A computer aided design method for car form and its application based on shape parameters

In the early design stage, automotive modeling should both meet the requirements of aesthetics and engineering. Therefore, a vehicle CAD (computer aided design) model that can be easily adjusted by feedbacks is necessary. Based on CE-Bézier surface, this paper presents a set of algorithms for parametric segmentation and fairing surface generation in a car model. This model is defined by a simplified automotive template and relevant control points, shape parameters and segmentation parameters, which can be modified to alter the car form efficiently. With this model and the corresponding adjustment method, more than fifty various vehicle models are established in this research according to different parameters. And two methods for calculating similarity index between car models are constructed, which are suitable for brand design trend analysis and modelling design decisionmaking.     

Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

A Novel Beam Search to Improve Neural Machine Translation for English-Chinese

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, overcoming the weaknesses of conventional phrase-based translation systems. Although NMT based systems have gained their popularity in commercial translation applications, there is still plenty of room for improvement. Being the most popular search algorithm in NMT, beam search is vital to the translation result. However, traditional beam search can produce duplicate or missing translation due to its target sequence selection strategy. Aiming to alleviate this problem, this paper proposed neural machine translation improvements based on a novel beam search evaluation function. And we use reinforcement learning to train a translation evaluation system to select better candidate words for generating translations. In the experiments, we conducted extensive experiments to evaluate our methods. CASIA corpus and the 1,000,000 pairs of bilingual corpora of NiuTrans are used in our experiments. The experiment results prove that the proposed methods can effectively improve the English to Chinese translation quality.     

知竹,知足——浅谈紫砂壶“知竹”的文化意境

紫砂壶以造型为基本的载体,通过形神兼备的造型表现出深厚的文化情感,它将自然万物融汇其中,将各种不同的生命、思想和个性呈现其上,使人观壶如同与人交流,产生深刻的情感、精神共鸣,感受到内心的平静,这十分有益于舒缓当代人的精神心理压力,让人们通过泡茶品茗这种生活方式来获得暂时的悠闲,并通过对紫砂壶的把玩来感悟其中的文化内蕴,从而获得自由淡泊的心态,更好地面对生活。本文以紫砂壶“知竹”为例,浅谈其文化意境。