Learn More
A novel framework for anomaly detection in crowded scenes is presented. Three properties are identified as important for the design of a localized video representation suitable for anomaly detection in such scenes: 1) joint mod-eling of appearance and dynamics of the scene, and the abilities to detect 2) temporal, and 3) spatial abnormalities. The model for(More)
The problem of adaptively selecting pooling regions for the classification of complex video events is considered. Complex events are defined as events composed of several characteristic behaviors, whose temporal configuration can change from sequence to sequence. A dynamic pooling operator is defined so as to enable a unified solution to the problems of(More)
The detection and localization of anomalous behaviors in crowded scenes is considered, and a joint detector of temporal and spatial anomalies is proposed. The proposed detector is based on a video representation that accounts for both appearance and dynamics, using a set of mixture of dynamic textures models. These models are used to implement 1) a(More)
In this paper we introduce the novel problem of understanding visual persuasion. Modern mass media make extensive use of images to persuade people to make commercial and political decisions. These effects and techniques are widely studied in the social sciences, but behavioral studies do not scale to massive datasets. Computer vision has made great strides(More)
We describe a novel and effective video enhancement algorithm for low lighting video. The algorithm works by first inverting the input low-lighting video and then applying an image de-haze algorithm on the inverted input. To facilitate faster computation and improve temporal consistency, correlations between temporally neighboring frames are utilized.(More)
In this work, we propose a novel video representation for activity recognition that models video dynamics with attributes of activities. A video sequence is decomposed into short-term segments, which are characterized by the dynamics of their attributes. These segments are modeled by a dictionary of attribute dynamics templates, which are implemented by a(More)
OBJECTIVE The goal of the present study was to evaluate the effects of bilateral deep brain stimulation (DBS) of the subthalamic nucleus (STN) on olfaction in patients with Parkinson's disease (PD). METHODS 15 patients suffering from sporadic PD-related dysosmia were implanted with bilateral electrodes aimed at the STN. One week before the surgery, odor(More)
—In this paper, we report bright, efficient Alq 3-based [tris-(8-hydroxyquinoline) aluminum] organic light-emitting diode (OLED) structures that incorporate hemispherical lenses for increased output power efficiency. The 6-layer hybrid (polymer/small molecule) OLED structure contains two spin-coated polymer layers and four thermally evaporated small(More)