Few-shot learning aims to train a classifier that can generalize well when just a small number of labeled samples per class are given. We introduce Transductive Maximum Margin Classifier (TMMC) for few-shot learning. The basic idea of the classical m
aximum margin classifier is to solve an optimal prediction function that the corresponding separating hyperplane can correctly divide the training data and the resulting classifier has the largest geometric margin. In few-shot learning scenarios, the training samples are scarce, not enough to find a separating hyperplane with good generalization ability on unseen data. TMMC is constructed using a mixture of the labeled support set and the unlabeled query set in a given task. The unlabeled samples in the query set can adjust the separating hyperplane so that the prediction function is optimal on both the labeled and unlabeled samples. Furthermore, we leverage an efficient and effective quasi-Newton algorithm, the L-BFGS method to optimize TMMC. Experimental results on three standard few-shot learning benchmarks including miniImagenet, tieredImagenet and CUB suggest that our TMMC achieves state-of-the-art accuracies.
The goal of few-shot video classification is to learn a classification model with good generalization ability when trained with only a few labeled videos. However, it is difficult to learn discriminative feature representations for videos in such a s
etting. In this paper, we propose Temporal Alignment Prediction (TAP) based on sequence similarity learning for few-shot video classification. In order to obtain the similarity of a pair of videos, we predict the alignment scores between all pairs of temporal positions in the two videos with the temporal alignment prediction function. Besides, the inputs to this function are also equipped with the context information in the temporal domain. We evaluate TAP on two video classification benchmarks including Kinetics and Something-Something V2. The experimental results verify the effectiveness of TAP and show its superiority over state-of-the-art methods.
We present an experimentally practical method to reveal Einstein-Podolsky-Rosen steering in non-Gaussian spin states by exploiting a connection to quantum metrology. Our criterion is based on the quantum Fisher information, and uses bounds derived fr
om generalized spin-squeezing parameters that involve measurements of higher-order moments. This leads us to introduce the concept of conditional spin-squeezing parameters, which quantify the metrological advantage provided by conditional states, as well as detect the presence of an EPR paradox.
The extremely large magnetoresistance (XMR) effect in nonmagnetic semimetals have attracted intensive attention recently. Here we propose an XMR candidate material SrPd based on first-principles electronic structure calculations in combination with a
semi-classical model. The calculated carrier densities in SrPd indicate that there is a good electron-hole compensation, while the calculated intrinsic carrier mobilities are as high as 10$^5$ cm$^2$V$^{-1}$s$^{-1}$. There are only two doubly degenerate bands crossing the Fermi level for SrPd, thus a semi-classical two-band model is available for describing its transport properties. Accordingly, the magnetoresistance of SrPd under a magnetic field of $4$ Tesla is predicted to reach ${10^5} %$ at low temperature. Furthermore, the calculated topological invariant indicates that SrPd is topologically trivial. Our theoretical studies suggest that SrPd can serve as an ideal platform to examine the charge compensation mechanism of the XMR effect.
The extremely large magnetoresistance (XMR) material LaBi was reported to become superconducting under pressure accompanying with suppressed magnetoresistance. However, the underlying mechanism is unclear. By using first-principles electronic structu
re calculations in combination with a semiclassical model, we have studied the electron-phonon coupling and magnetoresistance of LaBi in the pressure range from 0 to 18 GPa. Our calculations show that LaBi undergoes a structural phase transition from a face-centered cubic lattice to a primitive tetragonal lattice at $sim$7 GPa, verifying previous experimental results. Meanwhile, LaBi remains topologically nontrivial across the structural transition. Under all pressures that we have studied, the phonon-mediated mechanism based on the weak electron-phonon coupling cannot account for the observed superconductivity in LaBi, and the calculated magnetoresistance for LaBi does not show a suppression. The distinct difference between our calculations and experimental observations suggests either the existence of extra Bi impurities in the real LaBi compound or the possibility of other unknown mechanism.
