Search

Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections. By defining a graph with joints as vertices and their natural connections as edges, previous works successfully adopted Graph Convolutional networks (GCNs) to model joint co-occurrences and achieved superior performance. More recently, a limitation of GCNs is identified, i.e., the topology is fixed after training. To relax such a restriction, Self-Attention (SA) mechanism has been adopted to make the topology of GCNs adaptive to the input, resulting in the state-of-the-art hybrid models. Concurrently, attempts with plain Transformers have also been made, but they still lag behind state-of-the-art GCN-based methods due to the lack of structural prior. Unlike hybrid models, we propose a more elegant solution to incorporate the bone connectivity into Transformer via a graph distance embedding. Our embedding retains the information of skeletal structure during training, whereas GCNs merely use it for initialization. More importantly, we reveal an underlying issue of graph models in general, i.e., pairwise aggregation essentially ignores the high-order kinematic dependencies between body joints. To fill this gap, we propose a new self-attention (SA) mechanism on hypergraph, termed Hypergraph Self-Attention (HyperSA), to incorporate intrinsic higher-order relations into the model. We name the resulting model Hyperformer, and it beats state-of-the-art graph models w.r.t. accuracy and efficiency on NTU RGB+D, NTU RGB+D 120, and Northwestern-UCLA datasets.

Skeleton-based action recognition has recently received considerable attention. Current approaches to skeleton-based action recognition are typically formulated as one-hot classification tasks and do not fully exploit the semantic relations between actions. For example, "make victory sign" and "thumb up" are two actions of hand gestures, whose major difference lies in the movement of hands. This information is agnostic from the categorical one-hot encoding of action classes but could be unveiled from the action description. Therefore, utilizing action description in training could potentially benefit representation learning. In this work, we propose a Generative Action-description Prompts (GAP) approach for skeleton-based action recognition. More specifically, we employ a pre-trained large-scale language model as the knowledge engine to automatically generate text descriptions for body parts movements of actions, and propose a multi-modal training scheme by utilizing the text encoder to generate feature vectors for different body parts and supervise the skeleton encoder for action representation learning. Experiments show that our proposed GAP method achieves noticeable improvements over various baseline models without extra computation cost at inference. GAP achieves new state-of-the-arts on popular skeleton-based action recognition benchmarks, including NTU RGB+D, NTU RGB+D 120 and NW-UCLA. The source code is available at https://github.com/MartinXM/GAP., Comment: Accepted by ICCV23

Gate-based quantum computation has been extensively investigated using quantum circuits based on qubits. In many cases, such qubits are actually made out of multilevel systems but with only two states being used for computational purpose. While such a strategy has the advantage of being in line with the common binary logic, it in some sense wastes the ready-for-use resources in the large Hilbert space of these intrinsic multi-dimensional systems. Quantum computation beyond qubits (e.g., using qutrits or qudits) has thus been discussed and argued to be more efficient than its qubit counterpart in certain scenarios. However, one of the essential elements for qutrit-based quantum computation, two-qutrit quantum gate, remains a major challenge. In this work, we propose and demonstrate a highly efficient and scalable two-qutrit quantum gate in superconducting quantum circuits. Using a tunable coupler to control the cross-Kerr coupling between two qutrits, our scheme realizes a two-qutrit conditional phase gate with fidelity 89.3% by combining simple pulses applied to the coupler with single-qutrit operations. We further use such a two-qutrit gate to prepare an EPR state of two qutrits with a fidelity of 95.5%. Our scheme takes advantage of a tunable qutrit-qutrit coupling with a large on:off ratio. It therefore offers both high efficiency and low cross talk between qutrits, thus being friendly for scaling up. Our work constitutes an important step towards scalable qutrit-based quantum computation., Comment: 15 pages, 12 figures

