This report describes the MILOS Multimedia Content Management System: a general purpose software component tailored to support design and effective implementation of any digital library application. MILOS supports the storage and content... more
This report describes the MILOS Multimedia Content Management System: a general purpose software component tailored to support design and effective implementation of any digital library application. MILOS supports the storage and content based retrieval of any multimedia documents whose descriptions are provided by using arbitrary metadata models represented in XML. MILOS is flexible in the management of documents containing different types of data and content descriptions; it is efficient and ...
The Artificial Intelligence for Media and Humanities laboratory (AIMH) has the mission to investigate and advance the state of the art in the Artificial Intelligence field, specifically addressing applications to digital media and digital... more
The Artificial Intelligence for Media and Humanities laboratory (AIMH) has the mission to investigate and advance the state of the art in the Artificial Intelligence field, specifically addressing applications to digital media and digital humanities, and taking also into account issues related to scalability. This report summarize the 2020 activities of the research group.
Research Interests:
Nowadays, the possibilities offered by state-of-the-art deep neural networks allow the creation of systems capable of recognizing and indexing visual content with very high accuracy. Performance of these systems relies on the availability... more
Nowadays, the possibilities offered by state-of-the-art deep neural networks allow the creation of systems capable of recognizing and indexing visual content with very high accuracy. Performance of these systems relies on the availability of high quality training sets, containing a large number of examples (e.g. million), in addition to the the machine learning tools themselves. For several applications, very good training sets can be obtained, for example, crawling (noisily) annotated images from the internet, or by analyzing user interaction (e.g.: on social networks). However, there are several applications for which high quality training sets are not easy to be obtained/created. Consider, as an example, a security scenario where one wants to automatically detect rarely occurring threatening events. In this respect, recently, researchers investigated the possibility of using a visual virtual environment, capable of artificially generating controllable and photo-realistic contents, to create training sets for applications with little available training images. We explored this idea to generate synthetic photo-realistic training sets to train classifiers to recognize the proper use of individual safety equipment (e.g.: worker protection helmets, high-visibility vests, ear protection devices) during risky human activities. Then, we performed domain adaptation to real images by using a very small image data set of real-world photographs. We show that training with the generated synthetic training set and using the domain adaptation step is an effective solution to address applications for which no training sets exist.
Research Interests:
Many approaches for approximate metric search rely on a permutation-based representation of the original data objects. The main advantage of transforming metric objects into permutations is that the latter can be efficiently indexed and... more
Many approaches for approximate metric search rely on a permutation-based representation of the original data objects. The main advantage of transforming metric objects into permutations is that the latter can be efficiently indexed and searched using data structures such as inverted-files and prefix trees. Typically, the permutation is obtained by ordering the identifiers of a set of pivots according to their distances to the object to be represented. In this paper, we present a novel approach to transform metric objects into permutations. It uses the object-pivot distances in combination with a metric transformation, called n-Simplex projection. The resulting permutation-based representation , named SPLX-Perm, is suitable only for the large class of metric space satisfying the n-point property. We tested the proposed approach on two benchmarks for similarity search. Our preliminary results are encouraging and open new perspectives for further investigations on the use of the n-Simplex projection for supporting permutation-based indexing.
Most of the Peer-to-Peer search techniques proposed in the recent years have focused on the single-key retrieval. However, similarity search in metric spaces represents an important paradigm for content-based retrieval in many... more
Most of the Peer-to-Peer search techniques proposed in the recent years have focused on the single-key retrieval. However, similarity search in metric spaces represents an important paradigm for content-based retrieval in many applications. In this paper we introduce an extension of the well-known Content-Addressable Network paradigm to support storage and retrieval of more generic metric space objects.
Similarity search in metric spaces represents an important paradigm for content-based retrieval of many applications. Existing centralized search structures can speed-up retrieval, but they do not scale up to large volume of data because... more
Similarity search in metric spaces represents an important paradigm for content-based retrieval of many applications. Existing centralized search structures can speed-up retrieval, but they do not scale up to large volume of data because the response time is linearly increasing with the size of the searched file. The proposed GHT* index is a scalable and distributed structure.
