Improving Event detection in Cricket Videos Using Audio Feature Analysis

This paper discusses an event detection approach based on audio, which proves to be effective when applied to the audio component of cricket television broadcaster’s video. In this approach, both crowed noise levels which is in the background and commentator voice which is in focus are considered correlated to key events in the time frame. Classifiers related to Hidden Markov Model (or HMM) are utilized as it is an efficient tool for modeling processes varying with time and broadly used in the area of speech recognition. This experiment done using cricket television broadcaster videos, was successful thus this method can be used for automatic indexing of audio (or video containing audio) for quick searching or segmentation.

Manipuri Morphological Analysis

Morphological analysis is the basic foundation in Natural Language Processing applications including Syntax Parsing, Machine Translation (MT), Information Retrieval (IR) and Automatic Indexing. Morphological Analysis can provide valuable information for computer based linguistics task such as Lemmatization and studies of internal structure of the words or the feature values of the word. Computational Morphology is the application of morphological rules in the field of Computational Linguistics, and it is the emerging area in AI, which studies the structure of words, which are formed by combining smaller units of linguistics information, called morphemes: the building blocks of words. It provides about Semantic and Syntactic role in a sentence. It can analyze the Manipuri word forms and produces grammatical information, which is associated with the lexicon. Morphological Analyzer for Manipuri language has been tested on 4500 Manipuri lexicons in Shakti Standard Format (SSF) using Meitei Mayek Unicode as source; thereby an accuracy of 84% has been obtained on a manual check.

Special Issue on Advances in Deep Learning

Nowadays, deep learning is the fastest growing research field in machine learning and has a tremendous impact on a plethora of daily life applications, ranging from security and surveillance to autonomous driving, automatic indexing and retrieval of media content, text analysis, speech recognition, automatic translation, and many others [...]

Multimodal person discovery using label propagation over speaking faces graphs

The indexing of large datasets is a task of great importance, since it directly impacts on the quality of information that can be retrieved from these sets. Unfortunately, some datasets are growing in size so fast that manually indexing becomes unfeasible. Automatic indexing techniques can be applied to overcome this issue, and in this study, a unsupervised technique for multimodal person discovery is proposed, which consists in detecting persons that are appearing and speaking simultaneously on a video and associating names to them. To achieve that, the data is modeled as a graph of speaking-faces, and names are extracted via OCR and propagated through the graph based on audiovisual relations between speaking faces. To propagate labels, two graph based methods are proposed, one based on random walks and the other based on a hierarchical approach. In order to assess the proposed approach, we use two graph clustering baselines, and different modality fusion approaches. On the MediaEval MPD 2017 dataset, the proposed label propagation methods outperform all literature methods except one, which uses a different approach on the pre-processing step. Even though the Kappa coefficient indicates that the random walk and the hierarchical label propagation produce highly equivalent results, the hierarchical propagation is more than 6 times faster than the random walk under same configurations.

Representing Aboutness: Automatically Indexing 19th- Century Encyclopedia Britannica Entries

Representing aboutness is a challenge for humanities documents, given the linguistic indeterminacy of the text. The challenge is even greater when applying automatic indexing to historical documents for a multidisciplinary collection, such as encyclopedias. The research presented in this paper explores this challenge with an automatic indexing comparative study examining topic relevance. The setting is the NEH-funded 19th-Century Knowledge Project, where researchers in the Digital Scholarship Center, Temple University, and the Metadata Research Center, Drexel University, are investigating the best way to index entries across four historical editions of the Encyclopedia Britannica (3rd, 7th, 9th, and 11th editions). Individual encyclopedia entry entries were processed using the Helping Interdisciplinary Vocabulary Engineering (HIVE) system, a linked-data, automatic indexing terminology application that uses controlled vocabularies. Comparative topic relevance evaluation was performed for three separate keyword extraction algorithms: RAKE, Maui, and Kea++. Results show that RAKE performed the best, with an average of 67% precision for RAKE, and 28% precision for both Maui and Kea++. Additionally, the highest-ranked HIVE results with both RAKE and Kea++ demonstrated relevance across all sample entries, while Maui’s highest-ranked results returned zero relevant terms. This paper reports on background information, research objectives and methods, results, and future research prospects for further optimization of RAKE’s algorithm parameters to accommodate for encyclopedia entries of different lengths, and evaluating the indexing impact of correcting the historical Long S.

XGANDALF – extended gradient descent algorithm for lattice finding

Serial crystallography records still diffraction patterns from single, randomly oriented crystals, then merges data from hundreds or thousands of them to form a complete data set. To process the data, the diffraction patterns must first be indexed, equivalent to determining the orientation of each crystal. A novel automatic indexing algorithm is presented, which in tests usually gives significantly higher indexing rates than alternative programs currently available for this task. The algorithm does not require prior knowledge of the lattice parameters but can make use of that information if provided, and also allows indexing of diffraction patterns generated by several crystals in the beam. Cases with a small number of Bragg spots per pattern appear to particularly benefit from the new approach. The algorithm has been implemented and optimized for fast execution, making it suitable for real-time feedback during serial crystallography experiments. It is implemented in an open-source C++ library and distributed under the LGPLv3 licence. An interface to it has been added to the CrystFEL software suite.

A Semantic Distances-Based Approach for a Deeply Indexing of Learning Objects

Educational search engines are important for users to find learning objects (LO). However, these engines have not reached maturity in terms of searching, they suffer from several worries like the deep extraction of notions which diminishes their performance. The purpose of this paper is to propose a new approach that allows depth extraction of LO’s notions to increase the relevance level of educational search engines. The proposed approach focuses on semi-automatic indexing of textual LO and more precisely the deeper relations of sentences that flesh out explanations. It based on linguistic structures and semantic distances between specific and generic notions according to OntOAlgO ontology. The notions obtained will be improved by learning object metadata (LOM) and will be represented semantically in final index. The tests performed on algorithmic LO, proving the usefulness of our approach to educational search engines. It increases the degree of precision and recall of notions extracted from LO.