A rank aggregation framework for video multimodal geocoding

This paper proposes a rank aggregation framework for video multimodal geocoding. Textual and visual descriptions associated with videos are used to define ranked lists. These ranked lists are later combined, and the resulting ranked list is used to define appropriate locations for videos. An architecture that implements the proposed framework is designed. In this architecture, there are specific modules for each modality (e.g, textual and visual) that can be developed and evolved independently. Another component is a data fusion module responsible for combining seamlessly the ranked lists defined for each modality. We have validated the proposed framework in the context of the MediaEval 2012 Placing Task, whose objective is to automatically assign geographical coordinates to videos. Obtained results show how our multimodal approach improves the geocoding results when compared to methods that rely on a single modality (either textual or visual descriptors). We also show that the proposed multimodal approach yields comparable results to the best submissions to the Placing Task in 2012 using no extra information besides the available development/training data. Another contribution of this work is related to the proposal of a new effectiveness evaluation measure. The proposed measure is based on distance scores that summarize how effective a designed/tested approach is, considering its overall result for a test dataset. © 2013 Springer Science+Business Media New York.

Rank Aggregation for Pattern Classifier Selection in Remote Sensing Images

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Unsupervised manifold learning using Reciprocal kNN Graphs in image re-ranking and rank aggregation tasks

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Semi-supervised learning for relevance feedback on image retrieval tasks

Relevance feedback approaches have been established as an important tool for interactive search, enabling users to express their needs. However, in view of the growth of multimedia collections available, the user efforts required by these methods tend to increase as well, demanding approaches for reducing the need of user interactions. In this context, this paper proposes a semi-supervised learning algorithm for relevance feedback to be used in image retrieval tasks. The proposed semi-supervised algorithm aims at using both supervised and unsupervised approaches simultaneously. While a supervised step is performed using the information collected from the user feedback, an unsupervised step exploits the intrinsic dataset structure, which is represented in terms of ranked lists of images. Several experiments were conducted for different image retrieval tasks involving shape, color, and texture descriptors and different datasets. The proposed approach was also evaluated on multimodal retrieval tasks, considering visual and textual descriptors. Experimental results demonstrate the effectiveness of the proposed approach.

TEXT-MESS: Intelligent, Interactive and Multilingual Text Mining based on Human Language Technologies, TIN2006-15265-C06

The goal of the project is to analyze, experiment, and develop intelligent, interactive and multilingual Text Mining technologies, as a key element of the next generation of search engines, systems with the capacity to find "the need behind the query". This new generation will provide specialized services and interfaces according to the search domain and type of information needed. Moreover, it will integrate textual search (websites) and multimedia search (images, audio, video), it will be able to find and organize information, rather than generating ranked lists of websites.

Finding relevant search engine results:a minimax linear programming approach

For a submitted query to multiple search engines finding relevant results is an important task. This paper formulates the problem of aggregation and ranking of multiple search engines results in the form of a minimax linear programming model. Besides the novel application, this study detects the most relevant information among a return set of ranked lists of documents retrieved by distinct search engines. Furthermore, two numerical examples aree used to illustrate the usefulness of the proposed approach.

Community relation discovery by named entities

Discovering who works with whom, on which projects and with which customers is a key task in knowledge management. Although most organizations keep models of organizational structures, these models do not necessarily accurately reflect the reality on the ground. In this paper we present a text mining method called CORDER which first recognizes named entities (NEs) of various types from Web pages, and then discovers relations from a target NE to other NEs which co-occur with it. We evaluated the method on our departmental Website. We used the CORDER method to first find related NEs of four types (organizations, people, projects, and research areas) from Web pages on the Website and then rank them according to their co-occurrence with each of the people in our department. 20 representative people were selected and each of them was presented with ranked lists of each type of NE. Each person specified whether these NEs were related to him/her and changed or confirmed their rankings. Our results indicate that the method can find the NEs with which these people are closely related and provide accurate rankings.

