The Internet overhypes ChatGPT, which probably fits into the Dunning-Kruger effect curve. Nevertheless, we must bust some myths about this allegedly incredible AI. By Adam Kaczmarek
Skeleton data is widely used in human action recognition for easy access, computational efficiency and environmental robustness. Recently, encoding skeleton sequences into color images becomes a popular preprocessing procedure to make use of the spatial modeling ability of convolutional neural network (CNN). Furthermore, inspired by relevant work in other fields, attention mechanism has been introduced to CNN based skeleton action recognition. In this paper, we propose a two-branch hierarchical attention model (HAN) for skeleton based action recognition. The proposed model consists of a base branch for spatial-temporal feature extraction and an attention branch for feature enhancement. In attention branch, we utilize auxiliary feature instead of intermediate feature to generate attention maps. Specifically, variance vectors of skeleton sequences are fused as motion saliency matrices to determine the contributions of each joint. Then the motion saliency matrices are sent into the hierar
Affective computing (AC) has been regarded as a relevant approach to identifying online learners’ mental states and predicting their learning performance. Previous research mainly used one single-source data set, typically learners’ facial expression, to compute learners’ affection. However, a single facial expression may represent different affections in various head poses. This study proposed a dual-source data approach to solve the problem. Facial expression and head pose are two typical data sources that can be captured from online learning videos. The current study collected a dual-source data set of facial expressions and head poses from an online learning class in a middle school. A deep learning neural network using AlexNet with an attention mechanism was developed to verify the syncretic effect on affective computing of the proposed dual-source fusion strategy. The results show that the dual-source fusion approach significantly outperforms the single-source approach base
A text semantic classification is an essential approach to recognising the verbal intention of online learners, empowering reliable understanding and inquiry for the regulations of knowledge construction amongst students. However, online learning is increasingly switching from static watching patterns to the collaborative discussion. The current deep learning models, such as CNN and RNN, are ineffective in classifying verbal content contextually. Moreover, the contribution of verbal elements to semantics is often considerably varied, requiring the attachment of weights to these elements to increase verbal recognition precision. The Bi-LSTM is considered to be an adaptive model to investigate semantic relations according to the context. Moreover, the attention mechanism in deep learning simulating human vision could assign weights to target texts effectively. This study proposed to construct a deep learning model combining Bi-LSTM and attention mechanism, in which Bi-LSTM obtained the v
Generating high-quality complete question sets (for example, the question, answer and distractors) in reading comprehension tasks is challenging and rewarding. This paper proposes a question-distractor joint generation framework (QDG). The framework can automatically generate both questions and distractors given a background text and the specified answer. Our work makes it possible to combine complete multiple-choice reading comprehension questions that can be better applied to educators’ work. While there have been independent studies of question generation and distractor generation in previous studies, there have been few joint question-distractor generation studies. In a past joint generation, distractors could only be constructed by generating questions first and then by sorting the answers with similar words. It was impossible to generate question-distractor pairs in an end-to-end unified joint generation approach. To the best of our knowledge, we are the first to propose an end