While behavioural difficulties in facial emotion recognition (FER) have been observed in individuals with Autism Spectrum Disorder (ASD), behavioural studies alone are not suited to elucidate the specific nature of FER challenges in ASD. Eye tracking (ET) and electroencephalography (EEG) provide insights in to the attentional and neurological correlates of performance, and may therefore provide insight in to the mechanisms underpinning FER in ASD. Given that these processes develop over the course of the developmental trajectory, there is a need to synthesise findings in regard to the developmental stages to determine how the maturation of these systems may impact FER in ASD. We conducted a systematic review of fifty-four studies investigating ET or EEG meeting inclusion criteria. Findings indicate divergence of visual processing pathways in individuals with ASD. Altered function of the social brain in ASD impacts the processing of facial emotion across the developmental trajectory, resulting in observable differences in ET and EEG outcomes.

The purpose of this review was to build upon a recent review by Weigelt et al. which examined visual search strategies and face identification between individuals with autism spectrum disorders (ASD) and typically developing peers. Seven databases, CINAHL Plus, EMBASE, ERIC, Medline, Proquest, PsychInfo and PubMed were used to locate published scientific studies matching our inclusion criteria. A total of 28 articles not included in Weigelt et al. met criteria for inclusion into this systematic review. Of these 28 studies, 16 were available and met criteria at the time of the previous review, but were mistakenly excluded; and twelve were recently published. Weigelt et al. found quantitative, but not qualitative, differences in face identification in individuals with ASD. In contrast, the current systematic review found both qualitative and quantitative differences in face identification between individuals with and without ASD. There is a large inconsistency in findings across the eye tracking and neurobiological studies reviewed. Recommendations for future research in face recognition in ASD were discussed.

One of the essential pre-processing steps of semantic video analysis is the video shot boundary detection (SBD). It is the primary step to segment the sequence of video frames into shots. Many SBD systems using supervised learning have been proposed for years; however, the training process still remains its principal limitation. In this paper, a multi-modal visual features-based SBD framework is employed that aims to analyze the behaviors of visual representation in terms of the discontinuity signal. We adopt a candidate segment selection that performs without the threshold calculation but uses the cumulative moving average of the discontinuity signal to identify the position of shot boundaries and neglect the non-boundary video frames. The transition detection is structurally performed to distinguish candidate segment into a cut transition and a gradual transition, including fade in/out and logo occurrence. Experimental results are evaluated using the golf video clips and the TREC2001 documentary video data set. Results show that the proposed SBD framework can achieve good accuracy in both types of video data set compared with other proposed SBD methods.

A repetitive movement practice by motor imagery (MI) can influence motor cortical excitability in the electroencephalogram (EEG). The feedback and the feedback environment should be inherently motivating and relevant for the learner and should have an appeal of novelty, real-world relevance or aesthetic value (Ryan and Deci, 2000; Merrill, 2007). This study investigated if a realistic visualization in 3D of upper and lower limb movements can amplify motor related potentials during motor imagery. We hypothesized that a richer sensory visualization might be more effective during instrumental conditioning, resulting in a more pronounced event related desynchronisation (ERD) of the upper alpha band (10-12 Hz) over the sensorimotor cortices thereby potentially improving MI based BCI protocols for motor rehabilitation. The results show a strong increase of the characteristic patterns of ERD of the upper alpha band components for left and right limb motor imagery present over the sensorimotor areas in both visualization conditions. Overall, significant differences were observed as a function of visualization modality (2D vs. 3D). The largest upper alpha band power decrease was obtained during motor imagery after a 3-dimensional visualization. In total in 12 out of 20 tasks the end-user of the 3D visualization group showed an enhanced upper alpha ERD relative to 2D visualization modality group, with statistical significance in nine tasks. With a realistic visualization of the limb movements, we tried to increase motor cortex activation during MI. Realistic visual feedback, consistent with the participant’s motor imagery, might be helpful for accomplishing successful motor imagery and the use of such feedback may assist in making BCI a more natural interface for motor imagery based BCI rehabilitation.