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 & Computer science. The organization has 43411 authors who have published 93672 publications receiving 3066651 citations.

Local Derivative Pattern Versus Local Binary Pattern: Face Recognition With High-Order Local Pattern Descriptor

Abstract: This paper proposes a novel high-order local pattern descriptor, local derivative pattern (LDP), for face recognition. LDP is a general framework to encode directional pattern features based on local derivative variations. The nth-order LDP is proposed to encode the (n-1)th -order local derivative direction variations, which can capture more detailed information than the first-order local pattern used in local binary pattern (LBP). Different from LBP encoding the relationship between the central point and its neighbors, the LDP templates extract high-order local information by encoding various distinctive spatial relationships contained in a given local region. Both gray-level images and Gabor feature images are used to evaluate the comparative performances of LDP and LBP. Extensive experimental results on FERET, CAS-PEAL, CMU-PIE, Extended Yale B, and FRGC databases show that the high-order LDP consistently performs much better than LBP for both face identification and face verification under various conditions.

Abnormal Event Detection at 150 FPS in MATLAB

Abstract: Speedy abnormal event detection meets the growing demand to process an enormous number of surveillance videos. Based on inherent redundancy of video structures, we propose an efficient sparse combination learning framework. It achieves decent performance in the detection phase without compromising result quality. The short running time is guaranteed because the new method effectively turns the original complicated problem to one in which only a few costless small-scale least square optimization steps are involved. Our method reaches high detection rates on benchmark datasets at a speed of 140-150 frames per second on average when computing on an ordinary desktop PC using MATLAB.

Explaining International and Intertemporal Variations in Income Inequality

Abstract: This paper explores the propositions that, income inequality is relatively stable within countries; and that it varies significantly among countries. A new and expanded data set provides broad support for both propositions. Drawing on a political economy and capital market imperfection arguments to explain the intertemporal and international variation in inequality, the empirical analysis shows that the predicted variables associated with the first argument (a measure of civil liberties and the initial level of secondary schooling) and the second argument (a measure of financial depth and the initial distribution of land) are indeed important determinants of inequality. This paper explores two propositions regarding income inequality. They are: first, income inequality is relatively stable within countries; and second, it varies significantly across countries.' To illustrate, note that the Gini coefficient in India remained almost constant for forty years (1951-92) with mean 32.6 and standard deviation 2.0.2 In contrast, the variation in Gini coefficients across countries is large: 61.9 in Honduras in 1968 compared with 17.8 in Bulgaria in 1976. If substantiated, these propositions have potentially significant implications for poverty. The significance of the first is obvious - barring any fundamental socio-political change, poverty reduction will depend crucially on the rate of economic growth. Given this, the significance of the second is that in inegalitarian economies the poor will enjoy a smaller share of any national increment in income than in more egalitarian ones. Drawing on a new and expanded data set on inequality (Deininger and Squire, 1996a), the first of the paper's three sections conducts standard statistical tests of the two propositions. The sample comprises 573 observations on the most common measure of inequality - the Gini coefficient - for 49 developed and developing countries covering the period 1947-94. The results broadly confirm our two propositions. Specifically, analysis of variance (ANOVA) shows that about 90% of the total variance in the Gini coefficients