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.

Realtime and Robust Hand Tracking from Depth

Abstract: We present a realtime hand tracking system using a depth sensor. It tracks a fully articulated hand under large viewpoints in realtime (25 FPS on a desktop without using a GPU) and with high accuracy (error below 10 mm). To our knowledge, it is the first system that achieves such robustness, accuracy, and speed simultaneously, as verified on challenging real data. Our system is made of several novel techniques. We model a hand simply using a number of spheres and define a fast cost function. Those are critical for realtime performance. We propose a hybrid method that combines gradient based and stochastic optimization methods to achieve fast convergence and good accuracy. We present new finger detection and hand initialization methods that greatly enhance the robustness of tracking.

Reversible Cerebral Vasoconstriction Syndromes: Analysis of 139 Cases

Abstract: Objectives To compare the clinical, laboratory, and imaging features of patients with reversible cerebral vasoconstriction syndromes evaluated at 2 academic centers, compare subgroups, and investigate treatment effects. Design Retrospective analysis. Setting Massachusetts General Hospital (n = 84) or Cleveland Clinic (n = 55). Patients One hundred thirty-nine patients with reversible cerebral vasoconstriction syndromes. Main Outcome Measures Clinical, laboratory, and imaging features; treatment; and outcomes. Results The mean age was 42.5 years, and 81% were women. Onset with thunderclap headache was documented in 85% and 43% developed neurological deficits. Prior migraine was documented in 40%, vasoconstrictive drug exposure in 42%, and recent pregnancy in 9%. Admission computed tomography or magnetic resonance imaging was normal in 55%; however, 81% ultimately developed brain lesions including infarcts (39%), convexity subarachnoid hemorrhage (34%), lobar hemorrhage (20%), and brain edema (38%). Cerebral angiographic abnormalities typically normalized within 2 months. Nearly 90% had good clinical outcome; 9% developed severe deficits; and 2% died. In the combined cohort, calcium channel blocker therapy and symptomatic therapy alone showed no significant effect on outcome; however, glucocorticoid therapy showed a trend for poor outcome (P = .08). Subgroup comparisons based on prior headache status and identified triggers (vasoconstrictive drugs, pregnancy, other) showed no major differences. Conclusion Patients with reversible cerebral vasoconstriction syndromes have a unique set of clinical imaging features, with no significant differences between subgroups. Prospective studies are warranted to determine the effects of empirical treatment with calcium channel blockers and glucocorticoids.

Photo and Video Quality Evaluation: Focusing on the Subject

Abstract: Traditionally, distinguishing between high quality professional photos and low quality amateurish photos is a human task. To automatically assess the quality of a photo that is consistent with humans perception is a challenging topic in computer vision. Various differences exist between photos taken by professionals and amateurs because of the use of photography techniques. Previous methods mainly use features extracted from the entire image. In this paper, based on professional photography techniques, we first extract the subject region from a photo, and then formulate a number of high-level semantic features based on this subject and background division. We test our features on a large and diverse photo database, and compare our method with the state of the art. Our method performs significantly better with a classification rate of 93% versus 72% by the best existing method. In addition, we conduct the first study on high-level video quality assessment. Our system achieves a precision of over 95% in a reasonable recall rate for both photo and video assessments. We also show excellent application results in web image search re-ranking.

Detect Rumors Using Time Series of Social Context Information on Microblogging Websites

Abstract: Automatically identifying rumors from online social media especially microblogging websites is an important research issue. Most of existing work for rumor detection focuses on modeling features related to microblog contents, users and propagation patterns, but ignore the importance of the variation of these social context features during the message propagation over time. In this study, we propose a novel approach to capture the temporal characteristics of these features based on the time series of rumor's lifecycle, for which time series modeling technique is applied to incorporate various social context information. Our experiments using the events in two microblog datasets confirm that the method outperforms state-of-the-art rumor detection approaches by large margins. Moreover, our model demonstrates strong performance on detecting rumors at early stage after their initial broadcast.