RESUMEN
Information retrieval across multiple modes has attracted much attention from academics and practitioners. One key challenge of cross-modal retrieval is to eliminate the heterogeneous gap between different patterns. Most of the existing methods tend to jointly construct a common subspace. However, very little attention has been given to the study of the importance of different fine-grained regions of various modalities. This lack of consideration significantly influences the utilization of the extracted information of multiple modalities. Therefore, this study proposes a novel text-image cross-modal retrieval approach that constructs a dual attention network and an enhanced relation network (DAER). More specifically, the dual attention network tends to precisely extract fine-grained weight information from text and images, while the enhanced relation network is used to expand the differences between different categories of data in order to improve the computational accuracy of similarity. The comprehensive experimental results on three widely-used major datasets (i.e., Wikipedia, Pascal Sentence, and XMediaNet) show that our proposed approach is effective and superior to existing cross-modal retrieval methods.
RESUMEN
The complete mitochondrial genome of Ypthima baldus was determined and analysed for the first time. It is a circular molecule of 15,304 bp in length and contains 13 protein-coding genes (PCGs), 2 rRNA genes (12S and 16S), 22 tRNA genes (tRNAs), and 1 AT-rich region. The total base composition is 38.6% of A, 7.5% of G, 42.2% of T, and 11.7% of C, respectively. In addition, phylogenetic analysis was carried out with 13 PCGs using the Bayesian Inference (BI) method. The complete mitogenome of Y. baldus will play an important role in population genetics and phylogenetic studies of the species in the future.
RESUMEN
OBJECTIVE: To study the chemical constituents of Mosla chinensis 'jiangxiangru'. METHODS: The chemical components were isolated and purified by silica gel and Sephadex LH-20 column chromatography. The chemical structures were elucidated on the basis of physic chemical properties and spectral data. RESULTS: Five compounds have been isolated from Mosla chinensis 'jiangxiangru'. On the basis of spectral analysis and physicochemical properties, the compounds were identified as negletein (I), luteolin (II), quercetin (III), chrysoeriol (IV) and apigenin (V). CONCLUSION: Compounds I-V are obtained from the genus for the first time.