Learn More
This paper introduces a web image search reranking approach that explores multiple modalities in a graph-based learning scheme. Different from the conventional methods that usually adopt a single modality or integrate multiple modalities into a long feature vector, our approach can effectively integrate the learning of relevance scores, weights of(More)
Hedgehogs (Hhs) are key signaling regulators of stem cell maintenance and tissue patterning in embryos, and activating mutations in the pathway that increase Gli transcriptional activity are causal in a diversity of cancers. Here, we report that phosphoinositide 3-kinase (PI3-kinase)-dependent Akt activation is essential for Sonic Hedgehog (Shh) signaling(More)
Researchers have proposed various machine learning algorithms for traffic sign recognition, which is a supervised multicategory classification problem with unbalanced class frequencies and various appearances. We present a novel graph embedding algorithm that strikes a balance between local manifold structures and global discriminative information. A novel(More)
Methods used to strengthen metals generally also cause a pronounced decrease in electrical conductivity, so that a tradeoff must be made between conductivity and mechanical strength. We synthesized pure copper samples with a high density of nanoscale growth twins. They showed a tensile strength about 10 times higher than that of conventional coarse-grained(More)
Weakly-supervised image segmentation is a challenging problemwith multidisciplinary applications in multimedia content analysis and beyond. It aims to segment an image by leveraging its image-level semantics (i.e., tags). This paper presents a weakly-supervised image segmentation algorithm that learns the distribution of spatially structural superpixel sets(More)
Binary hashing has been widely used for efficient similarity search due to its query and storage efficiency. In most existing binary hashing methods, the high-dimensional data are embedded into Hamming space and the distance or similarity of two points are approximated by the Hamming distance between their binary codes. The Hamming distance calculation is(More)
Polymorphisms in DNA repair and apoptosis genes are suspected to alter the individual susceptibility to develop lung cancer. We investigated the relationship between polymorphisms in ATM (A60G), ERCC1 (Asn118Asn), APE1 (Asn148Glu) and iASPP (A67T) and the risk of developing lung cancer. A case-control study was conducted with 315 patients with lung cancer(More)
Mice have proved to be a powerful model organism for understanding obesity in humans. Single gene mutants and genetically modified mice have been used to identify obesity genes, and the discovery of loci for polygenic forms of obesity in the mouse is an important next step. To pursue this goal, the inbred mouse strains 129P3/J (129) and C57BL/6ByJ (B6),(More)
The most important animal reservoirs of Schistosoma japonicum in China are bovines. Diagnosis and control of bovine schistosomiasis is critical for reducing the prevalence of the disease. We screened defined diagnostic antigens that have the potential to increase the sensitivity and specificity of serological assays and to distinguish between active and(More)