Topological properties and topological superconductivity in real materials have attracted intensive experimental and theoretical attention recently. Based on symmetry analysis and first-principles electronic structure calculations, we predict that $R
$RuB$_{2}$ ($R$=Y, Lu) are not only topological superconductor (TSC) candidates, but also own the hybrid hourglass-type Dirac ring which is protected by the nonsymmorphic space group symmetry. Due to the band inversion around the time-reversal invariant $Gamma$ point in the Brillouin zone,$R$RuB$_{2}$ also have Dirac topological surface states (TSSs). More importantly, their TSSs on the (010) surface are within the band gap of bulk and cross the Fermi level, which form single Fermi surfaces. Considering the fact that both YRuB$_{2}$ and LuRuB$_{2}$ are superconductors with respective superconducting transition temperatures ($T_c$) of 7.6 K and 10.2 K, the superconducting bulks will likely induce superconductivity in the TSSs via the proximity effect. The ternary borides $R$RuB$_{2}$ may thus provide a very promising platform for studying the properties of topological superconductivity and hourglass fermions in the future experiments.
The topological electronic properties of orthorhombic-phase Mo$_{2}$C and W$_{2}$C superconductors have been studied based on first-principles electronic structure calculations. Our studies show that both Mo$_{2}$C and W$_{2}$C are three-dimensional
strong topological insulators defined on curved Fermi levels. The topological surface states on the (001) surface of Mo$_{2}$C right cross the Fermi level, while those of W$_{2}$C pass through the Fermi level with slight electron doping. These surface states hold helical spin textures and can be induced to become superconducting via a proximity effect, giving rise to an equivalent $p+ip$ type superconductivity. Our results show that Mo$_{2}$C and W$_{2}$C can provide a promising platform for exploring topological superconductivity and Majorana zero modes.
We consider the scattering of light in participating media composed of sparsely and randomly distributed discrete particles. The particle size is expected to range from the scale of the wavelength to the scale several orders of magnitude greater than
the wavelength, and the appearance shows distinct graininess as opposed to the smooth appearance of continuous media. One fundamental issue in physically-based synthesizing this appearance is to determine necessary optical properties in every local region. Since these optical properties vary spatially, we resort to geometrical optics approximation (GOA), a highly efficient alternative to rigorous Lorenz-Mie theory, to quantitatively represent the scattering of a single particle. This enables us to quickly compute bulk optical properties according to any particle size distribution. Then, we propose a practical Monte Carlo rendering solution to solve the transfer of energy in discrete participating media. Results show that for the first time our proposed framework can simulate a wide range of discrete participating media with different levels of graininess and converges to continuous media as the particle concentration increases.
The planning of whole-body motion and step time for bipedal locomotion is constructed as a model predictive control (MPC) problem, in which a sequence of optimization problems needs to be solved online. While directly solving these problems is extrem
ely time-consuming, we propose a predictive gait synthesizer to offer immediate solutions. Based on the full-dimensional model, a library of gaits with different speeds and periods is first constructed offline. Then the proposed gait synthesizer generates real-time gaits at 1kHz by synthesizing the gait library based on the online prediction of centroidal dynamics. We prove that the constructed MPC problem can ensure the uniform ultimate boundedness (UUB) of the CoM states and show that our proposed gait synthesizer can provide feasible solutions to the MPC optimization problems. Simulation and experimental results on a bipedal robot with 8 degrees of freedom (DoF) are provided to show the performance and robustness of this approach.
Over the past few decades, efforts have been made towards robust robotic grasping, and therefore dexterous manipulation. The soft gripper has shown their potential in robust grasping due to their inherent properties-low, control complexity, and high
adaptability. However, the deformation of the soft gripper when interacting with objects bring inaccuracy of grasped objects, which causes instability for robust grasping and further manipulation. In this paper, we present an omni-directional adaptive soft finger that can sense deformation based on embedded optical fibers and the application of machine learning methods to interpret transmitted light intensities. Furthermore, to use tactile information provided by a soft finger, we design a low-cost and multi degrees of freedom gripper to conform to the shape of objects actively and optimize grasping policy, which is called Rigid-Soft Interactive Grasping. Two main advantages of this grasping policy are provided: one is that a more robust grasping could be achieved through an active adaptation; the other is that the tactile information collected could be helpful for further manipulation.
