Automatic deduction of semantic labels for audiovisual data requires awareness of context, which in turn requires processing sequences of audiovisual scenes or events. The representation of such sequences is important for semantic analysis tasks. Whereas, conventionally, sequences of specific short-duration event labels, often hand-annotated for learning detectors or classifiers, have been used...

Nowadays more and more audiovisual information is available, from many sources around the world. Computer and data technologies are continuing to develop at a rapid rate, providing higher performance while reducing the cost and size of the system components. Users require assistance to avoid being overwhelmed by this amount of information and the information providers require assistance in auth...

  Having in mind the high level of challenge in writing as a foreign language, this research provided Iranian EFL learners with audiovisual feedbacks as an alternative of common written feedback and focused on its’ meaningfulness in order to provide an incentive medium for the participants and increase their moti-vation. One hundred young adult female learners in addition to six English languag...

First we analyse audiovisual documents and the temporalities they are concerned with. Then we define hypervideos as extended audiovisual documents that offer hypertextual capabilities in the framework of audiovisual information systems. We analyse some features of hypervideos regarding the temporalities we defined, and show that hypervideo are complex objects. So we finally present the beginnin...

The German National Library of Science and Technology (TIB) is developing a web-based platform for audiovisual media. The forthcoming audiovisual portal optimises access to scientific videos such as computer animations, lecture and conference recordings. TIB's AVPortal offers new methods for searching within videos enabled by automated video analysis with scene, speech, text and image recogniti...

Seeing the talker’s articulatory mouth movements can influence the auditory speech percept both in speech identification and detection tasks. Here we show that these audiovisual integration effects also occur for sine wave speech (SWS), which is an impoverished speech signal that naïve observers often fail to perceive as speech. While audiovisual integration in the identification task only occu...

With the aim of audiovisual database consulting, the prospect of an interactive visual organization tool should be enviable. We consider a document as a visual entity in a computer screen. Thanks to an appropriate simplified GUI, a user can organize a few documents. Its notion of audiovisual similarity is relative to the Euclidean distance between entities: the more they are close, the more the...

This paper describes the COALA (Content-Oriented Audiovisual Library Access) project, which aims to offer a framework for the retrieval of audiovisual TV news documents. COALA’s principal design features are based on the analysis of a classical archive system: TSR (Television Suisse Romande) archive. It provides a retrieval interface allowing simple/advanced search capabilities combined with hi...

The open, independent, and international standards organization Internet Engineering Task Force (IETF) has chartered a working group. It is named "Codec Encoding for LossLess Archiving and Realtime transmission" (CELLAR) and aims to develop specifications for a lossless audiovisual file format for use in archival environments and transmission. It consists of the combination of the audiovisual c...

We studied the representations underlying audiovisual integration using a priming paradigm. Audiovisual primes, preceding auditory targets, were either incongruent (auditory /ba/ & visual /va/) or congruent (auditory /va/ & visual /va/, auditory /ba/ & visual /ba/). The targets were /ba/ or /va/. The intensity of the prime ́s auditory component was either 50 dB or 60 dB. Identification speed of ...