X. Benavent

Followers

Following

Co-authors

Public Views

Interests

Uploads

Papers by X. Benavent

Multimedia Retrieval by Means of Merge of Results from Textual and Content Based Retrieval Subsystems

Lecture Notes in Computer Science, 2010

The main goal of this paper it is to present our experiments in Im-ageCLEF 2009 Campaign (photo r... more The main goal of this paper it is to present our experiments in Im-ageCLEF 2009 Campaign (photo retrieval task). In 2008 we proved empirically that the Text-based Image Retrieval (TBIR) methods defeats the Content-based Image Retrieval CBIR "quality" of results, so this time we developed several experiments in which the CBIR helps the TBIR. The TBIR System [6] main improvement is the named-entity sub-module. In case of the CBIR system [3] the number of low-level features has been increased from the 68 component used at ImageCLEF 2008 up to 114 components, and only the Mahalanobis distance has been used. We propose an ad-hoc management of the topics delivered, and the generation of XML structures for 0.5 million captions of the photographs (corpus) delivered. Two different merging algorithms were developed and the third one tries to improve our previous cluster level results promoting the diversity. Our best run for precision metrics appeared in position 16 th , in the 19 th for MAP score, and for diversity value in position 11 th , for a total of 84 submitted experiments. Our best and "only textual" experiment was the 6 th one over 41.

Download

Visual Concept Features and Textual Expansion in a Multimodal System for Concept Annotation and Retrieval with Flickr Photos at ImageCLEF2012

Abstract. This paper presents our submitted experiments in the Concept annotation and Concept Ret... more Abstract. This paper presents our submitted experiments in the Concept annotation and Concept Retrieval tasks using Flickr photos at ImageCLEF 2012. This edition we applied new strategies for both the textual and the visual subsystems included in our multimodal retrieval system. The visual subsystem has focus on extending the low-level features vector with concept features. These concept features have been calculated by means of a logistic regression model. The textual subsystem has focus on expanding the query information using external resources. Our best concept retrieval run, a multimodal one, is at the ninth position with a MnAP of 0.0295, being the second best group of the contest for the multimodal modality. This is also our best run in the global ordered list (where eleven textual runs are also better than it). We have adapted our multimodal retrieval process for the annotation task obtaining non-very good results for this first participation, with a MiAP of 0.1020.

Download

2010 International Conference on Pattern Recognition Wavelet-based Texture Retrieval Modeling the Magnitudes of Wavelet Detail Coefficients with a Generalized Gamma Distribution

Abstract—This paper presents a texture descriptor based on the fine detail coefficients at three ... more Abstract—This paper presents a texture descriptor based on the fine detail coefficients at three resolution levels of a traslation invariant undecimated wavelet transform. First, we consider vertical and horizontal wavelet detail coefficients at the same position as the components of a bivariate random vector, and the magnitude and angle of these vectors are computed. The magnitudes are modeled by a Generalized Gamma distribution. Their parameters, together with the circular histograms of angles, are used to characterize each texture image of the database. The Kullback-Leibler divergence is used as the similarity measurement. Retrieval experiments, in which we compare two wavelet transforms, are carried out on the Brodatz texture collection. Results reveal the good performance of this wavelet-based texture descriptor obtained via the Generalized Gamma distribution.

A.: Multimodal Information Approaches for the Wikipedia Collection at ImageCLEF

Abstract. The main goal of this paper it is to present our experiments in ImageCLEF 2011 Campaign... more Abstract. The main goal of this paper it is to present our experiments in ImageCLEF 2011 Campaign (Wikipedia retrieval task). This edition we focused on applying different strategies of merging multimodal information, textual and visual, following both early and late fusion approaches. Our best runs are in the top ten of the global list, at positions 8, 9 and 10 with MAP 0.3405, 0.3367 and 0.323, being the second best group of the contest. Moreover, 18 of the 20 runs submitted are above the average MAP of its own modality (textual or mixed). In our system, the TBIR module works firstly and acts as a filter, and the CBIR system works only with the filtered sub-collection. The two ranked lists are fused using its own probability in a final ranked list. The best run of the TBIR system is in position 14 with a MAP of 0.3044, and uses subsystems IDRA and Lucene, fusing monolingual experiments carried out with IDRA preprocessing and Lucene search engine, taking into account extra informat...

