An Investigation of College English Autonomous Learning in Network Multimodal Context

In the current society, based on the growing development of network information technology, the teaching in many colleges and universities has also introduced it to adapt to the situation. This trend can provide more useful conditions for students to learn, which requires students to master enough self-learning abilities to adapt to this model. The study in the paper shows that students are usually interested in autonomous learning in a multimodal environment, but the degree of strategy choice is relatively low, and the learning process is blind and passive with the lack of self-confidence. Facing the future, schools should actively integrate into network thinking, and teachers should change their roles and train and guide students’ learning strategies and learning motivations, so as to achieve better teaching results.

A multimodal dense convolution network for blind image quality assessment

Technological advancements continue to expand the communications industry’s potential.Images,which are an important component in strengthening communication,are widely available.Therefore,image quality assessment(IQA)is critical in improving content delivered to end users.Convolutional neural networks(CNNs)used in IQA face two common challenges.One issue is that these methods fail to provide the best representation of the image.The other issue is that the models have a large number of parameters,which easily leads to overfitting.To address these issues,the dense convolution network(DSC-Net),a deep learning model with fewer parameters,is proposed for no-reference image quality assessment(NR-IQA).Moreover,it is obvious that the use of multimodal data for deep learning has improved the performance of applications.As a result,multimodal dense convolution network(MDSC-Net)fuses the texture features extracted using the gray-level co-occurrence matrix(GLCM)method and spatial features extracted using DSC-Net and predicts the image quality.The performance of the proposed framework on the benchmark synthetic datasets LIVE,TID2013,and KADID-10k demonstrates that the MDSC-Net approach achieves good performance over state-of-the-art methods for the NR-IQA task.

MODELING THE CONGESTION COST AND VEHICLE EMISSION WITHIN MULTIMODAL TRAFFIC NETWORK UNDER THE CONDITION OF EQUILIBRIUM

Traditional system optimization models for traffic network focus on the treatment of congestion, which usually have an objective of minimizing the total travel time. However, the negative externality of congestion, such as environment pollution, is neglected in most cases. Such models fall short in taking Greenhouse Gas （GHG） emissions and its impact on climate change into consideration. In this paper, a social-cost based system optimization （SO） model is proposed for the multimodal traffic network considering both traffic congestion and corresponding vehicle emission. Firstly, a variation inequality model is developed to formulate the equilibrium problem for such network based on the analysis of travelers＇ combined choices. Secondly, the computational models of traffic congestion and vehicle emission of whole multimodal network are proposed based on the equilibrium link-flows and the corresponding travel times. A bi-level programming model, in which the social-cost based SO model is treated as the upper-level problem and the combined equilibrium model is processed as the lower-level problem, is then presented with its solution algorithm. Finally, the proposed models are illustrated through a simple numerical example. The study results confirm and support the idea of giving the priority to the development of urban public transport, which is an effective way to achieve a sustainable urban transportation.

Deep Multimodal Reinforcement Network with Contextually GuidedRecurrent Attention for Image Question Answering

Image question answering (IQA) has emerged as a promising interdisciplinary topic in computer vision and natural language processing fields. In this paper, we propose a contextually guided recurrent attention model for solving the IQA issues. It is a deep reinforcement learning based multimodal recurrent neural network. Based on compositional contextual information, it recurrently decides where to look using reinforcement learning strategy. Different from traditional 'static' soft attention, it is deemed as a kind of 'dynamic' attention whose objective is designed based on reinforcement rewards purposefully towards IQA. The finally learned compositional information incorporates both global context and local informative details, which is demonstrated to benefit for generating answers. The proposed method is compared with several state-of-the-art methods on two public IQA datasets, including COCO-QA and VQA from dataset MS COCO. The experimental results demonstrate that our proposed model outperforms those methods and achieves better performance.