Leveraging Multiple Features for Image Retrieval and Matching

The goal of image retrieval and matching is to find and locate object instances in images from a large-scale image database. While visual features are abundant, how to combine them to improve performance by individual features remains a challenging task. In this work, we focus on leveraging multiple features for accurate and efficient image retrieval and matching. We first propose two graph-based approaches to rerank initially retrieved images for generic image retrieval. In the graph, vertices are images while edges are similarities between image pairs. Our first approach employs a mixture Markov model based on a random walk model on multiple graphs to fuse graphs. We introduce a probabilistic model to compute the importance of each feature for graph fusion under a naive Bayesian formulation, which requires statistics of similarities from a manually labeled dataset containing irrelevant images. To reduce human labeling, we further propose a fully unsupervised reranking algorithm based on a submodular objective function that can be efficiently optimized by greedy algorithm. By maximizing an information gain term over the graph, our submodular function favors a subset of database images that are similar to query images and resemble each other. The function also exploits the rank relationships of images from multiple ranked lists obtained by different features. We then study a more well-defined application, person re-identification, where the database contains labeled images of human bodies captured by multiple cameras. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information. We apply a novel multi-task learning algorithm using both low level features and attributes. A low rank attribute embedding is joint learned within the multi-task learning formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered. To locate objects in images, we design an object detector based on object proposals and deep convolutional neural networks (CNN) in view of the emergence of deep networks. We improve a Fast RCNN framework and investigate two new strategies to detect objects accurately and efficiently: scale-dependent pooling (SDP) and cascaded rejection classifiers (CRC). The SDP improves detection accuracy by exploiting appropriate convolutional features depending on the scale of input object proposals. The CRC effectively utilizes convolutional features and greatly eliminates negative proposals in a cascaded manner, while maintaining a high recall for true objects. The two strategies together improve the detection accuracy and reduce the computational cost.

Query routing in cooperative semi-structured peer-to-peer information retrieval networks

Conventional web search engines are centralised in that a single entity crawls and indexes the documents selected for future retrieval, and the relevance models used to determine which documents are relevant to a given user query. As a result, these search engines suffer from several technical drawbacks such as handling scale, timeliness and reliability, in addition to ethical concerns such as commercial manipulation and information censorship. Alleviating the need to rely entirely on a single entity, Peer-to-Peer (P2P) Information Retrieval (IR) has been proposed as a solution, as it distributes the functional components of a web search engine – from crawling and indexing documents, to query processing – across the network of users (or, peers) who use the search engine. This strategy for constructing an IR system poses several efficiency and effectiveness challenges which have been identified in past work. Accordingly, this thesis makes several contributions towards advancing the state of the art in P2P-IR effectiveness by improving the query processing and relevance scoring aspects of a P2P web search. Federated search systems are a form of distributed information retrieval model that route the user’s information need, formulated as a query, to distributed resources and merge the retrieved result lists into a final list. P2P-IR networks are one form of federated search in routing queries and merging result among participating peers. The query is propagated through disseminated nodes to hit the peers that are most likely to contain relevant documents, then the retrieved result lists are merged at different points along the path from the relevant peers to the query initializer (or namely, customer). However, query routing in P2P-IR networks is considered as one of the major challenges and critical part in P2P-IR networks; as the relevant peers might be lost in low-quality peer selection while executing the query routing, and inevitably lead to less effective retrieval results. This motivates this thesis to study and propose query routing techniques to improve retrieval quality in such networks. Cluster-based semi-structured P2P-IR networks exploit the cluster hypothesis to organise the peers into similar semantic clusters where each such semantic cluster is managed by super-peers. In this thesis, I construct three semi-structured P2P-IR models and examine their retrieval effectiveness. I also leverage the cluster centroids at the super-peer level as content representations gathered from cooperative peers to propose a query routing approach called Inverted PeerCluster Index (IPI) that simulates the conventional inverted index of the centralised corpus to organise the statistics of peers’ terms. The results show a competitive retrieval quality in comparison to baseline approaches. Furthermore, I study the applicability of using the conventional Information Retrieval models as peer selection approaches where each peer can be considered as a big document of documents. The experimental evaluation shows comparative and significant results and explains that document retrieval methods are very effective for peer selection that brings back the analogy between documents and peers. Additionally, Learning to Rank (LtR) algorithms are exploited to build a learned classifier for peer ranking at the super-peer level. The experiments show significant results with state-of-the-art resource selection methods and competitive results to corresponding classification-based approaches. Finally, I propose reputation-based query routing approaches that exploit the idea of providing feedback on a specific item in the social community networks and manage it for future decision-making. The system monitors users’ behaviours when they click or download documents from the final ranked list as implicit feedback and mines the given information to build a reputation-based data structure. The data structure is used to score peers and then rank them for query routing. I conduct a set of experiments to cover various scenarios including noisy feedback information (i.e, providing positive feedback on non-relevant documents) to examine the robustness of reputation-based approaches. The empirical evaluation shows significant results in almost all measurement metrics with approximate improvement more than 56% compared to baseline approaches. Thus, based on the results, if one were to choose one technique, reputation-based approaches are clearly the natural choices which also can be deployed on any P2P network.