ABSTRACT Managing data and multimedia sources with a unique tool is a challenging issue. In this paper, the capabilities of the MOMIS integration system and the MILOS multimedia content management system are coupled, thus providing a... more
ABSTRACT Managing data and multimedia sources with a unique tool is a challenging issue. In this paper, the capabilities of the MOMIS integration system and the MILOS multimedia content management system are coupled, thus providing a methodology and a tool for building and querying a populated ontology representing data and multimedia sources.
ABSTRACT Wide access to large information collections is of great potential importance in many aspects-economic, environmental, health, cultural, social, etc.-of everyday life. Historical video documentaries hold by national audiovisual... more
ABSTRACT Wide access to large information collections is of great potential importance in many aspects-economic, environmental, health, cultural, social, etc.-of everyday life. Historical video documentaries hold by national audiovisual archives, constitute one of the most precious-from a historical and cultural viewpoint-and less accessible cultural information.
Similarity search in metric spaces represents an important paradigm for content-based retrieval in many applications. Existing centralized search structures can speed-up retrieval, but they do not scale up to large volume of data because... more
Similarity search in metric spaces represents an important paradigm for content-based retrieval in many applications. Existing centralized search structures can speed-up retrieval, but they do not scale up to large volume of data because the response time is linearly increasing with the size of the searched file. In this article, we study the problem of executing the nearest neighbor (s) queries in a distributed metric structure, which is based on the P2P communication paradigm and the generalized hyperplane partitioning.
Abstract In this paper we propose a new access structure, called GHT*, based on generalized hyperplane tree (GHT) and distributed dynamic hashing (DDH) techniques. GHT* is a distributed structure which allows to perform range search in a... more
Abstract In this paper we propose a new access structure, called GHT*, based on generalized hyperplane tree (GHT) and distributed dynamic hashing (DDH) techniques. GHT* is a distributed structure which allows to perform range search in a metric space according to a distance function d. The structure does not require a central directory and it is able to gracefully scale through splits of one bucket at a time.
Abstract This paper introduces queuing network models for the performance analysis of SPMD applications executed on general-purpose parallel architectures such as MIMD and clusters of workstations. The models are based on the pattern of... more
Abstract This paper introduces queuing network models for the performance analysis of SPMD applications executed on general-purpose parallel architectures such as MIMD and clusters of workstations. The models are based on the pattern of computation, communication, and I/O operations of typical parallel applications.
In this paper, we present a Distributed Incremental Nearest Neighbor algorithm (DINN) for finding closest objects in an incremental fashion over data distributed among computer nodes, each able to perform its local Incremental Nearest... more
In this paper, we present a Distributed Incremental Nearest Neighbor algorithm (DINN) for finding closest objects in an incremental fashion over data distributed among computer nodes, each able to perform its local Incremental Nearest Neighbor (local-INN) algorithm. We prove that our algorithm is optimum with respect to both the number of involved nodes and the number of local-INN invocations. An implementation of our DINN algorithm, on a real P2P system called MCAN, was used for conducting an extensive experimental evaluation on a real-life dataset.
Abstract A novel access structure for similarity search in metric data, called Similarity Hashing (sH), is proposed. Its multi-level hash structure of separable buckets on each level supports easy insertion and bounded search costs,... more
Abstract A novel access structure for similarity search in metric data, called Similarity Hashing (sH), is proposed. Its multi-level hash structure of separable buckets on each level supports easy insertion and bounded search costs, because at most one bucket needs to be accessed at each level for range queries up to a pre-defined value of search radius. At the same time, the number of distance computations is always significantly reduced by use of pre-computed distances obtained at insertion time.
Abstract. Similarity search for content-based retrieval (where content can be any combination of text, image, audio/video, etc.) has gained importance in recent years, also because of the advantage of ranking the retrieved results... more
Abstract. Similarity search for content-based retrieval (where content can be any combination of text, image, audio/video, etc.) has gained importance in recent years, also because of the advantage of ranking the retrieved results according to their proximity to a query. However, to use similarity search in real world applications, we need to tackle the problem of huge volumes of such mixed multimedia data (eg, coming from Web sites) and the problem of their distribution on multiple cooperating nodes.
