The number of granted patents is rapidly growing because of strong business competition. For decision-makers in enterprises, it is necessary to understand the patent evolutions as soon as possible. Thus, how to discov...
详细信息
ISBN:
(纸本)9781943436040
The number of granted patents is rapidly growing because of strong business competition. For decision-makers in enterprises, it is necessary to understand the patent evolutions as soon as possible. Thus, how to discover the patent evolutions from patent databases and generate a vivid presentation on them are becoming important. In this study, a patent relationship discovery method was employed to organize the topics of patents in temporal order. A new multi-document summarization method based on graph algorithm was proposed to conduct a summarization analysis for automatically extracting key-phrases from several granted patent documents. The proposed methodology was evaluated using the dataset Wireless Communication Network (encoded with H04W) from granted patents under section G (physics) of United States Patent and Trademark Office (USPTO). The experimental results show that the proposed methodology can obtain more effective results than other methods for extracting keywords and helping users discovering critical techniques. Copyright ISCA, CAINE 2016.
Topological insulators (TIs) provide a fascinating example where strong spin-orbit interaction leads to the formation of spin-momentum-locked (topological) surface states,[1,2] and are anticipated to mediate superior ...
详细信息
This paper presents an end-to-end neural network model, named Neural Generative Question Answering (GENQA), that can generate answers to simple factoid questions, based on the facts in a knowledge-base. More specifica...
详细信息
This paper presents an end-to-end neural network model, named Neural Generative Question Answering (GENQA), that can generate answers to simple factoid questions, based on the facts in a knowledge-base. More specifically, the model is built on the encoder-decoder framework for sequence-to-sequence learning, while equipped with the ability to enquire the knowledge-base, and is trained on a corpus of question-answer pairs, with their associated triples in the knowledge-base. Empirical study shows the proposed model can effectively deal with the variations of questions and answers, and generate right and natural answers by referring to the facts in the knowledge-base. The experiment on question answering demonstrates that the proposed model can outperform an embedding-based QA model as well as a neural dialogue model trained on the same data.
The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion. Whil...
详细信息
The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion. While a large number of distance metric/subspace learning models have been developed for re-id, the cross-view transformations they learned are view-generic and thus potentially less effective in quantifying the feature distortion inherent to each camera view. Learning view-specific feature transformations for re-id (i.e., view-specific re-id), an under-studied approach, becomes an alternative resort for this problem. In this work, we formulate a novel view-specific person re-identification framework from the feature augmentation point of view, called Camera coRrelation Aware Feature augmenTation (CRAFT). Specifically, CRAFT performs cross-view adaptation by automatically measuring camera correlation from cross-view visual data distribution and adaptively conducting feature augmentation to transform the original features into a new adaptive space. Through our augmentation framework, view-generic learning algorithms can be readily generalized to learn and optimize view-specific sub-models whilst simultaneously modelling view-generic discrimination information. Therefore, our framework not only inherits the strength of view-generic model learning but also provides an effective way to take into account view specific characteristics. Our CRAFT framework can be extended to jointly learn view-specific feature transformations for person re-id across a large network with more than two cameras, a largely under-investigated but realistic re-id setting. Additionally, we present a domain-generic deep person appearance representation which is designed particularly to be towards view invariant for facilitating cross-view adaptation by CRAFT. We conducted extensively comparative experiments to validate the superiority and advantages of our proposed framework over state-of
Quantum cryptography is information-theoretically secure owing to its solid basis in quantum mechanics. However, generally, initial implementations with practical imperfections might open loopholes, allowing an eavesd...
详细信息
Automatic segmentation of left ventricle (LV) myocardium in cardiac short-axis cine MR images acquired on subjects with myocardial infarction is a challenging task, mainly because of the various types of image inhomog...
详细信息
Two additions impacting tables 3 and 4 in ref. [1] are presented in the following. No significant impact is found for other results or figures in ref. [1].
Two additions impacting tables 3 and 4 in ref. [1] are presented in the following. No significant impact is found for other results or figures in ref. [1].
Very large data sets within the range of megabytes to terabytes generated daily from checkpoint-and- restart processes are seen in today's scientific simulations. Reliability and durability are two important facto...
详细信息
暂无评论