Elöd Egyed-Zsigmond

Club ♣ (Tréfle): a use trace model

In this paper we present a use trace model which allows the collection and reuse of user experience, based on a homogeneous and interconnected representation of users, procedures and objects. All these notions form a connected labeled directed graph containing highly connected and explained use traces. This model enables assistance in non trivial, creativity requiring situations. Our model uses the Case Based Reasoning (CBR) paradigm in order to reuse experience. After a formal description of the model we discuss how it can serve to capitalize and re-use experience.

World-wide scale geotagged image dataset for automatic image annotation and reverse geotagging

In this paper, a dataset of geotagged photos on a world-wide scale is presented. The dataset contains a sample of more than 14 million geotagged photos crawled from Flickr with the corresponding metadata. To guarantee the spatial representativeness of the dataset, a crawling approach based on the small-world phenomena and the Flickr friendships graph is applied. Furthermore, the noisiness of user-provided tags is reduced through an automatic tag cleaning approach. To enable efficient retrieval, photos in the dataset are indexed based on their location information using quad-tree data structure. The dataset can assists different applications, especially, search-based automatic image annotation and reverse geotagging.

Combining Relations and Text in Scientific Network Clustering

In this paper, we present different combined clustering methods and we evaluate their performances and their results on a dataset with ground truth. This dataset, built from several sources, contains a scientific social network in which textual data is associated to each vertex and the classes are known. Indeed, while the clustering task is widely studied both in graph clustering and in non supervised learning, combined clustering which exploits simultaneously the relationships between the vertices and attributes describing them, is quite new. We argue that, depending on the kind of data we have and the type of results we want, the choice of the clustering method is important and we present some concrete examples for underlining this.

Geo-based automatic image annotation

A huge number of user-tagged images are daily uploaded to the web. Recently, a growing number of those images are also geotagged. These provide new opportunities for solutions to automatically tag images so that efficient image management and retrieval can be achieved. In this paper an automatic image annotation approach is proposed. It is based on a statistical model that combines two different kinds of information: high level information represented by user tags of images captured in the same location as a new unlabeled image (input image); and low level information represented by the visual similarity between the input image and the collection of geographically similar images. To maximize the number of images that are visually similar to the input image, an iterative visual matching approach is proposed and evaluated. The results show that a significant recall improvement can be achieved with an increasing number of iterations. The quality of the recommended tags has also been evaluated and an overall good performance has been observed.

Improving SURF Image Matching Using Supervised Learning

Key points-based image matching algorithms have proven very successful in recent years. However, their execution time makes them unsuitable for online applications. Indeed, identifying similar key points requires comparing a large number of high dimensional descriptor vectors. Previous work has shown that matching could be still accurately performed when only considering a few highly significant key points. In this paper, we investigate reducing the number of generated SURF features to speed up image matching while maintaining the matching recall at a high level. We propose a machine learning approach that uses a binary classifier to identify key points that are useful for the matching process. Furthermore, we compare the proposed approach to another method for key point pruning based on saliency maps. The two approaches are evaluated using ground truth datasets. The evaluation shows that the proposed classification-based approach outperforms the adversary in terms of the trade-off between the matching recall and the percentage of reduced key points. Additionally, the evaluation demonstrates the ability of the proposed approach of effectively reducing the matching runtime.

Similarity Measures to Compare Episodes in Modeled Traces

This paper reports on a similarity measure to compare episodes in modeled traces. A modeled trace is a structured record of observations captured from users’ interactions with a computer system. An episode is a sub-part of the modeled trace, describing a particular task performed by the user. Our method relies on the definition of a similarity measure for comparing elements of episodes, combined with the implementation of the Smith-Waterman Algorithm for comparison of episodes. This algorithm is both accurate in terms of temporal sequencing and tolerant to noise generally found in the traces that we deal with. Our evaluations show that our approach offers quite satisfactory comparison quality and response time. We illustrate its use in the context of an application for video sequences recommendation.

Getting Clusters from Structure Data and Attribute Data

If the clustering task is widely studied both in graph clustering and in non supervised learning, combined clustering which exploits simultaneously the relationships between the vertices and attributes describing them, is quite new. In this paper, we present different scenarios for this task and, we evaluate their performances and their results on a dataset, with ground truth, built from several sources and containing a scientific social network in which textual data is associated to each vertex and the classes are known. We argue that, depending on the kind of data we have and the type of results we want, the choice of the clustering method is important and we present some concrete examples for underlining this.

Tag Relatedness Using Laplacian Score Feature Selection and Adapted Jensen-Shannon Divergence

Folksonomies - networks of users, resources, and tags allow users to easily retrieve, organize and browse web contents. However, their advantages are still limited according to the noisiness of user provided tags. To overcome this problem, we propose an approach for identifying related tags in folksonomies. The approach uses tag co-occurrence statistics and Laplacian score feature selection to create probability distribution for each tag. Consequently, related tags are determined according to the distance between their distributions. In this regards, we propose a distance metric based on Jensen-Shannon Divergence. The new metric named AJSD deals with the noise in the measurements due to statistical fluctuations in tag co-occurrences. We experimentally evaluated our approach using WordNet and compared it to a common tag relatedness approach based on the cosine similarity. The results show the effectiveness of our approach and its advantage over the adversary method.

Modeling, encoding and querying multi-structured documents

The issue of multi-structured documents became prominent with the emergence of the digital Humanities field of practices. Many distinct structures may be defined simultaneously on the same original content for matching different documentary tasks. For example, a document may have both a structure for the logical organization of content (logical structure), and a structure expressing a set of content formatting rules (physical structure). In this paper, we present MSDM, a generic model for multi-structured documents, in which several important features are established. We also address the problem of efficiently encoding multi-structured documents by introducing MultiX, a new XML formalism based on the MSDM model. Finally, we propose a library of Xquery functions for querying MultiX documents. We will illustrate all the contributions with a use case based on a fragment of an old manuscript.

Contextual trace-based video recommendations

People like creating their own videos by mixing various contents. Many applications allow us to generate video clips by merging different media like videos clips, photos, text and sounds. Some of these applications enable us to combine online content with our own resources. Given the large amount of content available, the problem is to quickly find content that truly meet our needs. This is when recommender systems come in. In this paper, we propose an approach for contextual video recommendations based on a Trace-Based Reasoning approach.