Abstract. Text collections of data need not only search support for identical objects, but the approximate matching is even more important. A suitable metric to such task is the edit distance measure. However, its quadratic computational... more
Abstract. Text collections of data need not only search support for identical objects, but the approximate matching is even more important. A suitable metric to such task is the edit distance measure. However, its quadratic computational complexity prevents from applying naive storage organizations, such as the sequential search, and more sophisticated search structures must be used. We have investigated the properties of the D-index to approximate searching in text databases.
ABSTRACT In this paper, a technique for making more effective the similarity search process of images in a Multimedia Content Management System is proposed. The contentbased retrieval process integrates the search on different multimedia... more
ABSTRACT In this paper, a technique for making more effective the similarity search process of images in a Multimedia Content Management System is proposed. The contentbased retrieval process integrates the search on different multimedia components, linked in XML structures.
The Mean Value Analysis (MVA) algorithm is one of the most popular for evaluating the performance of separable (or product-form) queueing networks. Although its complexity is modest when jobs are indistinguishable, the introduction of... more
The Mean Value Analysis (MVA) algorithm is one of the most popular for evaluating the performance of separable (or product-form) queueing networks. Although its complexity is modest when jobs are indistinguishable, the introduction of different customer classes rapidly increases its computational cost. The problems of parallelising the algorithm while retaining its conceptual simplicity are examined.
Abstract In this paper we present the architecture of a Digital Library for enabling the reusing of audiovisual documents in an e-Learning context. The reuse of Learning Objects is based on automatically extracted descriptors carrying a... more
Abstract In this paper we present the architecture of a Digital Library for enabling the reusing of audiovisual documents in an e-Learning context. The reuse of Learning Objects is based on automatically extracted descriptors carrying a semantic meaning for the professional that uses these Learning Objects to prepare new interactive multimedia lectures.
ABSTRACT Wide access to large information collections is of great potential importance in many aspects-economic, environmental, health, cultural, social, etc.-of everyday life. Historical video documentaries hold by national audiovisual... more
ABSTRACT Wide access to large information collections is of great potential importance in many aspects-economic, environmental, health, cultural, social, etc.-of everyday life. Historical video documentaries hold by national audiovisual archives, constitute one of the most precious-from a historical and cultural viewpoint-and less accessible cultural information.
Abstract. Managing data and multimedia sources with a unique tool is a challenging issue. In this paper, the capabilities of the MOMIS integration system and the MILOS multimedia content management system are coupled, thus providing a... more
Abstract. Managing data and multimedia sources with a unique tool is a challenging issue. In this paper, the capabilities of the MOMIS integration system and the MILOS multimedia content management system are coupled, thus providing a methodology and a tool for building and querying an integrated virtual view of data and multimedia sources.
The objective of this paper is to demonstrate the reuse of digital content, as video documents or PowerPoint presentations, by exploiting existing technologies for automatic extraction of metadata (OCR, speech recognition, cut detection,... more
The objective of this paper is to demonstrate the reuse of digital content, as video documents or PowerPoint presentations, by exploiting existing technologies for automatic extraction of metadata (OCR, speech recognition, cut detection, MPEG-7 visual descriptors, etc.). The multimedia documents and the extracted metadata are then indexed and managed by the Multimedia Content Management System (MCMS) MILOS, specifically developed to support design and effective implementation of digital library applications.
This paper describes the MILOS Multimedia Content Management System: a general purpose software component tailored to support design and effective implementation of digital library applications. MILOS supports the storage and content... more
This paper describes the MILOS Multimedia Content Management System: a general purpose software component tailored to support design and effective implementation of digital library applications. MILOS supports the storage and content based retrieval of any multimedia documents whose descriptions are provided by using arbitrary metadata models represented in XML.
When information is delivered by news agencies, broadcast TV programs,1,2 and even surveillance systems, users receive a huge amount of data, but they might be interested in only a limited part of it. The process of selecting only... more
When information is delivered by news agencies, broadcast TV programs,1,2 and even surveillance systems, users receive a huge amount of data, but they might be interested in only a limited part of it. The process of selecting only significant information is called information filtering. However, the complexity of the filtering process is linear with the number of streams, filters, and features used to represent the video data. The entire process must occur in real time, so it's likely that most of a systems processing power will be dedicated to filtering.
