AI TOP Database
- [:en]Title of the resource[:bg]Заглавие на ресурса[:nl]Titel van de bron[:sr]Назив ресурса[:el]Τίτλος της πηγής[:]
- A comparative study of Autistic Children Emotion recognition based on Spatio-Temporal and Deep analysis of facial expressions features during a Meltdown Crisis
- [:en]Who am I?[:bg]Вие сте:[:nl]Wie ben ik?[:sr]Ко сам ја?[:el]Ποιός είμαι;[:]
- [:en]Type of the resource[:bg]Вид на ресурса[:nl]Type van de bron[:sr]Тип ресурса[:el]Τύπος της πηγής[:]
- [:en]Scientific article[:bg]Научна статия[:nl]Wetenschappelijk artikel[:sr]Научни чланак[:el]Επιστημονικό άρθρο[:]
- [:en]Languages available[:bg]Налични езици[:nl]Beschikbare talen[:sr]Доступни језици[:el]Διαθέσιμες γλώσσες[:]
- [:en]English[:bg]Английски[:nl]Engels[:sr]Енглески[:el]Αγγλικά[:]
- [:en]Country of implementation[:bg]Държава на приложение[:nl]Land van implementatie[:sr]Земља имплементације[:el]Χώρα εφαρμογής[:]
- Tunisia
- [:en]Type of access[:bg]Тип достъп[:nl]Type toegang[:sr]Тип приступа[:el]Είδος πρόσβασης[:]
- [:en]Payment needed[:bg]Изисква се плащане[:nl]Betaling nodig[:sr]Потребно плаћање[:el]Απαιτείται πληρωμή
- [:en]Main description[:bg]Описание[:nl]Hoofdbeschrijving[:sr]Главни опис[:el]Κύρια περιγραφή[:]
- Present responses to the crisis meltdown are based on a reactive approach. Indeed, Meltdown symptoms are determined by abnormal facial expressions related to compound emotions. To provide for this correspondence, researchers experimentally evaluate, in this paper, hand-crafted Geometric Spatio-Temporal and Deep features of realistic autistic children facial expressions. Towards this end, we compared the Compound Emotion Recognition (CER) performance for different combinations of these features, and we determined the features that best distinguish a Compound Emotion (CE) of autistic children during a meltdown crisis from the normal state. We used “Meltdown crisis”1 dataset to conduct our experiments on realistic Meltdown / Normal scenarios of autistic children. In this evaluation, we show that the gathered features can lead to very encouraging performances through the use of Random Forest classifier (91.27%) with hand-crafted features. Moreover, classifiers trained on deep features from InceptionResnetV2 show higher performance (97.5%) with supervised learning techniques.
- [:en]Resource URL[:bg]URL адрес на ресурса[:nl]Bron-URL[:sr]Ресурс УРЛ[:el]URL πόρου[:]
- [:en]Resource[:bg]Ресурс[:nl]Bron[:sr]Ресурс[:el]Πηγή[:]
- [:en]Type of setting[:bg]Тип среда[:nl]Type instelling[:sr]Тип подешавања[:el]Τύπος ρύθμισης[:]
- [:en]Specialized school[:bg]Специално училище[:nl]Gespecialiseerde school[:sr]Специјализована школа[:el]Εξειδικευμένο σχολείο[:]
- [:en]Type of challenge addressed[:bg]Вид предизвикателство[:nl]Soort uitdaging die wordt aangepakt[:sr]Тип изазовне адресе[:el]Τύπος αντιμετώπισης της πρόκλησης[:]
- [:en]Prerumble and Meltdown moments[:bg]Предкризисни и кризисни епизоди[:nl]Prematuur en Meltdown momenten[:sr]Моменти почетка проблема[:el]Στιγμές πριν την κατάρρευση και στιγμές κατάρρευσης[:]