Semi-automatic annotation and retrieval of visual content using the topic map technology

There are still major challenges in the area of automatic indexing and retrieval of multimedia content data for very large multimedia content corpora. Current indexing and retrieval applications still use keywords to index multimedia content and those keywords usually do not provide any knowledge about the semantic content of the data. With the increasing amount of multimedia content, it is inefficient to continue with this approach. In this paper, we describe the project DREAM, which addresses such challenges by proposing a new framework for semi-automatic annotation and retrieval of multimedia based on the semantic content. The framework uses the Topic Map Technology, as a tool to model the knowledge automatically extracted from the multimedia content using an Automatic Labelling Engine. We describe how we acquire knowledge from the content and represent this knowledge using the support of NLP to automatically generate Topic Maps. The framework is described in the context of film post-production.

The DREAM Framework: using a network of scalable ontologies for intelligent indexing and retrieval of visual content

There are still major challenges in the area of automatic indexing and retrieval of digital data. The main problem arises from the ever increasing mass of digital media and the lack of efficient methods for indexing and retrieval of such data based on the semantic content rather than keywords. To enable intelligent web interactions or even web filtering, we need to be capable of interpreting the information base in an intelligent manner. Research has been ongoing for a few years in the field of ontological engineering with the aim of using ontologies to add knowledge to information. In this paper we describe the architecture of a system designed to automatically and intelligently index huge repositories of special effects video clips, based on their semantic content, using a network of scalable ontologies to enable intelligent retrieval.

Semi-automatic knowledge extraction, representation and context-sensitive intelligent retrieval of video content using collateral context modelling with scalable ontological networks

Automatic indexing and retrieval of digital data poses major challenges. The main problem arises from the ever increasing mass of digital media and the lack of efficient methods for indexing and retrieval of such data based on the semantic content rather than keywords. To enable intelligent web interactions, or even web filtering, we need to be capable of interpreting the information base in an intelligent manner. For a number of years research has been ongoing in the field of ontological engineering with the aim of using ontologies to add such (meta) knowledge to information. In this paper, we describe the architecture of a system (Dynamic REtrieval Analysis and semantic metadata Management (DREAM)) designed to automatically and intelligently index huge repositories of special effects video clips, based on their semantic content, using a network of scalable ontologies to enable intelligent retrieval. The DREAM Demonstrator has been evaluated as deployed in the film post-production phase to support the process of storage, indexing and retrieval of large data sets of special effects video clips as an exemplar application domain. This paper provides its performance and usability results and highlights the scope for future enhancements of the DREAM architecture which has proven successful in its first and possibly most challenging proving ground, namely film production, where it is already in routine use within our test bed Partners' creative processes. (C) 2009 Published by Elsevier B.V.

The neural response to emotional prosody, as revealed by functional magnetic resonance imaging

Prosody is an important feature of language, comprising intonation, loudness, and tempo. Emotional prosodic processing forms an integral part of our social interactions. The main aim of this study was to use bold contrast fMRI to clarify the normal functional neuroanatomy of emotional prosody, in passive and active contexts. Subjects performed six separate scanning studies, within which two different conditions were contrasted: (1) "pure" emotional prosody versus rest; (2) congruent emotional prosody versus 'neutral' sentences; (3) congruent emotional prosody versus rest; (4) incongruent emotional prosody versus rest; (5) congruent versus incongruent emotional prosody; and (6) an active experiment in which subjects were instructed to either attend to the emotion conveyed by semantic content or that conveyed by tone of voice. Data resulting from these contrasts were analysed using SPM99. Passive listening to emotional prosody consistently activated the lateral temporal lobe (superior and/or middle temporal gyri). This temporal lobe response was relatively right-lateralised with or without semantic information. Both the separate and direct comparisons of congruent and incongruent emotional prosody revealed that subjects used fewer brain regions to process incongruent emotional prosody than congruent. The neural response to attention to semantics, was left lateralised, and recruited an extensive network not activated by attention to emotional prosody. Attention to emotional prosody modulated the response to speech, and induced right-lateralised activity, including the middle temporal gyrus. In confirming the results of lesion and neuropsychological studies, the current study emphasises the importance of the right hemisphere in the processing of emotional prosody, specifically the lateral temporal lobes. (C) 2003 Elsevier Science Ltd. All rights reserved.