Abstract. This paper describes the architecture of the MILOS Content Management System. MILOS supports the storage and content based retrieval of any XML document, as well as multimedia documents whose descriptions are provided by using... more
Abstract. This paper describes the architecture of the MILOS Content Management System. MILOS supports the storage and content based retrieval of any XML document, as well as multimedia documents whose descriptions are provided by using heterogenous metadata models represented in XML. MILOS is flexible in the management of documents containing different types of data and content descriptions; it is efficient and scalable in the storage and content based retrieval of these documents.
The impact of I/O in the parallel machine is becoming ever more important as the computational power of the processor and the throughput of the communication network are increasing. In this paper we show some scenarios of I/O in parallel... more
The impact of I/O in the parallel machine is becoming ever more important as the computational power of the processor and the throughput of the communication network are increasing. In this paper we show some scenarios of I/O in parallel machines, in particular we focus on a hybrid MIMD+ SIMD architecture which is under the study of an initiative which involves two major MPP vendors in Europe, Alenia Spazio and Meiko.
Abstract MILOS is a multimedia content management system specialised to support multimedia digital library applications. MILOS provides applications with functionalities for the storage of arbitrary multimedia documents and their content... more
Abstract MILOS is a multimedia content management system specialised to support multimedia digital library applications. MILOS provides applications with functionalities for the storage of arbitrary multimedia documents and their content based retrieval using arbitrary metadata models represented in XML. MILOS is flexible in the management of documents containing different types of data and content descriptions; it is efficient and scalable in the storage and content based retrieval of these documents.
Abstract. Managing data and multimedia sources with a unique tool is a challenging issue. In this paper, the capabilities of the MOMIS integration system and the MILOS multimedia content management system are coupled, thus providing a... more
Abstract. Managing data and multimedia sources with a unique tool is a challenging issue. In this paper, the capabilities of the MOMIS integration system and the MILOS multimedia content management system are coupled, thus providing a methodology and a tool for building and querying an integrated virtual view of data and multimedia sources.
In order to speedup retrieval in large collections of data, index structures partition the data into subsets so that query requests can be evaluated without examining the entire collection. As the complexity of modern data types grows,... more
In order to speedup retrieval in large collections of data, index structures partition the data into subsets so that query requests can be evaluated without examining the entire collection. As the complexity of modern data types grows, metric spaces have become a popular paradigm for similarity retrieval.
Abstract Clusters of workstations represent today a satisfactory alternative to MPPs and supercomputers in many areas of application. The rapidly reduction of the cost of high performance workstations/PCs makes this technology ever more... more
Abstract Clusters of workstations represent today a satisfactory alternative to MPPs and supercomputers in many areas of application. The rapidly reduction of the cost of high performance workstations/PCs makes this technology ever more available. Moreover, new concepts for the integration of individual workstations through Local Area Networks are emerging. High speed interconnection networks and optimized protocol system architectures are the most important objectives of current research in this field of study.
In recent years, the emerging diffusion of peer-to-peer networks is going beyond the single-domain paradigm like, for instance, the mono-thematic file sharing one (eg, Napster for music). Peers are more and more heterogeneous data sources... more
In recent years, the emerging diffusion of peer-to-peer networks is going beyond the single-domain paradigm like, for instance, the mono-thematic file sharing one (eg, Napster for music). Peers are more and more heterogeneous data sources which need to share data with commercial, educational, and/or collaboration purposes, just to mention a few.
This index covers all technical itemspapers, correspondence, reviews, etc. that appeared in this periodical during 2002, and items from previous years that were commmented upon or corrected in 2002. Departments and other items may be also... more
This index covers all technical itemspapers, correspondence, reviews, etc. that appeared in this periodical during 2002, and items from previous years that were commmented upon or corrected in 2002. Departments and other items may be also covered if they have been judged to have archival value.
Abstract Wide access to large information collections is of great potential importance in many aspectseconomic, environmental, health, cultural, social, etc.-of everyday life. Historical video documentaries hold by national audiovisual... more
Abstract Wide access to large information collections is of great potential importance in many aspectseconomic, environmental, health, cultural, social, etc.-of everyday life. Historical video documentaries hold by national audiovisual archives, constitute one of the most precious-from a historical and cultural viewpoint-and less accessible cultural information.
