Learn More
Highlights: 1. A deep CNN to rank photo aesthetics with pairwse rank loss 2. Joint learning of meaningful photographic attributes and image content cues which help regularize the complicated photo aesthetics rating problem 3. A new aesthetics and attributes dataset (AADB) containing aesthetic scores and meaningful attributes assigned to each image by(More)
BACKGROUND Human embryonic stem cell (hESC) lines derived from poor quality embryos usually have either normal or abnormal karyotypes. However, it is still unclear whether their biological characteristics are similar. METHODS Seven new hESC lines were established using discarded embryos. Five cell lines had normal karyotype, one was with an unbalanced(More)
To tackle the problem of saliency detection in images, we propose to learn adaptive mid-level features to represent image local information, and present an efficient way to calculate multi-scale and multi-level saliency maps. With the simple k-means algorithm, we learn adaptive low-level filters to convolve the image to produce response maps as the(More)
We now know that mid-level features can greatly enhance the performance of image learning, but how to automatically learn the image features efficiently and in an unsupervised manner is still an open question. In this paper, we present a very efficient mid-level feature learning approach (Mid-Fea), which only involves simple operations such as k-means(More)
4 Principal component analysis (PCA) suffers from the fact that each principal component (PC) is a linear combination 5 of all the original variables, thus it is difficult to interpret the results. For this reason, sparse PCA (sPCA), which 6 produces modified PCs with sparse loadings, arises to clear away this interpretation puzzlement. However, as a result(More)
In this paper, we propose an unsupervised cluster method via a multi-task learning strategy, called Mt-Cluster. Our MtCluster learns a cluster-specific dictionary for each cluster to represent its sample signals and a shared common pattern pool (the commonality) for the essentially complemental representation. By treating learning the cluster-specific(More)