Pub Date : 2016-06-15DOI: 10.1109/CBMI.2016.7500238
Vu-Lam Nguyen, Ngoc-Son Vu, P. Gosselin
In this paper, we propose a combined feature approach which takes full advantages of local structure information and the more global one for improving texture image classification results. In this way, Local Binary Pattern is used for extracting local features, whilst the Scattering Transform feature plays the role of a global descriptor. Intensive experiments conducted on many texture benchmarks such as ALOT, CUReT, KTH-TIPS2-a, KTH-TIPS2b, and OUTEX show that the combined method outweigh each one which stands alone in term of classification accuracy. Also, our method outperforms many others, whilst it is comparable to state of the art on the experimented datasets.
{"title":"A scattering transform combination with local binary pattern for texture classification","authors":"Vu-Lam Nguyen, Ngoc-Son Vu, P. Gosselin","doi":"10.1109/CBMI.2016.7500238","DOIUrl":"https://doi.org/10.1109/CBMI.2016.7500238","url":null,"abstract":"In this paper, we propose a combined feature approach which takes full advantages of local structure information and the more global one for improving texture image classification results. In this way, Local Binary Pattern is used for extracting local features, whilst the Scattering Transform feature plays the role of a global descriptor. Intensive experiments conducted on many texture benchmarks such as ALOT, CUReT, KTH-TIPS2-a, KTH-TIPS2b, and OUTEX show that the combined method outweigh each one which stands alone in term of classification accuracy. Also, our method outperforms many others, whilst it is comparable to state of the art on the experimented datasets.","PeriodicalId":356608,"journal":{"name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133344774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-15DOI: 10.1109/CBMI.2016.7500272
M. Fernandez-Torres, I. González-Díaz, F. Díaz-de-María
The modeling of visual attention has gained much interest during the last few years since it allows to efficiently drive complex visual processes to particular areas of images or video frames. Although the literature concerning bottom-up saliency models is vast, we still lack of generic approaches modeling top-down task and context-driven visual attention. Indeed, many top-down models simply modulate the weights associated to low-level descriptors to learn more accurate representations of visual attention than those ones of the generic fusion schemes in bottom-up techniques. In this paper we propose a hierarchical generic probabilistic framework that decomposes the complex process of context-driven visual attention into a mixture of latent subtasks, each of them being in turn modeled as a combination of specific distributions of low-level descriptors. The inclusion of this intermediate level bridges the gap between low-level features and visual attention and enables more comprehensive representations of the later. Our experiments on a dataset in which videos are organized by genre demonstrate that, by learning specific distributions for each video category, we can notably enhance the system performance.
{"title":"A probabilistic topic approach for context-aware visual attention modeling","authors":"M. Fernandez-Torres, I. González-Díaz, F. Díaz-de-María","doi":"10.1109/CBMI.2016.7500272","DOIUrl":"https://doi.org/10.1109/CBMI.2016.7500272","url":null,"abstract":"The modeling of visual attention has gained much interest during the last few years since it allows to efficiently drive complex visual processes to particular areas of images or video frames. Although the literature concerning bottom-up saliency models is vast, we still lack of generic approaches modeling top-down task and context-driven visual attention. Indeed, many top-down models simply modulate the weights associated to low-level descriptors to learn more accurate representations of visual attention than those ones of the generic fusion schemes in bottom-up techniques. In this paper we propose a hierarchical generic probabilistic framework that decomposes the complex process of context-driven visual attention into a mixture of latent subtasks, each of them being in turn modeled as a combination of specific distributions of low-level descriptors. The inclusion of this intermediate level bridges the gap between low-level features and visual attention and enables more comprehensive representations of the later. Our experiments on a dataset in which videos are organized by genre demonstrate that, by learning specific distributions for each video category, we can notably enhance the system performance.","PeriodicalId":356608,"journal":{"name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116357670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-15DOI: 10.1109/CBMI.2016.7500271
M. Riegler, Konstantin Pogorelov, M. Lux, P. Halvorsen, C. Griwodz, T. Lange, S. Eskeland
Exploring and annotating collections of images without meta-data is a laborious task. Visual analytics and information visualization can help users by providing interfaces for exploration and annotation. In this paper, we show a prototype application that allows users from the medical domain to use feature-based clustering to perform explorative browsing and annotation in an unsupervised manner. For this, we utilize global image feature extraction, different unsupervised clustering algorithms and hyperbolic tree representation. First, the prototype application extracts features from images or video frames, and then, one or multiple features at the same time can be used to perform clustering. The clusters are presented to the users as a hyperbolic tree for visual analysis and annotation.
