The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Dimension reduction methods have been commonly used for content-based multimedia indexing and retrieval. In this paper, we investigate the use of a mapping by adaptive threshold (MAT) method for dimension reduction of feature data. The proposed MAT method is implemented and compared to two other well-known dimension reduction methods, namely Principal Component Analysis and Multidimensional Scaling...
Conventional statistical language models such as N-grams are inadequate to model long distance dependencies in natural language. In this paper we propose a novel statistical language model to capture topic related long range dependencies. Humans have the inherent ability to identify long range dependencies in natural language. Given a set of related words humans can easily identify the context in...
In this paper we present, for the first time, the development of a new OCR system for the off-line optical recognition of the characters of the Orthodox Hellenic Byzantine Music Notation, that has been established for use since 1814. We describe the structure of the new system, and propose algorithms for the recognition of the 71 distinct character classes, based on structural and statistical features...
The data derived from the social tagging system, known as folksonomy, is a potentially useful source for understanding users' intentions. This study seeks to uncover some of the unexplored areas of folksonomy and examine the plausibility of new ideas for the improvement of personalized search. In particular, we challenge several state-of-the-art algorithms by exploiting folksonomy network structures...
In this paper, we introduce a multi-modal graphical model to address the problems of semantic segmentation using 2D-3D data exhibiting extensive many-to-one correspondences. Existing methods often impose a hard correspondence between the 2D and 3D data, where the 2D and 3D corresponding regions are forced to receive identical labels. This results in performance degradation due to misalignments, 3D-2D...
Key frame based video summarization, which enables an user to access any video in a friendly and meaningful way, has emerged as an important area of research for the multimedia community. Various pattern clustering techniques are applied for the extraction of key frames from a video to form a storyboard. In this work, we improve existing Delaunay graph based video summarization framework with i) semantic...
We propose clause lets, sets of concurrent actions and their temporal relationships, and explore their application to video event analysis. We train clause lets in two stages. We initially train first level clause let detectors that find a limited set of actions in particular qualitative temporal configurations based on Allen's interval relations. In the second stage, we apply the first level detectors...
In course of a breaking news event, such as natural calamity, political uproar etc., a massive crowd sourced data is generated over social media which makes social media platforms an important source of information in such scenarios. The value of the information being propagated via social media is being increasingly realised by the news organisations and the journalists. Better tools and methodologies...
Vast amounts of data available online and in other digital repositories make it challenging for users to find the right sources of information. In this paper, we present a novel approach for recommending documents to users by analyzing user browsing behavior, and demonstrate the effectiveness of our methods using an original data set. We conducted a study to collect a novel data set of document browsing...
An example-based dialog model often require a lot of data collections to achieve a good performance. However, when it comes on handling an out of vocabulary (OOV) database queries, this approach resulting in weakness and inadequate handling of interactions between words in the sentence. In this work, we try to overcome this problem by utilizing recursive neural network paraphrase identification to...
Retrieval engines provide results according to user request. Nevertheless, reaching satisfaction can not be guaranteed with simple retrieval step. Therefore, it is necessary to communicate this dissatisfaction to the system through relevance feedback techniques. Indeed, with the growing number of image collections and by applying approximate nearest neighbor (ANN) algorithms to resolve the curse of...
Due to the semantic gap between low-level visual features and high-level semantic content of images, the methods for image annotation based on low-level visual features, cannot well meet the requirement of knowledge discovery from web images. Therefore, the automatic acquisition for high-level semantic content of image has become a hot research topic. The traditional image annotation methods represent...
Despite the tremendous importance and availability of large video collections, support for video retrieval is still rather limited and is mostly tailored to very concrete use cases and collections. In image retrieval, for instance, standard keyword search on the basis of manual annotations and content-based image retrieval, based on the similarity to query image (s), are well established search paradigms,...
In this paper, we address the problem of automatic speech summarization on open-domain TED talks. The large vocabulary and diversity of topics from speaker-to-speaker presents significant difficulties. The challenges increase not only how to handle disfluencies and fillers, but also how to extract topic-related meaningful messages within the free talks. Here, we propose to incorporate semantic and...
This work reports the evaluation of a data-driven chatbot strategy, which is based on the vector space model IR framework. The evaluation is conducted by means of an empirical comparison between the proposed strategy and a baseline system that implements a similar, but naïve, strategy. The proposed chatbot strategy combines semantic evidence from both the current user input and the previous recent...
The word-to-vector (W2V) technique represents words as low-dimensional continuous vectors in such a way that semantic related words are close to each other. This produces a semantic space where a word or a word collection (e.g., a document) can be well represented, and thus lends itself to a multitude of applications including document classification. Our previous study demonstrated that representations...
Multi-document summary plays an increasingly important role with the exponential document growth on the web. Among many traditional multi-document summarization techniques, the latent semantic analysis (LSA) is a unique duo to its using latent semantic information instead of original feature, which results in a better performance. However, since those approaches based on LSA evaluate and select sentence...
Mining topics in Twitter is increasingly attracting more attention. However, the shortness and informality of tweets leads to extreme sparse vector representation with a large vocabulary, which makes the conventional topic models (e.g., Latent Dirichlet Allocation) often fail to achieve high quality underlying topics. Luckily, tweets always show up with rich user-generated hash tags as keywords. In...
In this work, we propose a research method to summarize popular information from massive tourism blog data. First, we crawl blog contents from website and segment each of them into a semantic word vector separately. Then, we select the geographical terms in each word vector into a corresponding geographical term vector and present a new method to explore the hot tourism locations and, especially,...
In this study, we have proposed a domain-independent unsupervised text segmentation method, which is applicable to even if unseen single document. This proposed method segments text documents by evaluating similarity between sentences. It is generally difficult to calculate semantic similarity between words that comprise sentences when the domain knowledge is insufficient. This problem influences...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.