Learn More
In real-world action recognition problems, low-level features cannot adequately characterize the rich spatial-temporal structures in action videos. In this work, we encode actions based on attributes that describes actions as high-level concepts e.g., jump forward or motion in the air. We base our analysis on two types of action attributes. One type of(More)
Discriminative appearance features are effective for recognizing actions in a fixed view, but generalize poorly to changes in viewpoint. We present a method for view-invariant action recognition based on sparse representations using a transferable dictionary pair. A transferable dictionary pair consists of two dictionaries that correspond to the source and(More)
Domain adaptation algorithms that handle shifts in the distribution between training and testing data are receiving much attention in computer vision. Recently, a Grassmann manifold-based domain adaptation algorithm that models the domain shift using intermediate subspaces along the geodesic connecting the source and target domains was presented in [6]. We(More)
We present an approach to jointly learn a set of view-specific dictionaries and a common dictionary for cross-view action recognition. The set of view-specific dictionaries is learned for specific views while the common dictionary is shared across different views. Our approach represents videos in each view using both the corresponding view-specific(More)
The diverse barrier height database DBH24 is updated by using W4 and W3.2 data (Karton, A.; Tarnopolsky, A.; Lamère, J.-F.; Schatz, G. C.; Martin, J. M. L. J. Phys. Chem. A 2008, 112, 12868) to replace previous W1 values; we call the new database DBH24/08. We used the new database to assess 348 model chemistries, each consisting of a combination of a wave(More)
Domain adaptation algorithms aim at handling the shift between source and target domains. A classifier is trained on images from the source domain; and the classifier recognizes objects in images from the target domain. In this paper, we present a joint subspace and dictionary learning framework for domain adaptation. Our approach simultaneously exploits(More)
BACKGROUND Recepteur d'origine nantais (RON) is a receptor tyrosine kinase that is activated by a serum-derived, macrophage stimulating protein (MSP) growth factor and is expressed in many malignant tumors. The aim of the present study was to reveal the protein expression profile of RON and its relationship with clinicopathological characteristics of(More)
Inflammation is a prominent feature of CNS injury that heavily influences neuronal survival, yet the signals that initiate and control it remain poorly understood. Here we identify the nuclear alarmin, interleukin (IL)-33, as an important regulator of the innate immune response after CNS injury. IL-33 is expressed widely throughout the healthy brain and is(More)
PURPOSE Kashin-Beck disease (KBD) is an endemic degenerative osteoarthritis associated with extracellular matrix degradation. The aim of this investigation was to evaluate the role of targeting genes in the pathogenesis of KBD and primary osteoarthritis (OA) involved in extracellular matrix degradation. METHODS Agilent 44 K human whole-genome(More)