{"title":"Explorative hyperbolic-tree-based clustering tool for unsupervised knowledge discovery","authors":"M. Riegler, Konstantin Pogorelov, M. Lux, P. Halvorsen, C. Griwodz, T. Lange, S. Eskeland","doi":"10.1109/CBMI.2016.7500271","DOIUrl":"https://doi.org/10.1109/CBMI.2016.7500271","url":null,"abstract":"Exploring and annotating collections of images without meta-data is a laborious task. Visual analytics and information visualization can help users by providing interfaces for exploration and annotation. In this paper, we show a prototype application that allows users from the medical domain to use feature-based clustering to perform explorative browsing and annotation in an unsupervised manner. For this, we utilize global image feature extraction, different unsupervised clustering algorithms and hyperbolic tree representation. First, the prototype application extracts features from images or video frames, and then, one or multiple features at the same time can be used to perform clustering. The clusters are presented to the users as a hyperbolic tree for visual analysis and annotation.","PeriodicalId":356608,"journal":{"name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132235715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-15DOI: 10.1109/CBMI.2016.7500261
S. Dupont, Omar Seddati, S. Mahmoudi
Freehand sketches are a simple and powerful tool for communication. They are easily recognized across cultures and suitable for various applications. In this paper, we propose a new approach for partial sketch recognition. This could be used to design applications using real-time sketch recognition. We use deep convolutional neural networks (ConvNets), state-of-the-art in the field of sketch recognition. To the best of our knowledge, it is the first ConvNet for partial sketch classification. Our first aim is to build a ConvNet capable of recognizing partial sketches without compromising the accuracy reached for complete sketch recognition. Therefore, we evaluate different approaches and propose an efficient way for partial sketch recognition. Our second aim is improving complete sketch recognition using information about sketching progression. We obtained a ConvNet that outperforms state-of-the-art results in the TU-Berlin sketch benchmark. We reached an accuracy of 77.69%.
{"title":"DeepSketch 2: Deep convolutional neural networks for partial sketch recognition","authors":"S. Dupont, Omar Seddati, S. Mahmoudi","doi":"10.1109/CBMI.2016.7500261","DOIUrl":"https://doi.org/10.1109/CBMI.2016.7500261","url":null,"abstract":"Freehand sketches are a simple and powerful tool for communication. They are easily recognized across cultures and suitable for various applications. In this paper, we propose a new approach for partial sketch recognition. This could be used to design applications using real-time sketch recognition. We use deep convolutional neural networks (ConvNets), state-of-the-art in the field of sketch recognition. To the best of our knowledge, it is the first ConvNet for partial sketch classification. Our first aim is to build a ConvNet capable of recognizing partial sketches without compromising the accuracy reached for complete sketch recognition. Therefore, we evaluate different approaches and propose an efficient way for partial sketch recognition. Our second aim is improving complete sketch recognition using information about sketching progression. We obtained a ConvNet that outperforms state-of-the-art results in the TU-Berlin sketch benchmark. We reached an accuracy of 77.69%.","PeriodicalId":356608,"journal":{"name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132735277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-15DOI: 10.1109/CBMI.2016.7500248
M. Lux, N. Anagnostopoulos, C. Iakovidou
Image retrieval deals with the problem of finding relevant images to satisfy a specific user need. Many methods for content based image retrieval have been developed over the years, ranging from global to local features and, lately, to convolutional neural networks. Each of the approaches has its own benefits and drawbacks, but they also have similarities. In this paper we investigate how a method initially developed for local features, pyramid matching, then employed on texture features, spatial pyramids, can enhance general global features. We apply a spatial pyramid based approach to add spatial information to well known and established global descriptors, and present the results of an extensive evaluation that shows that this combination is able to outperform the original versions of the global features.
