Learn 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)
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)
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)
Event understanding in videos is a key element of computer vision systems in the context of visual surveillance, human-computer interaction, sports interpretation, and video search and retrieval. The standard and yet state-of-the-art pipeline for activity recognition and interaction description consists of extracting hand-crafted local feature descriptors(More)
The chemical composition of the essential oil obtained by hydrodistillation from the aerial parts of Mentha haplocalyx was investigated by GC-FID and GC/MS analyses. In sum, 23 components, representing 92.88% of the total oil composition, were identified, and the main compounds were found to be menthol (59.71%), menthyl acetate (7.83%), limonene (6.98%),(More)
Essential oil extracted from nutmeg seeds (Myristica fragrans Houtt.) by hydrodistillation was subjected to GC/MS and GC analysis. A total of 27 constituents were identified, of which eugenol (19.9%), methylisoeugenol (16.8%), methyleugenol (16.7%), sabinene (11.8%), and terpinen-4-ol (8.5%) were the major components. The essential oil was tested against(More)
The aim of this research was to determine chemical composition and insecticidal activity of the essential oil of Illicium pachyphyllum fruits against two grain storage insects, Sitophilus zeamais and Tribolium castaneum, and to isolate any insecticidal constituents from the essential oil. The essential oil of I. pachyphyllum fruits was obtained by(More)
Chemical examination of the soft coral Sinularia rigida resulted in the isolation of 12 new cembranoids, namely, sinulariols T-Z5 (1-12), together with a known analogue, 13. Their structures were determined on the basis of 1D and 2D NMR (COSY, HSQC, HMBC, and NOESY) spectroscopic analyses in association with MS and IR data. Compounds 7 and 13 showed potent(More)
Semantic segmentation requires a detailed labeling of image pixels by object category. Information derived from local image patches is necessary to describe the detailed shape of individual objects. However, this information is ambiguous and can result in noisy labels. Global inference of image content can instead capture the general semantic concepts(More)
We develop a novel framework for action localization in videos. We propose the Tube Proposal Network (TPN), which can generate generic, class-independent, video-level tubelet proposals in videos. The generated tubelet proposals can be utilized in various video analysis tasks, including recognizing and localizing actions in videos. In particular, we(More)