST),program. More than 260,000 cDNA clones were partially sequenced from 26 standard cDNA libraries generated from different sugarcane tissues. After the processing of the sequences, 237,954 high-quality ESTs were identified. These ESTs were assembled into 43,141 putative transcripts. of the assembled sequences, 35.6% presented no matches with existing sequences in public databases. A global analysis of the whole SUCEST data set indicated that 14,409 assembled sequences (33% of the total) contained at least one cDNA clone with a full-length insert. Annotation of the 43,141 assembled sequences associated almost 50% of the putative identified sugarcane genes with protein metabolism, cellular communication/signal transduction, bioenergetics, and stress responses. Inspection of the translated assembled sequences for conserved protein domains revealed 40,821 amino acid sequences with 1415 Pfam domains. Reassembling the consensus sequences of the 43,141 transcripts revealed a 22% redundancy in the first assembling. This indicated that possibly 33,620 unique genes had been identified and indicated that >90% of the sugarcane expressed genes were tagged.

Automatic classification of enzyme family in protein annotation

Most of the tasks in genome annotation can be at least partially automated. Since this annotation is time-consuming, facilitating some parts of the process - thus freeing the specialist to carry out more valuable tasks - has been the motivation of many tools and annotation environments. In particular, annotation of protein function can benefit from knowledge about enzymatic processes. The use of sequence homology alone is not a good approach to derive this knowledge when there are only a few homologues of the sequence to be annotated. The alternative is to use motifs. This paper uses a symbolic machine learning approach to derive rules for the classification of enzymes according to the Enzyme Commission (EC). Our results show that, for the top class, the average global classification error is 3.13%. Our technique also produces a set of rules relating structural to functional information, which is important to understand the protein tridimensional structure and determine its biological function. © 2009 Springer Berlin Heidelberg.

A revision of Evaniscus (Hymenoptera, Evaniidae) using ontology-based semantic phenotype annotation

The Neotropical evaniid genus Evaniscus Szepligeti currently includes six species. Two new species are described, Evaniscus lansdownei Mullins, sp. n. from Colombia and Brazil and E. rafaeli Kawada, sp. n. from Brazil. Evaniscus sulcigenis Roman, syn. n., is synonymized under E. rufithorax Enderlein. An identification key to species of Evaniscus is provided. Thirty-five parsimony informative morphological characters are analyzed for six ingroup and four outgroup taxa. A topology resulting in a monophyletic Evaniscus is presented with E. tibialis and E. rafaeli as sister to the remaining Evaniscus species. The Hymenoptera Anatomy Ontology and other relevant biomedical ontologies are employed to create semantic phenotype statements in Entity-Quality (EQ) format for species descriptions. This approach is an early effort to formalize species descriptions and to make descriptive data available to other domains.