Recently, transformers have shown great potential in image classification and established state-of-the-art results on the ImageNet benchmark. However, compared to CNNs, transformers converge slowly and are prone to overfitting in low-data regimes due to the lack of spatial inductive biases. Such spatial inductive biases can be especially beneficial since the 2D structure of an input image is not well preserved in transformers. In this work, we present Spatial Prior-enhanced Self-Attention (SP-SA), a novel variant of vanilla Self-Attention (SA) tailored for vision transformers. Spatial Priors (SPs) are our proposed family of inductive biases that highlight certain groups of spatial relations. Unlike convolutional inductive biases, which are forced to focus exclusively on hard-coded local regions, our proposed SPs are learned by the model itself and take a variety of spatial relations into account. Specifically, the attention score is calculated with emphasis on certain kinds of spatial relations at each head, and such learned spatial foci can be complementary to each other. Based on SP-SA we propose the SP-ViT family, which consistently outperforms other ViT models with similar GFlops or parameters. Our largest model SP-ViT-L achieves a record-breaking 86.3% Top-1 accuracy with a reduction in the number of parameters by almost 50% compared to previous state-of-the-art model (150M for SP-ViT-L vs 271M for CaiT-M-36) among all ImageNet-1K models trained on 224x224 and fine-tuned on 384x384 resolution w/o extra data.

Hybrid transition metal oxides continue to attract attention due to their multiple degrees of freedom ($e.g.$, lattice, charge, spin, and orbital) and versatile properties. Here we investigate the magnetic and electronic properties of the newly synthesized double perovskite Ba$_2$NiIrO$_6$, using crystal field theory, superexchange model analysis, density functional calculations, and parallel tempering Monte Carlo (PTMC) simulations. Our results indicate that Ba$_2$NiIrO$_6$ has the Ni$^{2+}$ ($t_{2g}^{6}e_{g}^{2}$)-Ir$^{6+}$ ($t_{2g}^{3}$) charge states. The first nearest-neighboring (1NN) Ni$^{2+}$-Ir$^{6+}$ ions prefer a ferromagnetic (FM) coupling as expected from the Goodenough-Kanamori-Anderson rules, which contradicts the experimental antiferromagnetic (AF) order in Ba$_2$NiIrO$_6$. We find that the strong 2NN AF couplings are frustrated in the fcc sublattices, and they play a major role in determining the observed AF ground state. We also prove that the $J_{\rm eff}$ = 3/2 and $J_{\rm eff}$ = 1/2 states induced by spin-orbit coupling, which would be manifested in low-dimensional (e.g., layered) iridates, are however not the case for cubic Ba$_2$NiIrO$_6$. Our PTMC simulations show that when the long-range (2NN and 3NN) AF interactions are included, an AF transition with $T_{\rm N}$ = 66 K would be obtained and it is well comparable with the experimental 51 K. Meanwhile, we propose a possible 2$\times$2$\times$2 noncollinear AF structure for Ba$_2$NiIrO$_6$., Comment: 6 pages, 8 figures, 1 table

The table-based fact verification task has recently gained widespread attention and yet remains to be a very challenging problem. It inherently requires informative reasoning over natural language together with different numerical and logical reasoning on tables (e.g., count, superlative, comparative). Considering that, we exploit mixture-of-experts and present in this paper a new method: Self-adaptive Mixture-of-Experts Network (SaMoE). Specifically, we have developed a mixture-of-experts neural network to recognize and execute different types of reasoning -- the network is composed of multiple experts, each handling a specific part of the semantics for reasoning, whereas a management module is applied to decide the contribution of each expert network to the verification result. A self-adaptive method is developed to teach the management module combining results of different experts more efficiently without external knowledge. The experimental results illustrate that our framework achieves 85.1% accuracy on the benchmark dataset TabFact, comparable with the previous state-of-the-art models. We hope our framework can serve as a new baseline for table-based verification. Our code is available at https://github.com/THUMLP/SaMoE., Comment: Accepted by Findings of ACL 2022

Scalable quantum information processing requires that modular gate operations can be executed in parallel. The presence of crosstalk decreases the individual addressability, causing erroneous results during simultaneous operations. For superconducting qubits which operate in the microwave regime, electromagnetic isolation is often limited due to design constraints, leading to signal crosstalk that can deteriorate the quality of simultaneous gate operations. Here, we propose and demonstrate a method based on AC Stark effect for calibrating the microwave signal crosstalk. The method is suitable for processors based on fixed-frequency qubits which are known for high coherence and simple control. The optimal compensation parameters can be reliably identified from a well-defined interference pattern. We implement the method on an array of 7 superconducting qubits, and show its effectiveness in removing the majority of crosstalk errors.