{"title":"Spatial pyramids for boosting global features in content based image retrieval","authors":"M. Lux, N. Anagnostopoulos, C. Iakovidou","doi":"10.1109/CBMI.2016.7500248","DOIUrl":"https://doi.org/10.1109/CBMI.2016.7500248","url":null,"abstract":"Image retrieval deals with the problem of finding relevant images to satisfy a specific user need. Many methods for content based image retrieval have been developed over the years, ranging from global to local features and, lately, to convolutional neural networks. Each of the approaches has its own benefits and drawbacks, but they also have similarities. In this paper we investigate how a method initially developed for local features, pyramid matching, then employed on texture features, spatial pyramids, can enhance general global features. We apply a spatial pyramid based approach to add spatial information to well known and established global descriptors, and present the results of an extensive evaluation that shows that this combination is able to outperform the original versions of the global features.","PeriodicalId":356608,"journal":{"name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126958832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-15DOI: 10.1109/CBMI.2016.7500257
M. Riegler, Konstantin Pogorelov, P. Halvorsen, T. Lange, C. Griwodz, P. Schmidt, S. Eskeland, Dag Johansen
Analysis of medical videos for detection of abnormalities like lesions and diseases requires both high precision and recall but also real-time processing for live feedback during standard colonoscopies and scalability for massive population based screening, which can be done using a capsular video endoscope. Existing related work in this field does not provide the necessary combination of detection accuracy and performance. In this paper, a multimedia system is presented where the aim is to tackle automatic analysis of videos from the human gastrointestinal (GI) tract. The system includes the whole pipeline from data collection, processing and analysis, to visualization. The system combines filters using machine learning, image recognition and extraction of global and local image features, and it is built in a modular way, so that it can easily be extended. At the same time, it is developed for efficient processing in order to provide real-time feedback to the doctor. Initial experiments show that our system has detection and localisation accuracy at least as good as existing systems, but it stands out in terms of real-time performance and low resource consumption for scalability.
{"title":"EIR — Efficient computer aided diagnosis framework for gastrointestinal endoscopies","authors":"M. Riegler, Konstantin Pogorelov, P. Halvorsen, T. Lange, C. Griwodz, P. Schmidt, S. Eskeland, Dag Johansen","doi":"10.1109/CBMI.2016.7500257","DOIUrl":"https://doi.org/10.1109/CBMI.2016.7500257","url":null,"abstract":"Analysis of medical videos for detection of abnormalities like lesions and diseases requires both high precision and recall but also real-time processing for live feedback during standard colonoscopies and scalability for massive population based screening, which can be done using a capsular video endoscope. Existing related work in this field does not provide the necessary combination of detection accuracy and performance. In this paper, a multimedia system is presented where the aim is to tackle automatic analysis of videos from the human gastrointestinal (GI) tract. The system includes the whole pipeline from data collection, processing and analysis, to visualization. The system combines filters using machine learning, image recognition and extraction of global and local image features, and it is built in a modular way, so that it can easily be extended. At the same time, it is developed for efficient processing in order to provide real-time feedback to the doctor. Initial experiments show that our system has detection and localisation accuracy at least as good as existing systems, but it stands out in terms of real-time performance and low resource consumption for scalability.","PeriodicalId":356608,"journal":{"name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","volume":"362 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115953093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-15DOI: 10.1109/CBMI.2016.7500236
Soumyadeb Chowdhury, M. Ferdous, J. Jose
With continuous advances in the pervasive sensing and lifelogging technologies for the quantified self, users now can record their daily life activities automatically and seamlessly. In the existing lifelogging research, visualization techniques for presenting the lifelogs and evaluating the effectiveness of such techniques from a lifelogger's perspective has not been adequately studied. In this paper, we investigate the effectiveness of four distinct visualization techniques for exploring the lifelogs, which were collected by 22 lifeloggers who volunteered to use a wearable camera and a GPS device simultaneously, for a period of 3 days. Based on a user study with these 22 lifeloggers, which required them to browse through their personal lifelogs, we seek to identify the most effective visualization technique. Our results suggest various ways to augment and improve the visualization of personal lifelogs to enrich the quality of user experience and making lifelogging tools more engaging. We also propose a new visualization feature-drill-down approach with details-on-demand, to make the lifelogging visualization process more meaningful and informative to the lifeloggers.
