No abstract

Neural machine translation (NMT) aims at solving machine translation (MT) problems using neural networks and has exhibited promising results in recent years. However, most of the existing NMT models are shallow and there is still a performance gap between a single NMT model and the best conventional MT system. In this work, we introduce a new type of linear connections, named fastforward connections, based on deep Long Short-Term Memory (LSTM) networks, and an interleaved bi-directional architecture for stacking the LSTM layers. Fast-forward connections play an essential role in propagating the gradients and building a deep topology of depth 16. On the WMT'14 Englishto-French task, we achieve BLEU=37.7 with a single attention model, which outperforms the corresponding single shallow model by 6.2 BLEU points. This is the first time that a single NMT model achieves state-of-the-art performance and outperforms the best conventional model by 0.7 BLEU points. We can still achieve BLEU=36.3 even without using an attention mechanism. After special handling of unknown words and model ensembling, we obtain the best score reported to date on this task with BLEU=40.4. Our models are also validated on the more difficult WMT'14 English-to-German task.

Layout is fundamental to graphic designs. For visual attractiveness and efficient communication of messages and ideas, graphic design layouts often have great variation, driven by the contents to be presented. In this paper, we study the problem of content-aware graphic design layout generation. We propose a deep generative model for graphic design layouts that is able to synthesize layout designs based on the visual and textual semantics of user inputs. Unlike previous approaches that are oblivious to the input contents and rely on heuristic criteria, our model captures the effect of visual and textual contents on layouts, and implicitly learns complex layout structure variations from data without the use of any heuristic rules. To train our model, we build a large-scale magazine layout dataset with fine-grained layout annotations and keyword labeling. Experimental results show that our model can synthesize high-quality layouts based on the visual semantics of input images and keyword-based summary of input text. We also demonstrate that our model internally learns powerful features that capture the subtle interaction between contents and layouts, which are useful for layout-aware design retrieval.

No abstract

No abstract

Figure 1: Three layouts generated by our approach trained on "Fairy Tail". The left side of each example displays the sequence of input artworks ("Daffy: The Commando"(1943) in the public domain), single-panel semantics, including importance-ranking values (within the parenthesis and region of interest (masked by rectangle), as well as optional inter-panel semantics that describe a group of consecutive semantically related panels (grouped by a red line in the rightmost example). The character masked by the green rectangle is chosen for a"fourth wall break" effect. The reading order of each layout is from left to right and then top to bottom. AbstractManga layout is a core component in manga production, characterized by its unique styles. However, stylistic manga layouts are difficult for novices to produce as it requires hands-on experience and domain knowledge. In this paper, we propose an approach to automatically generate a stylistic manga layout from a set of input artworks with user-specified semantics, thus allowing lessexperienced users to create high-quality manga layouts with minimal efforts. We first introduce three parametric style models that encode the unique stylistic aspects of manga layouts, including layout structure, panel importance, and panel shape. Next, we propose a two-stage approach to generate a manga layout: 1) an initial layout is created that best fits the input artworks and layout structure model, according to a generative probabilistic framework; 2) the layout and artwork geometries are jointly refined using an efficient optimization procedure, resulting in a professional-looking manga layout. Through a user study, we demonstrate that our approach enables novice users to easily and quickly produce higherquality layouts that exhibit realistic manga styles, when compared to a commercially-available manual layout tool.

How to provide construction managers with information about and insight into the existing data so as to make decision more efficiently without interrupting the daily work of an On-Line Transaction Processing (OLTP) system is a problem during the construction management process. To solve this problem, the integration of a Data Warehouse and a Decision Support System (DSS) seems to be efficient. 'Data warehouse' technology is a new database branch, which has not been applied to construction management yet. Hence, it is worthwhile to experiment in this particular field, in order to gauge the full scope of its capability. First reviewed in this paper, are the concepts of the data warehouse, On-Line Analysis Processing (OLAP) and DSS. The method of creating a data warehouse is then shown, changing the data in the data warehouse into a multidimensional data cube and integrating the data warehouse with a DSS. Finally, an application example is given to illustrate the use of the Construction Management Decision Support System (CMDSS) developed in this study. Integration of a data warehouse and a DSS can enable the right data to be tracked down and provides the required information in a direct, rapid and meaningful way. Construction managers can view data from various perspectives with significantly reduced query time, thus making decisions faster and more comprehensive. The applications of a data warehousing integrated with a DSS in construction management practice are seen to have considerable potential.

AdaBoost has attracted much attention in the machine learning community because of its excellent performance in combining weak classifiers into strong classifiers. However, AdaBoost tends to overfit to the noisy data in many applications. Accordingly, improving the antinoise ability of AdaBoost plays an important role in many applications. The sensitiveness to the noisy data of AdaBoost stems from the exponential loss function, which puts unrestricted penalties to the misclassified samples with very large margins. In this paper, we propose two boosting algorithms, referred to as RBoost1 and RBoost2, which are more robust to the noisy data compared with AdaBoost. RBoost1 and RBoost2 optimize a nonconvex loss function of the classification margin. Because the penalties to the misclassified samples are restricted to an amount less than one, RBoost1 and RBoost2 do not overfocus on the samples that are always misclassified by the previous base learners. Besides the loss function, at each boosting iteration, RBoost1 and RBoost2 use numerically stable ways to compute the base learners. These two improvements contribute to the robustness of the proposed algorithms to the noisy training and testing samples. Experimental results on the synthetic Gaussian data set, the UCI data sets, and a real malware behavior data set illustrate that the proposed RBoost1 and RBoost2 algorithms perform better when the training data sets contain noisy data.