Download

A multimedia IR-based system for the Photo Annotation Task at ImageCLEF2013

Abstract. The UNED-UV group at the ImageCLEF2013 Campaign have par-ticipated in the Scalable Conc... more Abstract. The UNED-UV group at the ImageCLEF2013 Campaign have par-ticipated in the Scalable Concept Image Annotation subtask. We present a mul-timedia IR-based system for the annotation task. In this collection, the images do not have any textual description associated, so we have downloaded and pre-processed the web pages which contain the images. Regarding the concepts, we expanded their textual description with additional information from external re-sources as Wikipedia or WordNet and we generate a KLD concept model using recovered textual information. The multimedia IR-based system uses a logistic relevance algorithm to get a model for each of the concepts to be trained using visual image features. Finally, the fusion subsystem merges textual and visual scores for a certain image to belong a concept, and decides the presence of the concept in the images.

Download

Using Visual Concept Features in a Multimodal Retrieval System for the Medical collection at ImageCLEF2012

Abstract. The main goal of this paper is to present our experiments in the classification modalit... more Abstract. The main goal of this paper is to present our experiments in the classification modality and in the ad-hoc image retrieval tasks with the Medical collection at ImageCLEF 2012 Campaign. This edition we focus on applying new strategies for both the textual and the visual subsystems included in our multimodal retrieval system. The visual subsystem has focus on extending the low-level features vector with concept features. These concept features have been calculated by means of a logistic regression model. The textual subsystem has focus on applying a query reformulation to remove general and domain stop-words, trying to produce a query with only medical-related terms. We have not obtained the results as good as obtained at the Photo annotation retrieval subtask using similar techniques. Therefore, a deep analysis for the Medical collection will be done.

Download

Image retrieval system for citizen services using penalized logistic regression models

Proceedings of the 10th Euro-American Conference on Telematics and Information Systems

This paper describes a procedure to deal with large image collections obtained by smart city serv... more This paper describes a procedure to deal with large image collections obtained by smart city services based on interaction with citizens providing pictures. The semantic gap between the low-level image features and represented concepts and situations has been addressed using image retrieval techniques. A relevance feedback procedure is proposed for Content-Based Image Retrieval (CBIR) based on the modelling of user responses. One of the novelties of the proposal is that the feedback learning procedure can use the information that citizens themselves can provide when using these services. The proposed algorithm considers the probability of an image belonging to the set of those sought by the user, by selecting a set of relevant and irrelevant images to the query, and by adjusting a penalized logistic regression model to the information provided by the user. The Wikipedia2011 image collection has been used for testing purposes. The procedure has been compared to other retrieval relevance feedback procedures in recent literature. Good results have been obtained with just one global model fitted with high dimensionality data.

Image retrieval system for citizen services using penalized logistic regression models

Proceedings of the 10th Euro-American Conference on Telematics and Information Systems, 2020

Visual navigation on optic flow

ABSTRACT

Visual navigation on optic flow

Netherlands Heart Journal, 1997

ABSTRACT

Wavelet-Based Texture Retrieval Modeling the Magnitudes of Wavelet Detail Coefficients with a Generalized Gamma Distribution

2010 20th International Conference on Pattern Recognition, 2010

This paper presents a texture descriptor based on the fine detail coefficients at three resolutio... more This paper presents a texture descriptor based on the fine detail coefficients at three resolution levels of a traslation invariant undecimated wavelet transform. First, we consider vertical and horizontal wavelet detail coefficients at the same position as the components of a bivariate random vector, and the magnitude and angle of these vectors are computed. The magnitudes are modeled by a Generalized Gamma distribution. Their parameters, together with the circular histograms of angles, are used to characterize each texture image of the database. The Kullback-Leibler divergence is used as the similarity measurement. Retrieval experiments, in which we compare two wavelet transforms, are carried out on the Brodatz texture collection. Results reveal the good performance of this wavelet-based texture descriptor obtained via the Generalized Gamma distribution.

Download

Modeling user preferences in content-based image retrieval: A novel attempt to bridge the semantic gap

Neurocomputing, 2015

ABSTRACT This paper is concerned with content-based image retrieval from a stochastic point of vi... more ABSTRACT This paper is concerned with content-based image retrieval from a stochastic point of view. The semantic gap problem is addressed in two ways. First, a dimensional reduction is applied using the (pre-calculated) distances among images. The dimension of the reduced vector is the number of preferences that we allow the user to choose from, in this case, three levels. Second, the conditional probability distribution of the random user preference, given this reduced feature vector, is modeled using a proportional odds model. A new model is fitted at each iteration. The score used to rank the image database is based on the estimated probability function of the random preference. Additionally, some memory is incorporated in the procedure by weighting the current and previous scores. Also, a novel evaluation procedure is proposed in this work based on the empirical commutative distribution functions of the relevant and non-relevant retrieved images. Good experimental results are achieved in very different experimental setups and tested in different databases.

