Abstract
Creating descriptive labels for videos is an important task, with application in video retrieval, Web accessibility and computer vision. However automatic creation of such labels is difficult and, alternatively, having professionals manually describing content is too expensive. Engaging end-users in the process of describing multimedia assets may lead to good results and enables creating the sense of participation which is currently one of the key factors to attract customers to a service. The existing approaches are highly successful in terms of number of engaged players and number of collected labels, but hardly create comprehensive tag sets, contributing both with generic or too narrow meaning tags. "Games With A Purpose" are one of the approaches that have been used in an attempt to create comprehensive video descriptions by harnessing the intelligence of human players and have them contributing and collaborating towards a common goal that is recognized if successful. This paper describes a game which implements two mechanisms for collecting data via human-based computation games. Tags introduced by registered players, in a given timecode, are validated based on a collaborative scoring mechanism that eliminates irregular annotations. Additionally, a voting mechanism that enables players to endorse or refuse existing tags, provides an extra instrument to guarantee the quality of the annotations. © 2013 ACM.

Abstract
This paper presents a methodology for correcting band distortions in Thin-Layer Chromatography (TLC) images. After the segmentation of image lanes, the intensity profile of each lane column is spatially aligned with a reference profile using a modified version of the Correlation Optimized Warping (COW) algorithm. As the initial partition of the profile into equal length segments proposed by COW can result in the separation of a single band between two segments to be disjointedly aligned, in the proposed method the warping function is only applied to selected profile regions containing groups of adjacent bands. The proposed band correction methodology was assessed using 105 profiles of 105 TLC lanes. A set of features for band characterization was extracted from each lane profile, before and after band distortion correction, and was used as input for three distinct one-class classifiers aiming at band identification. In all cases, the best results of band classification were obtained for the set lanes after band distortion correction.

Abstract
Despite the rising number of emotional state detection methods motivated by the popularity increase in affective computing techniques in recent years, they are yet faced with subject and domain transferability issues. In this paper, we present an improved methodology for modelling individuals' emotional states in multimedia interactive environments. Our method relies on a two-layer classification process to classify Arousal and Valence based on four distinct physiological sensor inputs. The first classification layer uses several regression models to normalize each of the sensor inputs across participants and experimental conditions, while also correlating each input to either Arousal or Valence - effectively addressing the aforementioned transferability issues. The second classification layer then employs a residual sum of squares-based weighting scheme to merge the various regression outputs into one optimal Arousal/Valence classification in real-time, while maintaining a smooth prediction output. The presented method exhibited convincing accuracy ratings - 85% for Arousal and 78% for Valence -, which are only marginally worse than our previous non-real-time approach.

Abstract
This paper introduces a new approach to 3-D position estimation from acceleration data, i.e., a 3-D motion tracking system having a small size and low-cost magnetic and inertial measurement unit (MIMU) composed by both a digital compass and a gyroscope as interaction technology. A major challenge is to minimize the error caused by the process of double integration of accelerations due to motion (these ones have to be separated from the accelerations due to gravity). Owing to drift error, position estimation cannot be performed with adequate accuracy for periods longer than few seconds. For this reason, we propose a method to detect motion stops and only integrate accelerations in moments of effective hand motion during the demonstration process. The proposed system is validated and evaluated with experiments reporting a common daily life pick-and-place task.

Abstract
We quantitatively evaluated the localizing and lateralizing characteristics of ictal upper limb automatisms (ULAs) in patients with temporal lobe epilepsy (TLE; n = 38) and frontal lobe epilepsy (FLE; n = 20). Movement speed, extent, length, and duration of ULAs were quantitatively analyzed with motion capturing techniques. Upper limb automatisms had a larger extent (p < 0.001), covered more distance (p < 0.05), and were faster (p < 0.001) in FLE than in TLE. In TLE, the maximum speed of ULAs was higher ipsilaterally than contralaterally (173 vs. 84 pixels/s; p = 0.02), with no significant difference in FLE (511 vs. 428). The duration of ictal automatisms in relation to the total seizure duration was shorter in TLE than in FLE (median 36% vs. 63%; p < 0.001), with no difference in the absolute duration (26 s vs. 27 s). These results demonstrate that quantitative movement analysis of ULAs differentiates FLE from TLE, which may aid in the localization of the epileptogenic zone.

Abstract