The Chinese University of Hong Kong

About: The Chinese University of Hong Kong is a education organization based out in Hong Kong, China. It is known for research contribution in the topics: Population & Cancer. The organization has 43411 authors who have published 93672 publications receiving 3066651 citations.

Joint Detection and Identification Feature Learning for Person Search

Abstract: Existing person re-identification benchmarks and methods mainly focus on matching cropped pedestrian images between queries and candidates. However, it is different from real-world scenarios where the annotations of pedestrian bounding boxes are unavailable and the target person needs to be searched from a gallery of whole scene images. To close the gap, we propose a new deep learning framework for person search. Instead of breaking it down into two separate tasks—pedestrian detection and person re-identification, we jointly handle both aspects in a single convolutional neural network. An Online Instance Matching (OIM) loss function is proposed to train the network effectively, which is scalable to datasets with numerous identities. To validate our approach, we collect and annotate a large-scale benchmark dataset for person search. It contains 18,184 images, 8,432 identities, and 96,143 pedestrian bounding boxes. Experiments show that our framework outperforms other separate approaches, and the proposed OIM loss function converges much faster and better than the conventional Softmax loss.

miRTarBase update 2014: an information resource for experimentally validated miRNA-target interactions

Abstract: MicroRNAs (miRNAs) are small non-coding RNA molecules capable of negatively regulating gene expression to control many cellular mechanisms. The miRTarBase database (http://mirtarbase.mbc.nctu.edu.tw/) provides the most current and comprehensive information of experimentally validated miRNA-target interactions. The database was launched in 2010 with data sources for >100 published studies in the identification of miRNA targets, molecular networks of miRNA targets and systems biology, and the current release (2013, version 4) includes significant expansions and enhancements over the initial release (2010, version 1). This article reports the current status of and recent improvements to the database, including (i) a 14-fold increase to miRNA-target interaction entries, (ii) a miRNA-target network, (iii) expression profile of miRNA and its target gene, (iv) miRNA target-associated diseases and (v) additional utilities including an upgrade reminder and an error reporting/user feedback system.

Sequence variants affecting eosinophil numbers associate with asthma and myocardial infarction.

Abstract: Eosinophils are pleiotropic multifunctional leukocytes involved in initiation and propagation of inflammatory responses and thus have important roles in the pathogenesis of inflammatory diseases. Here we describe a genome-wide association scan for sequence variants affecting eosinophil counts in blood of 9,392 Icelanders. The most significant SNPs were studied further in 12,118 Europeans and 5,212 East Asians. SNPs at 2q12 (rs1420101), 2q13 (rs12619285), 3q21 (rs4857855), 5q31 (rs4143832) and 12q24 (rs3184504) reached genome-wide significance (P = 5.3 x 10(-14), 5.4 x 10(-10), 8.6 x 10(-17), 1.2 x 10(-10) and 6.5 x 10(-19), respectively). A SNP at IL1RL1 associated with asthma (P = 5.5 x 10(-12)) in a collection of ten different populations (7,996 cases and 44,890 controls). SNPs at WDR36, IL33 and MYB that showed suggestive association with eosinophil counts were also associated with atopic asthma (P = 4.2 x 10(-6), 2.2 x 10(-5) and 2.4 x 10(-4), respectively). We also found that a nonsynonymous SNP at 12q24, in SH2B3, associated significantly (P = 8.6 x 10(-8)) with myocardial infarction in six different populations (6,650 cases and 40,621 controls).

Face Photo-Sketch Synthesis and Recognition

Abstract: In this paper, we propose a novel face photo-sketch synthesis and recognition method using a multiscale Markov Random Fields (MRF) model. Our system has three components: 1) given a face photo, synthesizing a sketch drawing; 2) given a face sketch drawing, synthesizing a photo; and 3) searching for face photos in the database based on a query sketch drawn by an artist. It has useful applications for both digital entertainment and law enforcement. We assume that faces to be studied are in a frontal pose, with normal lighting and neutral expression, and have no occlusions. To synthesize sketch/photo images, the face region is divided into overlapping patches for learning. The size of the patches decides the scale of local face structures to be learned. From a training set which contains photo-sketch pairs, the joint photo-sketch model is learned at multiple scales using a multiscale MRF model. By transforming a face photo to a sketch (or transforming a sketch to a photo), the difference between photos and sketches is significantly reduced, thus allowing effective matching between the two in face sketch recognition. After the photo-sketch transformation, in principle, most of the proposed face photo recognition approaches can be applied to face sketch recognition in a straightforward way. Extensive experiments are conducted on a face sketch database including 606 faces, which can be downloaded from our Web site (http://mmlab.ie.cuhk.edu.hk/facesketch.html).

Interpreting TF-IDF term weights as making relevance decisions

Abstract: A novel probabilistic retrieval model is presented It forms a basis to interpret the TF-IDF term weights as making relevance decisions It simulates the local relevance decision-making for every location of a document, and combines all of these “local” relevance decisions as the “document-wide” relevance decision for the document The significance of interpreting TF-IDF in this way is the potential to: (1) establish a unifying perspective about information retrieval as relevance decision-making; and (2) develop advanced TF-IDF-related term weights for future elaborate retrieval models Our novel retrieval model is simplified to a basic ranking formula that directly corresponds to the TF-IDF term weights In general, we show that the term-frequency factor of the ranking formula can be rendered into different term-frequency factors of existing retrieval systems In the basic ranking formula, the remaining quantity - log p(r¯|t ∈ d) is interpreted as the probability of randomly picking a nonrelevant usage (denoted by r¯) of term t Mathematically, we show that this quantity can be approximated by the inverse document-frequency (IDF) Empirically, we show that this quantity is related to IDF, using four reference TREC ad hoc retrieval data collections