Controlling the flow of quantum information is a fundamental task for quantum computers, which is unfeasible to realize on classical devices. Coherent devices which can process quantum states are thus required to route the quantum states that encode information. In this paper we demonstrate experimentally the smallest quantum transistor with a superconducting quantum processor which is composed of a collector qubit, an emitter qubit, and a coupler (transistor gate). The interaction strength between the collector and emitter qubits is controlled by the frequency and state of the coupler, effectively implementing a quantum switch. Through the coupler-state-dependent Heisenberg (inherent) interaction between the qubits, a single-step (native) conditional $i$SWAP operation can be applied. To this end, we find that it is important to take into consideration higher energy level for achieving a native and high-fidelity transistor operation. By reconstructing the Quantum Process Tomography, we obtain an operation fidelity of $92.36\%$ when the transistor gate is open ($i$SWAP implementation) and $95.23 \%$ in the case of closed gate (identity gate implementation). The architecture has strong potential in quantum information processing applications with superconducting qubits., Comment: 10 pages and 6 figures, including Appendix Section

Identifying, quantifying, and suppressing decoherence mechanisms in qubits are important steps towards the goal of engineering a quantum computer or simulator. Superconducting circuits offer flexibility in qubit design; however, their performance is adversely affected by quasiparticles (broken Cooper pairs). Developing a quasiparticle mitigation strategy compatible with scalable, high-coherence devices is therefore highly desirable. Here we experimentally demonstrate how to control quasiparticle generation by downsizing the qubit, capping it with a metallic cover, and equipping it with suitable quasiparticle traps. Using a flip-chip design, we shape the electromagnetic environment of the qubit above the superconducting gap, inhibiting quasiparticle poisoning. Our findings support the hypothesis that quasiparticle generation is dominated by the breaking of Cooper pairs at the junction, as a result of photon absorption by the antenna-like qubit structure. We achieve record low charge-parity switching rate (<1Hz). Our aluminium devices also display improved stability with respect to discrete charging events.

Implementing quantum algorithms on realistic hardware requires translating high-level global operations into sequences of native elementary gates, a process known as quantum compiling. Physical limitations, such as constraints in connectivity and gate alphabets, often result in unacceptable implementation costs. To enable successful near-term applications, it is crucial to optimize compilation by exploiting the potential capabilities of existing hardware. Here, we implement a resource-efficient construction for a quantum version of AND logic that can reduce the cost, enabling the execution of key quantum circuits. On a high-scalability superconducting quantum processor, we demonstrate low-depth synthesis of high-fidelity generalized Toffoli gates with up to 8 qubits and Grover's search algorithm in a search space of up to 64 entries; both are the largest such implementations in scale to date. Our experimental demonstration illustrates a scalable implementation of simplifying quantum algorithms, paving the way for larger, more meaningful quantum applications on noisy devices.

Quantum batteries are miniature energy storage devices and play a very important role in quantum thermodynamics. In recent years, quantum batteries have been extensively studied, but limited in theoretical level. Here we report the experimental realization of a quantum battery based on superconducting qubits. Our model explores dark and bright states to achieve stable and powerful charging processes, respectively. Our scheme makes use of the quantum adiabatic brachistochrone, which allows us to speed up the {battery ergotropy injection. Due to the inherent interaction of the system with its surrounding, the battery exhibits a self-discharge, which is shown to be described by a supercapacitor-like self-discharging mechanism. Our results paves the way for proposals of new superconducting circuits able to store extractable work for further usage., Comment: 5 pages and 3 figures + Supplemental material

Scalable quantum information processing requires the ability to tune multi-qubit interactions. This makes the precise manipulation of quantum states particularly difficult for multi-qubit interactions because tunability unavoidably introduces sensitivity to fluctuations in the tuned parameters, leading to erroneous multi-qubit gate operations. The performance of quantum algorithms may be severely compromised by coherent multi-qubit errors. It is therefore imperative to understand how these fluctuations affect multi-qubit interactions and, more importantly, to mitigate their influence. In this study, we demonstrate how to implement dynamical-decoupling techniques to suppress the two-qubit analogue of the dephasing on a superconducting quantum device featuring a compact tunable coupler, a trending technology that enables the fast manipulation of qubit--qubit interactions. The pure-dephasing time shows an up to ~14 times enhancement on average when using robust sequences. The results are in good agreement with the noise generated from room-temperature circuits. Our study further reveals the decohering processes associated with tunable couplers and establishes a framework to develop gates and sequences robust against two-qubit errors., Comment: 19 pages, 14 figures