Surface and subterranean ichthyofauna in the Serra do Ramalho karst area, northeastern Brazil, with updated lists of Brazilian troglobitic and troglophilic fishes

After an ichthyofaunistic survey in several epigean (surface) water bodies of the Serra do Ramalho, southern Bahia, conducted in May 2007, 44 species were recorded; in addition, three non-troglomorphic (normally eyed and pigmented) and two troglomorphic species were recorded only in caves, totaling 49 species of fishes for the area, which represents a little more than one fourth of the total registered in the literature for the entire Rio São Francisco basin. In these caves, which have been studied since 2005, eight non-troglomorphic species were sampled and their presence in both epigean and subterranean habitats, associated to the lack of morphological differences, indicate that they may be either troglophiles (species encompassing individuals able to live and complete their life cycle either in the surface or in the subterranean environment), trogloxenes (individuals regularly found in subterranean habitats, but which must return periodically to the surface in order to complete their life cycle) or even accidental in caves. In addition, two troglomorphic species (with reduced eyes and melanic pigmentation when compared to close epigean relatives), belonging respectively to the genera Rhamdia and Trichomycterus, were recorded exclusively in caves, thus classified as troglobites. Interestingly, no epigean representative of the genus Trichomycterus was collected. The new data are integrated into updated lists of Brazilian troglobitic and troglophilic fishes, based on published data and new records recently confirmed.

Fossil groups in the Millennium Simulation Evolution of the brightest galaxies

Aims. We create a catalogue of simulated fossil groups and study their properties, in particular the merging histories of their first-ranked galaxies. We compare the simulated fossil group properties with those of both simulated non-fossil and observed fossil groups. Methods. Using simulations and a mock galaxy catalogue, we searched for massive (>5 x 10(13) h(-1) M-circle dot) fossil groups in the Millennium Simulation Galaxy Catalogue. In addition, we attempted to identify observed fossil groups in the Sloan Digital Sky Survey Data Release 6 using identical selection criteria. Results. Our predictions on the basis of the simulation data are: (a) fossil groups comprise about 5.5% of the total population of groups/clusters with masses larger than 5 x 10(13) h(-1) M-circle dot. This fraction is consistent with the fraction of fossil groups identified in the SDSS, after all observational biases have been taken into account; (b) about 88% of the dominant central objects in fossil groups are elliptical galaxies that have a median R-band absolute magnitude of similar to-23.5-5 log h, which is typical of the observed fossil groups known in the literature; (c) first-ranked galaxies of systems with M > 5 x 10(13) h(-1) M-circle dot, regardless of whether they are either fossil or non-fossil, are mainly formed by gas-poor mergers; (d) although fossil groups, in general, assembled most of their virial masses at higher redshifts in comparison with non-fossil groups, first-ranked galaxies in fossil groups merged later, i.e. at lower redshifts, compared with their non-fossil-group counterparts. Conclusions. We therefore expect to observe a number of luminous galaxies in the centres of fossil groups that show signs of a recent major merger.