Vehicle navigation on optic ﬂow _

Vehicle navigation on optic

MIRACLE (FI) at ImageCLEFphoto 2009

The Miracle-FI participation at ImageCLEF 2009 photo retrieval task main goal was to improve the ... more The Miracle-FI participation at ImageCLEF 2009 photo retrieval task main goal was to improve the merge of content-based and text-based techniques in our experiments. The global system includes our own implemented tool IDRA (InDexing and Retrieving Automatically), and the Valencia University CBIR system. Analyzing both "topics_part1.txt" and "topics_part2.txt" task topics files, we have built different queries files, eliminating the negative sentences with the text from title and clusterTitle or clusterDescription, one query for each cluster (or not) of each topic from 1 to 25 and one for each of the three images of each topic from 26 to 50. In the CBIR system the number of low-level features has been increased from the 68 component used at ImageCLEF 2008 up to 114 components, and in this edition only the Mahalanobis distance has been used in our experiments. Three different merging algorithms were developed in order to fuse together different results lists from visual or textual modules, different textual indexations, or cluster level results into a unique topic level results list. For the five runs submitted we observe that MirFI1, MirFI2 and MifFI3 obtain quite higher precision values than the average ones. Experiment MirFI1, our best run for precision metrics (very similar to MirFI2 and MirFI3), appears in the 16th position in R-Precision classification and in the 19th in MAP one (from a total of 84 submitted experiments). MirFI4 and MirFI5 obtain our best diversity values, appearing in position 11th (over 84) in cluster recall classification, and being the 5th best group from all the 19 participating ones.

Download

A multimedia IR-based system for the Photo Annotation Task at ImageCLEF2013

The UNED-UV group at the ImageCLEF2013 Campaign have participated in the Scalable Concept Image A... more The UNED-UV group at the ImageCLEF2013 Campaign have participated in the Scalable Concept Image Annotation subtask. We present a multimedia IR-based system for the annotation task. In this collection, the images do not have any textual description associated, so we have downloaded and preprocessed the web pages which contain the images. Regarding the concepts, we expanded their textual description with additional information from external resources as Wikipedia or WordNet and we generate a KLD concept model using recovered textual information. The multimedia IR-based system uses a logistic relevance algorithm to get a model for each of the concepts to be trained using visual image features. Finally, the fusion subsystem merges textual and visual scores for a certain image to belong a concept, and decides the presence of the concept in the images.

Download

Using visual concep features in a multimodal retrieval system for the medical collection at Image-CLEF2012

Visual Concept Features and Textual Expansion in a Multimodal System for Concept Annotation and Retrieval with Flickr Photos at ImageCLEF2012

On the Use of Longitudinal Data Techniques for Modeling the Behavior of a Complex System

Lecture Notes in Computer Science, 2002

This work presents the use of longitudinal data analysis techniques to fit the accelerations of a... more This work presents the use of longitudinal data analysis techniques to fit the accelerations of a real car in terms of some previous throttle pedal measurements and of the current time. Different repetitions of the same driving maneuvers have been observed in a real car, which constitute the data used to learn the model. The natural statistical framework to analyze these data is to consider it as a particular case of longitudinal data. Different fits are given and tested as a first step in order to explain the relationship between variables describing the control of the car by the driver and the final variables describing the movement of the vehicle. Results show that the approach can be valid in those cases in which a temporal implicit dependency can be assumed and in which several realizations of the experiment in similar conditions are available; in such cases an analytical model of the system can be obtained which has the ability to generalize, i.e. to show a robust behavior when faced to input data not used in the model construction phase.

Download

A New Wavelet-Based Texture Descriptor for Image Retrieval

Lecture Notes in Computer Science, 2007

This paper presents a novel texture descriptor based on the wavelet transform. First, we will con... more This paper presents a novel texture descriptor based on the wavelet transform. First, we will consider vertical and horizontal coefficients at the same position as the components of a bivariate random vector. The magnitud and angle of these vectors are computed and its histograms are analyzed. This empirical magnitud histogram is modelled by using a gamma distribution (pdf). As a result, the feature extraction step consists of estimating the gamma parameters using the maxima likelihood estimator and computing the circular histograms of angles. The similarity measurement step is done by means of the well-known Kullback-Leibler divergence. Finally, retrieval experiments are done using the Brodatz texture collection obtaining a good performance of this new texture descriptor. We compare two wavelet transforms, with and without downsampling, and show the advantage of the second one, which is translation invariant, for the construction of our texture descriptor.

Download

X. Benavent

Uploads

Papers by X. Benavent

Log In