Visual motion interferes with lexical decision on motion words

Embodied theories of cognition propose that neural substrates used in experiencing the referent of a word, for example perceiving upward motion, should be engaged in weaker form when that word, for example ‘rise’, is comprehended. Motivated by the finding that the perception of irrelevant background motion at near-threshold, but not supra-threshold, levels interferes with task execution, we assessed whether interference from near-threshold background motion was modulated by its congruence with the meaning of words (semantic content) when participants completed a lexical decision task (deciding if a string of letters is a real word or not). Reaction times for motion words, such as ‘rise’ or ‘fall’, were slower when the direction of visual motion and the ‘motion’ of the word were incongruent — but only when the visual motion was at nearthreshold levels. When motion was supra-threshold, the distribution of error rates, not reaction times, implicated low-level motion processing in the semantic processing of motion words. As the perception of near-threshold signals is not likely to be influenced by strategies, our results support a close contact between semantic information and perceptual systems.

Auditory distraction in memory tasks: Can it be controlled?

Irrelevant sound accompanying the processes of encoding and retrieval of verbal events impairs memory performance. However, the degree of impairment is highly dependent on a range of factors. Some of them lie outside rememberers’ control, like the semantic content of distracting sound or the nature of a test used to assess memory. Others, like a strategy used to encode memoranda, rest under control of the rememberer. In this paper the factors that modulate memory impairment are outlined and discussed in terms of multiple mechanisms contributing to memory impairment under auditory distraction. The mechanisms of a capture of attention by distraction, interference of automatic seriation of distraction and voluntary seriation of memoranda, semantic inhibition of distraction, and blocking of memoranda by semantically related distracters are described. Results that demonstrate how these mechanisms determine memory impairment under auditory distraction are also discussed. Particular attention is devoted to the possibility of voluntary control over the workings of these mechanisms and the conditions under which the negative impact of auditory distraction upon memory performance could be minimised.

An optimized ERP brain–computer interface based on facial expression changes

Objective. Interferences from spatially adjacent non-target stimuli are known to evoke event-related potentials (ERPs) during non-target flashes and, therefore, lead to false positives. This phenomenon was commonly seen in visual attention-based brain–computer interfaces (BCIs) using conspicuous stimuli and is known to adversely affect the performance of BCI systems. Although users try to focus on the target stimulus, they cannot help but be affected by conspicuous changes of the stimuli (such as flashes or presenting images) which were adjacent to the target stimulus. Furthermore, subjects have reported that conspicuous stimuli made them tired and annoyed. In view of this, the aim of this study was to reduce adjacent interference, annoyance and fatigue using a new stimulus presentation pattern based upon facial expression changes. Our goal was not to design a new pattern which could evoke larger ERPs than the face pattern, but to design a new pattern which could reduce adjacent interference, annoyance and fatigue, and evoke ERPs as good as those observed during the face pattern. Approach. Positive facial expressions could be changed to negative facial expressions by minor changes to the original facial image. Although the changes are minor, the contrast is big enough to evoke strong ERPs. In this paper, a facial expression change pattern between positive and negative facial expressions was used to attempt to minimize interference effects. This was compared against two different conditions, a shuffled pattern containing the same shapes and colours as the facial expression change pattern, but without the semantic content associated with a change in expression, and a face versus no face pattern. Comparisons were made in terms of classification accuracy and information transfer rate as well as user supplied subjective measures. Main results. The results showed that interferences from adjacent stimuli, annoyance and the fatigue experienced by the subjects could be reduced significantly (p < 0.05) by using the facial expression change patterns in comparison with the face pattern. The offline results show that the classification accuracy of the facial expression change pattern was significantly better than that of the shuffled pattern (p < 0.05) and the face pattern (p < 0.05). Significance. The facial expression change pattern presented in this paper reduced interference from adjacent stimuli and decreased the fatigue and annoyance experienced by BCI users significantly (p < 0.05) compared to the face pattern.

