Learn 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)
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)
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)
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)
Optimized scale factors for calculating vibrational harmonic and fundamental frequencies and zero-point energies have been determined for 145 electronic model chemistries, including 119 based on approximate functionals depending on occupied orbitals, 19 based on single-level wave function theory, three based on the neglect-of-diatomic-differential-overlap,(More)
We present a perspective on the use of diffuse basis functions for electronic structure calculations by density functional theory and wave function theory. We especially emphasize minimally augmented basis sets and calendar basis sets. We base our conclusions on our previous experience with commonly computed quantities, such as bond energies, barrier(More)
Thirty four density functional approximations are tested against two diverse databases, one with 18 bond energies and one with 24 barriers. These two databases are chosen to include bond energies and barrier heights which are relevant to catalysis, and in particular the bond energy database includes metal-metal bonds, metal-ligand bonds, alkyl bond(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)
Complex molecules often have many structures (conformations) of the reactants and the transition states, and these structures may be connected by coupled-mode torsions and pseudorotations; some but not all structures may have hydrogen bonds in the transition state or reagents. A quantitative theory of the reaction rates of complex molecules must take(More)
Thirty-four density functional approximations are tested against two diverse databases, one with 18 bond energies and one with 24 barriers. These two databases are chosen to include bond energies and barrier heights which are relevant to catalysis, and in particular the bond energy database includes metal-metal bonds, metal-ligand bonds, alkyl bond(More)