{"title":"A user-study examining visualization of lifelogs","authors":"Soumyadeb Chowdhury, M. Ferdous, J. Jose","doi":"10.1109/CBMI.2016.7500236","DOIUrl":"https://doi.org/10.1109/CBMI.2016.7500236","url":null,"abstract":"With continuous advances in the pervasive sensing and lifelogging technologies for the quantified self, users now can record their daily life activities automatically and seamlessly. In the existing lifelogging research, visualization techniques for presenting the lifelogs and evaluating the effectiveness of such techniques from a lifelogger's perspective has not been adequately studied. In this paper, we investigate the effectiveness of four distinct visualization techniques for exploring the lifelogs, which were collected by 22 lifeloggers who volunteered to use a wearable camera and a GPS device simultaneously, for a period of 3 days. Based on a user study with these 22 lifeloggers, which required them to browse through their personal lifelogs, we seek to identify the most effective visualization technique. Our results suggest various ways to augment and improve the visualization of personal lifelogs to enrich the quality of user experience and making lifelogging tools more engaging. We also propose a new visualization feature-drill-down approach with details-on-demand, to make the lifelogging visualization process more meaningful and informative to the lifeloggers.","PeriodicalId":356608,"journal":{"name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116838707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-15DOI: 10.1109/CBMI.2016.7500259
Miroslav Macík, Jakub Lokoč, Premysl Cech, T. Skopal
Recent studies show that 3D visualization and browsing interfaces in content-based exploration systems of unstructured data represent a promising alternative to classical 2D grids. In this paper, we study 3D visualization techniques based on the particle physics model with focus on efficient evaluation of presentation layouts. We show that the particle physics model is a versatile approach suitable for exploration systems, enabling generation of various types of layouts. We also show that the model is able to organize thousands of objects given only limited time which is crucial for content-based exploration.
{"title":"Particle physics model for content-based 3D exploration","authors":"Miroslav Macík, Jakub Lokoč, Premysl Cech, T. Skopal","doi":"10.1109/CBMI.2016.7500259","DOIUrl":"https://doi.org/10.1109/CBMI.2016.7500259","url":null,"abstract":"Recent studies show that 3D visualization and browsing interfaces in content-based exploration systems of unstructured data represent a promising alternative to classical 2D grids. In this paper, we study 3D visualization techniques based on the particle physics model with focus on efficient evaluation of presentation layouts. We show that the particle physics model is a versatile approach suitable for exploration systems, enabling generation of various types of layouts. We also show that the model is able to organize thousands of objects given only limited time which is crucial for content-based exploration.","PeriodicalId":356608,"journal":{"name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116617040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-15DOI: 10.1109/CBMI.2016.7500242
Sheetal Rajgure, Vincent Oria, Krithika Raghavan, Hardik Dasadia, Sai Shashank Devannagari, Reza Curtmola, J. Geller, P. Gouton, Edina Renfro-Michel, Soon Ae Chun
In this system prototype demonstration we present, Ultimate Course Search (UCS), a learning tool developed to provide students ways to efficiently search electronic educational materials. UCS integrates slides, lecture videos and textbooks into a single platform. The keywords extracted from the textbooks and the slides are the basis of the indexing scheme. For the videos, UCS relies on slide transitions and metadata to establish the correspondence between slides and video segments. The video segmentation is based on the slides being presented using the meta-data provided by the video recording software and image processing techniques.