When semantics aids phonology: a processing advantage for iconic word forms in aphasia

Iconicity is the non-arbitrary relation between properties of a phonological form and semantic content (e.g. “moo”, “splash”). It is a common feature of both spoken and signed languages, and recent evidence shows that iconic forms confer an advantage during word learning. We explored whether iconic forms conferred a processing advantage for 13 individuals with aphasia following left-hemisphere stroke. Iconic and control words were compared in four different tasks: repetition, reading aloud, auditory lexical decision and visual lexical decision. An advantage for iconic words was seen for some individuals in all tasks, with consistent group effects emerging in reading aloud and auditory lexical decision. Both these tasks rely on mapping between semantics and phonology. We conclude that iconicity aids spoken word processing for individuals with aphasia. This advantage may be due to a stronger connection between semantic information and phonological forms.

An optimized ERP Brain-computer interface based on facial expression changes

OBJECTIVE: Interferences from spatially adjacent non-target stimuli are known to evoke event-related potentials (ERPs) during non-target flashes and, therefore, lead to false positives. This phenomenon was commonly seen in visual attention-based brain-computer interfaces (BCIs) using conspicuous stimuli and is known to adversely affect the performance of BCI systems. Although users try to focus on the target stimulus, they cannot help but be affected by conspicuous changes of the stimuli (such as flashes or presenting images) which were adjacent to the target stimulus. Furthermore, subjects have reported that conspicuous stimuli made them tired and annoyed. In view of this, the aim of this study was to reduce adjacent interference, annoyance and fatigue using a new stimulus presentation pattern based upon facial expression changes. Our goal was not to design a new pattern which could evoke larger ERPs than the face pattern, but to design a new pattern which could reduce adjacent interference, annoyance and fatigue, and evoke ERPs as good as those observed during the face pattern. APPROACH: Positive facial expressions could be changed to negative facial expressions by minor changes to the original facial image. Although the changes are minor, the contrast is big enough to evoke strong ERPs. In this paper, a facial expression change pattern between positive and negative facial expressions was used to attempt to minimize interference effects. This was compared against two different conditions, a shuffled pattern containing the same shapes and colours as the facial expression change pattern, but without the semantic content associated with a change in expression, and a face versus no face pattern. Comparisons were made in terms of classification accuracy and information transfer rate as well as user supplied subjective measures. MAIN RESULTS: The results showed that interferences from adjacent stimuli, annoyance and the fatigue experienced by the subjects could be reduced significantly (p < 0.05) by using the facial expression change patterns in comparison with the face pattern. The offline results show that the classification accuracy of the facial expression change pattern was significantly better than that of the shuffled pattern (p < 0.05) and the face pattern (p < 0.05). SIGNIFICANCE: The facial expression change pattern presented in this paper reduced interference from adjacent stimuli and decreased the fatigue and annoyance experienced by BCI users significantly (p < 0.05) compared to the face pattern.

Semantic-level Visual Content Descriptor combining visual and textual cues as collaterals

In this paper, we introduce a novel high-level visual content descriptor which is devised for performing semantic-based image classification and retrieval. The work can be treated as an attempt to bridge the so called “semantic gap”. The proposed image feature vector model is fundamentally underpinned by the image labelling framework, called Collaterally Confirmed Labelling (CCL), which incorporates the collateral knowledge extracted from the collateral texts of the images with the state-of-the-art low-level image processing and visual feature extraction techniques for automatically assigning linguistic keywords to image regions. Two different high-level image feature vector models are developed based on the CCL labelling of results for the purposes of image data clustering and retrieval respectively. A subset of the Corel image collection has been used for evaluating our proposed method. The experimental results to-date already indicates that our proposed semantic-based visual content descriptors outperform both traditional visual and textual image feature models.