The merging cluster Abell 1758 revisited: multi-wavelength observations and numerical simulations

Context. Cluster properties can be more distinctly studied in pairs of clusters, where we expect the effects of interactions to be strong. Aims. We here discuss the properties of the double cluster Abell 1758 at a redshift z similar to 0.279. These clusters show strong evidence for merging. Methods. We analyse the optical properties of the North and South cluster of Abell 1758 based on deep imaging obtained with the Canada-France-Hawaii Telescope (CFHT) archive Megaprime/Megacam camera in the g' and r' bands, covering a total region of about 1.05 x 1.16 deg(2), or 16.1 x 17.6 Mpc(2). Our X-ray analysis is based on archive XMM-Newton images. Numerical simulations were performed using an N-body algorithm to treat the dark-matter component, a semi-analytical galaxy-formation model for the evolution of the galaxies and a grid-based hydrodynamic code with a parts per million (PPM) scheme for the dynamics of the intra-cluster medium. We computed galaxy luminosity functions (GLFs) and 2D temperature and metallicity maps of the X-ray gas, which we then compared to the results of our numerical simulations. Results. The GLFs of Abell 1758 North are well fit by Schechter functions in the g' and r' bands, but with a small excess of bright galaxies, particularly in the r' band; their faint-end slopes are similar in both bands. In contrast, the GLFs of Abell 1758 South are not well fit by Schechter functions: excesses of bright galaxies are seen in both bands; the faint-end of the GLF is not very well defined in g'. The GLF computed from our numerical simulations assuming a halo mass-luminosity relation agrees with those derived from the observations. From the X-ray analysis, the most striking features are structures in the metal distribution. We found two elongated regions of high metallicity in Abell 1758 North with two peaks towards the centre. In contrast, Abell 1758 South shows a deficit of metals in its central regions. Comparing observational results to those derived from numerical simulations, we could mimic the most prominent features present in the metallicity map and propose an explanation for the dynamical history of the cluster. We found in particular that in the metal-rich elongated regions of the North cluster, winds had been more efficient than ram-pressure stripping in transporting metal-enriched gas to the outskirts. Conclusions. We confirm the merging structure of the North and South clusters, both at optical and X-ray wavelengths.

Merging Resource Availability with Isotope Mixing Models: The Role of Neutral Interaction Assumptions

Background: Bayesian mixing models have allowed for the inclusion of uncertainty and prior information in the analysis of trophic interactions using stable isotopes. Formulating prior distributions is relatively straightforward when incorporating dietary data. However, the use of data that are related, but not directly proportional, to diet (such as prey availability data) is often problematic because such information is not necessarily predictive of diet, and the information required to build a reliable prior distribution for all prey species is often unavailable. Omitting prey availability data impacts the estimation of a predator's diet and introduces the strong assumption of consumer ultrageneralism (where all prey are consumed in equal proportions), particularly when multiple prey have similar isotope values. Methodology: We develop a procedure to incorporate prey availability data into Bayesian mixing models conditional on the similarity of isotope values between two prey. If a pair of prey have similar isotope values (resulting in highly uncertain mixing model results), our model increases the weight of availability data in estimating the contribution of prey to a predator's diet. We test the utility of this method in an intertidal community against independently measured feeding rates. Conclusions: Our results indicate that our weighting procedure increases the accuracy by which consumer diets can be inferred in situations where multiple prey have similar isotope values. This suggests that the exchange of formalism for predictive power is merited, particularly when the relationship between prey availability and a predator's diet cannot be assumed for all species in a system.

Zone trapping/merging zones in flow analysis: A novel approach for rapid assays involving relatively slow chemical reactions

A novel strategy for accomplishing zone trapping in flow analysis is proposed. The sample and the reagent solutions are simultaneously inserted into convergent carrier streams and the established zones merge together before reaching the detector, where the most concentrated portion of the entire sample zone is trapped. The main characteristics, potentialities and limitations of the strategy were critically evaluated in relation to an analogous flow system with zone stopping. When applied to the spectrophotometric determination of nitrite in river waters, the main figures of merit were maintained, exception made for the sampling frequency which was calculated as 189h(-1), about 32% higher relatively to the analogous system with zone stopping. The sample inserted volume can be increased up to 1.0 mL without affecting sampling frequency and no problems with pump heating or malfunctions were noted after 8-h operation of the system. In contrast to zone stopping, only a small portion of the sample zone is halted with zone trapping, leading to these beneficial effects. (C) 2011 Elsevier B.V. All rights reserved.