In this paper we present a scalable and distributed access structure for similarity search in metric spaces. The approach is based on the Content–addressable Network (CAN) paradigm, which provides a Distributed Hash Table (DHT)... more
In this paper we present a scalable and distributed access structure for similarity search in metric spaces. The approach is based on the Content–addressable Network (CAN) paradigm, which provides a Distributed Hash Table (DHT) abstraction over a Cartesian space. We have extended the CAN structure to support storage and retrieval of generic metric space objects.
Abstract. Similarity retrieval is an important paradigm for searching in environments where exact match has little meaning. Moreover, in order to enlarge the set of data types for which the similarity search can efficiently be performed,... more
Abstract. Similarity retrieval is an important paradigm for searching in environments where exact match has little meaning. Moreover, in order to enlarge the set of data types for which the similarity search can efficiently be performed, the notion of mathematical metric space provides a useful abstraction for similarity. In this paper we consider the problem of organizing and searching large data-sets from arbitrary metric spaces, and a novel access structure for similarity search in metric data, called D-Index, is discussed.
Abstract: Enabling integrated robots and Wireless Sensor Network (WSN) applications is an important and extended challenge for both robotics and WSN research & development and a key enabler for a range of advanced hybrid applications,... more
Abstract: Enabling integrated robots and Wireless Sensor Network (WSN) applications is an important and extended challenge for both robotics and WSN research & development and a key enabler for a range of advanced hybrid applications, such as environmental monitoring and Ambient Assisted Living (AAL).
Abstract In this paper a technique for evaluating the effectiveness of MPEG-7 image features on specific image data sets is proposed. It is based on well defined statistical characteristics. The aim is to improve the effectiveness of the... more
Abstract In this paper a technique for evaluating the effectiveness of MPEG-7 image features on specific image data sets is proposed. It is based on well defined statistical characteristics. The aim is to improve the effectiveness of the image retrieval process, based on the similarity computed on these features. This technique is validated with extensive experiments with real users.
Abstract While triggers have become a classical ingredient of relational database systems, research in active databases is aiming at extending the functionality and expressive power of active rules beyond the scope of relational triggers.... more
Abstract While triggers have become a classical ingredient of relational database systems, research in active databases is aiming at extending the functionality and expressive power of active rules beyond the scope of relational triggers. One of the most important current trend concerns the support of detached active rules, ie, of rules which are executed as separate transactions, running outside of the scope of the transaction which generates the triggering event.
Abstract. Given the lack of standard building component, in several cases digital library applications are built from scratch using ad-hoc approaches to implement all required components. On the other hand, our claim is that the... more
Abstract. Given the lack of standard building component, in several cases digital library applications are built from scratch using ad-hoc approaches to implement all required components. On the other hand, our claim is that the development of ad-hoc software modules for each new digital library is not convenient. It is necessary to define and design standard software components in order to support the design and effective implementation of Digital Library Applications.
Abstract Searching for non-text data (eg, images) is mostly done by means of metadata annotations or by extracting the text close to the data. However, supporting real content-based audio-visual search, based on similarity search on... more
Abstract Searching for non-text data (eg, images) is mostly done by means of metadata annotations or by extracting the text close to the data. However, supporting real content-based audio-visual search, based on similarity search on features, is significantly more expensive than searching for text. Moreover, the search exhibits linear scalability with respect to the data set size.
Abstract: The most common use of wireless sensor networks (WSNs) is to collect environmental data from a specific area, and to channel it to a central processing node for on-line or off-line analysis. The WSN technology, however, can be... more
Abstract: The most common use of wireless sensor networks (WSNs) is to collect environmental data from a specific area, and to channel it to a central processing node for on-line or off-line analysis. The WSN technology, however, can be used for much more ambitious goals.
Abstract. In this paper, we elaborate on a scalable and distributed similarity search structure, that is the problem, which has previously been studied only for single computers. Our structure is scalable in that it distributes the data... more
Abstract. In this paper, we elaborate on a scalable and distributed similarity search structure, that is the problem, which has previously been studied only for single computers. Our structure is scalable in that it distributes the data over more and more independent peer computers. It has no hot spot-all peers use as precise addressing scheme as possible and they all incrementally learn from misaddressing. Updates are performed locally and a node splitting never requires sending multiple messages to many peers.