The effects of web logs and the semantic web on autonomous web agents

Search engines exploit the Web's hyperlink structure to help infer information content. The new phenomenon of personal Web logs, or 'blogs', encourage more extensive annotation of Web content. If their resulting link structures bias the Web crawling applications that search engines depend upon, there are implications for another form of annotation rapidly on the rise, the Semantic Web. We conducted a Web crawl of 160 000 pages in which the link structure of the Web is compared with that of several thousand blogs. Results show that the two link structures are significantly different. We analyse the differences and infer the likely effect upon the performance of existing and future Web agents. The Semantic Web offers new opportunities to navigate the Web, but Web agents should be designed to take advantage of the emerging link structures, or their effectiveness will diminish.

Semantic-associative visual content labelling and retrieval: A multimodal approach

A novel framework referred to as collaterally confirmed labelling (CCL) is proposed, aiming at localising the visual semantics to regions of interest in images with textual keywords. Both the primary image and collateral textual modalities are exploited in a mutually co-referencing and complementary fashion. The collateral content and context-based knowledge is used to bias the mapping from the low-level region-based visual primitives to the high-level visual concepts defined in a visual vocabulary. We introduce the notion of collateral context, which is represented as a co-occurrence matrix of the visual keywords. A collaborative mapping scheme is devised using statistical methods like Gaussian distribution or Euclidean distance together with collateral content and context-driven inference mechanism. We introduce a novel high-level visual content descriptor that is devised for performing semantic-based image classification and retrieval. The proposed image feature vector model is fundamentally underpinned by the CCL framework. Two different high-level image feature vector models are developed based on the CCL labelling of results for the purposes of image data clustering and retrieval, respectively. A subset of the Corel image collection has been used for evaluating our proposed method. The experimental results to-date already indicate that the proposed semantic-based visual content descriptors outperform both traditional visual and textual image feature models. (C) 2007 Elsevier B.V. All rights reserved.

Collaterally cued labelling framework underpinning semantic-level visual content descriptor

In this paper, we introduce a novel high-level visual content descriptor devised for performing semantic-based image classification and retrieval. The work can be treated as an attempt for bridging the so called "semantic gap". The proposed image feature vector model is fundamentally underpinned by an automatic image labelling framework, called Collaterally Cued Labelling (CCL), which incorporates the collateral knowledge extracted from the collateral texts accompanying the images with the state-of-the-art low-level visual feature extraction techniques for automatically assigning textual keywords to image regions. A subset of the Corel image collection was used for evaluating the proposed method. The experimental results indicate that our semantic-level visual content descriptors outperform both conventional visual and textual image feature models.

The relation between content and structure in language production: an analysis of speech errors in semantic dementia

In order to explore the impact of a degraded semantic system on the structure of language production, we analysed transcripts from autobiographical memory interviews to identify naturally-occurring speech errors by eight patients with semantic dementia (SD) and eight age-matched normal speakers. Relative to controls, patients were significantly more likely to (a) substitute and omit open class words, (b) substitute (but not omit) closed class words, (c) substitute incorrect complex morphological forms and (d) produce semantically and/or syntactically anomalous sentences. Phonological errors were scarce in both groups. The study confirms previous evidence of SD patients’ problems with open class content words which are replaced by higher frequency, less specific terms. It presents the first evidence that SD patients have problems with closed class items and make syntactic as well as semantic speech errors, although these grammatical abnormalities are mostly subtle rather than gross. The results can be explained by the semantic deficit which disrupts the representation of a pre-verbal message, lexical retrieval and the early stages of grammatical encoding.