Visual Information Retrieval

A special issue of Future Internet (ISSN 1999-5903).

Deadline for manuscript submissions: closed (15 November 2011) | Viewed by 5469

Special Issue Editor


E-Mail
Guest Editor
Dipartimento Sistemi e Informatica, Università di Firenze, Via S. Marta, 3, 50139 Firenze, Italy
Interests: content based retrieval of images and video; visual concepts extractions in images and videos; indexing structures for content based retrieval; retrieval of 3D models; segmentation of 3D models; 3D face recognition

Special Issue Information

Dear Colleagues,

Thanks to the advances in compression and storage technologies, massive amounts of image and video material are produced daily in a broad range of different application contexts such as biomedicine, social networks, cultural heritage and digital libraries. Once it has been stored, the potential of this material largely depends on the availability of models and tools for making it accessible effectively and efficiently to different users matching different profiles. The development of paradigms and theories to address this challenging issue has been the goal of visual information retrieval research that now builds upon consolidated models defined in the last decade to face new challenges in the design of usable system interfaces and interaction paradigms for querying, browsing and summarization, the definition of models for learning visual concepts from large and unstructured image and video collections, the definition of indexing structures to enable efficient access to local and distributed repositories.

The purpose of this Special Issue is to bring together a number of research papers for providing a representative view of the frontier of this research field. Original, high quality papers are solicited that address challenging issues in the field of visual information retrieval, including

  • Large-scale and web-scale indexing and retrieval of visual information
  • Integration of content, meta data and social network
  • Scalable and distributed search
  • Novel interfaces and interaction paradigms for search and retrieval of visual information
  • Visual content descriptors and similarity metrics
  • Indexing algorithms
  • Machine learning for visual concept learning and detection
  • Large-scale summarization and visualization
  • Performance evaluation
  • Navigation and browsing on the Web
  • Visual information retrieval systems and applications
Prof. Dr. Pietro Pala
Guest Editor

Keywords

Categories and Subject Descriptors:

  • H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval
  • I.2.6 [Artificial Intelligence]: Learning
  • I.4.9 [Image Processing and Computer Vision]: Applications

Additional Keywords:

  • visual information retrieval
  • image search
  • video retrieval
  • image databases
  • image and video indexing
  • human-computer interaction
  • visual concepts learning in social media

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

1164 KiB  
Article
A Flexible Object-of-Interest Annotation Framework for Online Video Portals
by Robert Sorschag
Future Internet 2012, 4(1), 179-215; https://doi.org/10.3390/fi4010179 - 22 Feb 2012
Viewed by 5134
Abstract
In this work, we address the use of object recognition techniques to annotate what is shown where in online video collections. These annotations are suitable to retrieve specific video scenes for object related text queries which is not possible with the manually generated [...] Read more.
In this work, we address the use of object recognition techniques to annotate what is shown where in online video collections. These annotations are suitable to retrieve specific video scenes for object related text queries which is not possible with the manually generated metadata that is used by current portals. We are not the first to present object annotations that are generated with content-based analysis methods. However, the proposed framework possesses some outstanding features that offer good prospects for its application in real video portals. Firstly, it can be easily used as background module in any video environment. Secondly, it is not based on a fixed analysis chain but on an extensive recognition infrastructure that can be used with all kinds of visual features, matching and machine learning techniques. New recognition approaches can be integrated into this infrastructure with low development costs and a configuration of the used recognition approaches can be performed even on a running system. Thus, this framework might also benefit from future advances in computer vision. Thirdly, we present an automatic selection approach to support the use of different recognition strategies for different objects. Last but not least, visual analysis can be performed efficiently on distributed, multi-processor environments and a database schema is presented to store the resulting video annotations as well as the off-line generated low-level features in a compact form. We achieve promising results in an annotation case study and the instance search task of the TRECVID 2011 challenge. Full article
(This article belongs to the Special Issue Visual Information Retrieval)
Show Figures

Figure 1

Back to TopTop