{"title":"UCS: Ultimate course search","authors":"Sheetal Rajgure, Vincent Oria, Krithika Raghavan, Hardik Dasadia, Sai Shashank Devannagari, Reza Curtmola, J. Geller, P. Gouton, Edina Renfro-Michel, Soon Ae Chun","doi":"10.1109/CBMI.2016.7500242","DOIUrl":"https://doi.org/10.1109/CBMI.2016.7500242","url":null,"abstract":"In this system prototype demonstration we present, Ultimate Course Search (UCS), a learning tool developed to provide students ways to efficiently search electronic educational materials. UCS integrates slides, lecture videos and textbooks into a single platform. The keywords extracted from the textbooks and the slides are the basis of the indexing scheme. For the videos, UCS relies on slide transitions and metadata to establish the correspondence between slides and video segments. The video segmentation is based on the slides being presented using the meta-data provided by the video recording software and image processing techniques.","PeriodicalId":356608,"journal":{"name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123330472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-06-15DOI: 10.1109/CBMI.2016.7500270
N. Zikos, A. Delopoulos, Dafni Maria Vasilikari
In this paper we present a framework to transform textual queries into visual ones. The proposed method uses standard image retrieval techniques with textual queries and the Fast Geometric Consistency Test (FGCT) method. For every textual query a set of images is retrieved and for every image a set of descriptors is extracted. Extracted features are combined with respect to their similarity in their descriptors' space and afterwards with respect to their geometric consistency on the image plane. All pairs of images are tested for consistent geometric structures using the FGCT method. This procedure extracts the subset of images that have a persistent geometric formation in the descriptors' space. Descriptors that compose the persistent formation are extracted and used as the input in a visual query; those features constitute the visual context of the visual query. Afterwards we perform again the FGCT method, but this time using the set of extracted features of the persistent formation into the cloud of images that consists of images with out a priori textual knowledge. It is noteworthy that the proposed method is scale, rotation and translation invariant. Experimental results on the Microsoft's Clickture dataset which consist of 1 million images are presented to support these statements.
{"title":"From textual queries to visual queries","authors":"N. Zikos, A. Delopoulos, Dafni Maria Vasilikari","doi":"10.1109/CBMI.2016.7500270","DOIUrl":"https://doi.org/10.1109/CBMI.2016.7500270","url":null,"abstract":"In this paper we present a framework to transform textual queries into visual ones. The proposed method uses standard image retrieval techniques with textual queries and the Fast Geometric Consistency Test (FGCT) method. For every textual query a set of images is retrieved and for every image a set of descriptors is extracted. Extracted features are combined with respect to their similarity in their descriptors' space and afterwards with respect to their geometric consistency on the image plane. All pairs of images are tested for consistent geometric structures using the FGCT method. This procedure extracts the subset of images that have a persistent geometric formation in the descriptors' space. Descriptors that compose the persistent formation are extracted and used as the input in a visual query; those features constitute the visual context of the visual query. Afterwards we perform again the FGCT method, but this time using the set of extracted features of the persistent formation into the cloud of images that consists of images with out a priori textual knowledge. It is noteworthy that the proposed method is scale, rotation and translation invariant. Experimental results on the Microsoft's Clickture dataset which consist of 1 million images are presented to support these statements.","PeriodicalId":356608,"journal":{"name":"2016 14th International Workshop on Content-Based Multimedia Indexing (CBMI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125537744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：