Search

Cross-modal hashing has received increasing research attentions due to its less storage and efficient retrieval. However, most existing cross-modal hashing methods focus only on exploring multi-modal information, while underestimate the significance of local and Euclidean structure information on the hashing learning procedure. In this paper, we propose a supervised discrete-based cross-modal hashing method, named Scalable Discriminative Discrete Hashing (SDDH), for cross-modal retrieval, where 1) the discrete hash codes are directly obtained by multi-modal features and semantic labels so that the quantization errors are dramatically reduced, and 2) the discrete hash codes simultaneously preserve the heterogeneous similarity and manifold information in the original space by employing matrix factoring with orthogonal and balanced constraints. Moreover, an efficient optimization is introduced to tackle the discrete solution, which makes the SDDH scalable to large-scale cross-modal retrieval. Empirical results on three widely-used benchmark databases clearly demonstrate the effectiveness and efficiency of the proposed method in comparison with state-of-the-arts.

Hashing has been widely studied for cross-modal retrieval due to its promising efficiency and effectiveness in massive data analysis. However, most existing supervised hashing has the limitations of inefficiency for very large-scale search and intractable discrete constraint for hash codes learning. In this paper, we propose a new supervised hashing method, namely, Discrete Semantic Matrix Factorization Hashing (DSMFH), for cross-modal retrieval. First, we conduct the matrix factorization via directly utilizing the available label information to obtain a latent representation, so that both the inter-modality and intra-modality similarities are well preserved. Then, we simultaneously learn the discriminative hash codes and corresponding hash functions by deriving the matrix factorization into a discrete optimization. Finally, we adopt an alternatively iterative procedure to efficiently optimize the matrix factorization and discrete learning. Extensive experimental results on three widely used image-tag databases demonstrate the superiority of the DSMFH over state-of-the-art cross-modal hashing methods.

3D palmprint-based biometric recognition has drawn growing research attention due to its several merits over 2D counterpart such as robust structural measurement of a palm surface and high anti-counterfeiting capability. However, most existing 3D palmprint descriptors are hand-crafted that usually extract stationary features from 3D palmprint images. In this paper, we propose a feature learning method to jointly learn compact curvature feature descriptor for 3D palmprint recognition. We first form multiple curvature data vectors to completely sample the intrinsic curvature information of 3D palmprint images. Then, we jointly learn a feature projection function that project curvature data vectors into binary feature codes, which have the maximum inter-class variances and minimum intra-class distance so that they are discriminative. Moreover, we learn the collaborative binary representation of the multiple curvature feature codes by minimizing the information loss between the final representation and the multiple curvature features, so that the proposed method is more compact in feature representation and efficient in matching. Experimental results on the baseline 3D palmprint database demonstrate the superiority of the proposed method in terms of recognition performance in comparison with state-of-the-art 3D palmprint descriptors.

Social media network is inseparable from image recognition, and image super-resolution (SR) reconstruction plays an important role in image recognition. The changes of scale and geometry are rarely considered in the image super-resolution reconstruction based on deep learning over the years, we introduce a super-resolution reconstruction network based on deformable convolutional network. We replace the ordinary convolution with the deformable convolution to pretend the geometric deformation and extract abundant local features. The image super-resolution reconstruction is usually based on the conventional convolutional neural network (CNN). Most CNN-based SR models do not utilize the features of the original low resolution (LR) image as much as possible, resulting in lower performance. After introducing the idea of deformable convolution, though the complexity is increased, the recognition accuracy is obviously raised.

The armyworm Mythimna roseilinea (Walker) is a major pest of grain crops in South China. So far little is known about its basic biology and ecology, making prediction of population dynamics difficult. This study examined the relationships of individual development and population growth with temperature based on an age-stage, two-sex life table of M. roseilinea reared on maize in the laboratory at 18, 21, 24, 27 and 30°C. The highest values of net reproductive rate (R0) and fecundity were observed at 21 and 24°C, respectively. Both the intrinsic rate of increase (r) and finite rate of increase (λ) increased significantly and mean generation time (T) decreased significantly with increasing temperature. M. roseilinea was able to develop, survive and lay eggs at all temperature regimes tested. Development rates of the egg, larval, pupal, as well as the whole pre-oviposition stages had a positive linear relationship with temperature. The calculated development threshold temperatures of egg, larval, pupal, pre-oviposition and total pre-oviposition stages were 13.29, 8.39, 14.35, 7.42, and 12.24°C, respectively, and their effective accumulated temperatures were 63.59, 445.00, 211.11, 89.02, and 698.95 degree-days, respectively. These results provide insight into temperature-based phenology and population ecology of this insect pest and will allow population prediction and management available in the field.

The Mythimna (=Leucania) loreyi (Duponchel) has recently emerged as a major pest of grain crops in China. Little is known about its basic biology and ecology, making it difficult to predict its population dynamics. An age-stage, two-sex life table was constructed for this insect when reared on maize in the laboratory at five constant temperatures (18, 21, 24, 27, and 30 °C). Both the intrinsic rate of increase (r) and finite rate increase (λ) increased as temperature significantly increased and mean generation time (T) decreased significantly with increasing temperature. The highest values for net reproductive rate (R0) and fecundity were observed at 24 °C. However, M. loreyi was able to develop, survive, and lay eggs at all temperatures tested (18-30 °C). Development rates at different temperatures for the egg, larval, pupal, as well as for a total preoviposition period, fit a linear equation. The lower threshold temperatures of egg, larval, pupal, preoviposition, and total preoviposition period were 8.83, 10.95, 11.67, 9.30, and 9.65 °C, respectively. And their effective accumulated temperatures were 87.64, 298.51, 208.33, 66.47, and 729.93 degree-days, respectively. This study provides insight into the temperature-based phenology and population ecology in M. loreyi. The results will benefit population dynamics monitoring, prediction, and management of this insect pest in the field.

Background/Aims: To investigate the downregulation of microRNA (miR)-10b in clear cell renal cell carcinoma (ccRCC) and its mechanistic involvement in tumourigenesis. Methods: The relative expression of miR-10b in ccRCC samples were determined by real-time PCR. Exogenous expression and knockdown of endogenous miR-10b were performed by transfection with indicated plasmids into 786-0 cells. Cell proliferation was evaluated using Cell Counting Kit-8 assay. Cell apoptosis was analyzed by Annexin V/propidium iodide staining. MAPK pathway activation was detected by western blotting with indicated antibodies. Results: We confirmed the downregulation of miR-10b in ccRCC tumour. The forced expression of miR-10b inhibited cell proliferation in 786-0 cells. Moreover, miR-10b stimulated apoptosis in 786-0 cells, which was abrogated by specific miR-10b inhibitor. We further elucidated that the apoptosis induction was mediated by the JNK pathway activation. We consolidated this observation by combinational treatment with JNK specific inhibitor, which was shown to completely impede miR-10b elicited apoptosis. Conclusion: We suggested a tumour suppressor function of miR-10b in tumourigenesis of ccRCC via proliferation suppression and apoptosis induction, and the latter was mediated by the JNK pathway activation.