In this paper we present our main current research activity in the Italian co-funded FIRB Project NeP4B (Networked Peers for Business). In particular, we provide an overview of our P2P query routing approach which combines semantics and... more
In this paper we present our main current research activity in the Italian co-funded FIRB Project NeP4B (Networked Peers for Business). In particular, we provide an overview of our P2P query routing approach which combines semantics and multimedia aspects in order to make query processing effective and efficient.
Abstract Although HPF allows programmers to express data-parallel computations in a portable, high-level way, it is widely accepted that many important parallel applications cannot be efficiently implemented following a pure data-parallel... more
Abstract Although HPF allows programmers to express data-parallel computations in a portable, high-level way, it is widely accepted that many important parallel applications cannot be efficiently implemented following a pure data-parallel paradigm. For these applications, rather than having a single data-parallel program, it is more profitable to subdivide the whole computation into several data-parallel pieces, where the various pieces run concurrently and co-operate, thus exploiting task parallelism.
Abstract In this paper we present a prototype system to enrich audiovisual contents with annotations, which exploits existing technologies for automatic extraction of metadata (such as OCR, speech recognition, cut detection, visual... more
Abstract In this paper we present a prototype system to enrich audiovisual contents with annotations, which exploits existing technologies for automatic extraction of metadata (such as OCR, speech recognition, cut detection, visual descriptors, etc.).
Abstract In this paper we present the MILOS 1 Multimedia Content Management System. MILOS supports the storage and content based retrieval of any multimedia documents whose descriptions are provided by using arbitrary metadata models... more
Abstract In this paper we present the MILOS 1 Multimedia Content Management System. MILOS supports the storage and content based retrieval of any multimedia documents whose descriptions are provided by using arbitrary metadata models represented in XML. It provides developers of digital library applications with functionalities for dealing with heterogeneous digital documents, heterogeneous metadata, and metadata schema mapping.
Abstract. Similarity search in metric spaces represents an important paradigm for content-based retrieval of many applications. Existing centralized search structures can speed-up retrieval, but they do not scale up to large volume of... more
Abstract. Similarity search in metric spaces represents an important paradigm for content-based retrieval of many applications. Existing centralized search structures can speed-up retrieval, but they do not scale up to large volume of data because the response time is linearly increasing with the size of the searched file. The proposed GHT* index is a scalable and distributed structure.
Abstract This report describes the MILOS Multimedia Content Management System: a general purpose software component tailored to support design and effective implementation of any digital library application. MILOS supports the storage and... more
Abstract This report describes the MILOS Multimedia Content Management System: a general purpose software component tailored to support design and effective implementation of any digital library application. MILOS supports the storage and content based retrieval of any multimedia documents whose descriptions are provided by using arbitrary metadata models represented in XML.
Video can be considered today as a primarily mean of communication, due to its richness in informative content and to its appeal. Indeed, the combination of audio and video is an extremely important communication channel: it is considered... more
Video can be considered today as a primarily mean of communication, due to its richness in informative content and to its appeal. Indeed, the combination of audio and video is an extremely important communication channel: it is considered that approximately 50% of what is seen and heard simultaneously is retained.
Abstract. Robotic ecologies are networks of heterogeneous robotic devices pervasively embedded in everyday environments, where they cooperate to perform complex tasks. While their potential makes them increasingly popular, one fundamental... more
Abstract. Robotic ecologies are networks of heterogeneous robotic devices pervasively embedded in everyday environments, where they cooperate to perform complex tasks. While their potential makes them increasingly popular, one fundamental problem is how to make them self-adaptive, so as to reduce the amount of preparation, pre-programming and human supervision that they require in real world applications.
Abstract Text collections of data need not only search support for identical objects, but the approximate matching is even more important. A suitable metric to such a task is the edit distance measure. However, the quadratic computational... more
Abstract Text collections of data need not only search support for identical objects, but the approximate matching is even more important. A suitable metric to such a task is the edit distance measure. However, the quadratic computational complexity of edit distance prevents from applying naive storage organizations, such as the sequential search, and more sophisticated search structures must be applied. We have investigated the properties of the D-index to approximate searching and matching in text databases.