Zhiwei Deng

Learn More
This paper presents a deep neural-network-based hierarchical graphical model for individual and group activity recognition in surveillance scenes. Deep networks are used to recognize the actions of individual people in a scene. Next, a neural-network-based hierarchical graphical model refines the predicted labels for each class by considering dependencies(More)
Human action categories exhibit significant intra-class variation. Changes in viewpoint, human appearance, and the temporal evolution of an action confound recognition algorithms. In order to address this, we present an approach to discover action primitives, sub-categories of action classes, that allow us to model this intra-class variation. We learn(More)
Rich semantic relations are important in a variety of visual recognition problems. As a concrete example, group activity recognition involves the interactions and relative spatial relations of a set of people in a scene. State of the art recognition methods center on deep learning approaches for training highly effective, complex classifiers for(More)
In group activity recognition, the temporal dynamics of the whole activity can be inferred based on the dynamics of the individual people representing the activity. We build a deep model to capture these dynamics based on LSTM (long short-term memory) models. To make use of these observations , we present a 2-stage deep temporal model for the group activity(More)
Chemical examination of a Chinese soft coral Lobophytum pauciflorum resulted in the isolation of five new biscembranoids named lobophytones O-S (1-5) and a new "monomeric" cembrane lobophytone T (6). The structures of the new compounds were elucidated by interpretation of 1D and 2D NMR (COSY, HSQC, HMBC, and NOESY) spectroscopic data in association with MS(More)
Two new jaspamide derivatives 2 and 3, together with the parent compound jaspamide (1) have been isolated from the marine sponge Jaspis splendens collected in Kalimantan (Indonesia). The structures of the new compounds were unambiguously elucidated based on 1D and 2D NMR spectral data, mass spectrometry and comparison with jaspamide (1). The new derivatives(More)
Chemical examination of the green alga Cladophora fascicularis resulted in the isolation and characterization of a new porphyrin derivative, porphyrinolactone (1), along with five known phaeophytins 2-6 and fourteen sterols and cycloartanes. The structure of 1 was determined on the basis of spectroscopic analyses and by comparison of its NMR data with those(More)
—In this paper we present an approach for classifying the activity performed by a group of people in a video sequence. This problem of group activity recognition can be addressed by examining individual person actions and their relations. Temporal dynamics exist both at the level of individual person actions as well as at the level of group activity. Given(More)
Monitoring physical training is important for the health and performance of athletes, and real-time assessment of fatigue is crucial to improve training efficiency. The relationship between key biomarkers and exercise has been reported. The aim of this study was to determine the effects of different levels of training exercises on the urine metabolome. (1)H(More)
Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with fine-grained labels that describe major components, coarse-grained labels that depict high level abstraction, or a set of labels that reveal attributes. Such categorization at different(More)