The software inevitably encounters the crash, which will take developers a large amount of effort to find the fault causing the crash (short for crashing fault). Developing automatic methods to identify the residence of the crashing fault is a crucial activity for software quality assurance. Researchers have proposed methods to predict whether the crashing fault resides in the stack trace based on the features collected from the stack trace and faulty code, aiming at saving the debugging effort for developers. However, previous work usually neglected the feature preprocessing operation towards the crash data and only used traditional classification models. In this paper, we propose a novel crashing fault residence prediction framework, called ConDF, which consists of a consistency based feature subset selection method and a state-of-the-art deep forest model. More specifically, first, the feature selection method is used to obtain an optimal feature subset and reduce the feature dimension by reserving the representative features. Then, a simplified deep forest model is employed to build the classification model on the reduced feature set. The experiments on seven open source software projects show that our ConDF method performs significantly better than 17 baseline methods on three performance indicators.

Quantum simulation can be implemented in pure digital or analog ways, each with their pros and cons. By taking advantage of the universality of a digital route and the efficiency of analog simulation, hybrid digital-analog approaches can enrich the possibilities for quantum simulation. We use a unique hybrid approach to experimentally perform a quantum simulation of phase-controlled dynamics resulting from a closed-contour interaction (CCI) within certain multi-level systems in superconducting quantum circuits. Due to symmetry constraints, such systems cannot host an inherent CCI. Nevertheless, by assembling analog modules corresponding to their natural evolutions and specially designed digital modules constructed from standard quantum logic gates, we can bypass such constraints and realize an effective CCI in these systems. Based on this realization, we demonstrate a variety of related and interesting phenomena, including phase-controlled chiral dynamics, separation of chiral enantiomers, and a new mechanism to generate entangled states based on CCI., Comment: 13 pages, 11 figures

High-quality two-qubit gate operations are crucial for scalable quantum information processing. Often, the gate fidelity is compromised when the system becomes more integrated. Therefore, a low-error-rate, easy-to-scale two-qubit gate scheme is highly desirable. Here, we experimentally demonstrate a new two-qubit gate scheme that exploits fixed-frequency qubits and a tunable coupler in a superconducting quantum circuit. The scheme requires less control lines, reduces crosstalk effect, simplifies calibration procedures, yet produces a controlled-Z gate in 30ns with a high fidelity of 99.5%, derived from the interleaved randomized benchmarking method. Error analysis shows that gate errors are mostly coherence limited. Our demonstration paves the way for large-scale implementation of high-fidelity quantum operations.

Deep generative networks trained via maximum likelihood on a natural image dataset like CIFAR10 often assign high likelihoods to images from datasets with different objects (e.g., SVHN). We refine previous investigations of this failure at anomaly detection for invertible generative networks and provide a clear explanation of it as a combination of model bias and domain prior: Convolutional networks learn similar low-level feature distributions when trained on any natural image dataset and these low-level features dominate the likelihood. Hence, when the discriminative features between inliers and outliers are on a high-level, e.g., object shapes, anomaly detection becomes particularly challenging. To remove the negative impact of model bias and domain prior on detecting high-level differences, we propose two methods, first, using the log likelihood ratios of two identical models, one trained on the in-distribution data (e.g., CIFAR10) and the other one on a more general distribution of images (e.g., 80 Million Tiny Images). We also derive a novel outlier loss for the in-distribution network on samples from the more general distribution to further improve the performance. Secondly, using a multi-scale model like Glow, we show that low-level features are mainly captured at early scales. Therefore, using only the likelihood contribution of the final scale performs remarkably well for detecting high-level feature differences of the out-of-distribution and the in-distribution. This method is especially useful if one does not have access to a suitable general distribution. Overall, our methods achieve strong anomaly detection performance in the unsupervised setting, and only slightly underperform state-of-the-art classifier-based methods in the supervised setting. Code can be found at https://github.com/boschresearch/hierarchical_anomaly_detection., Comment: Published at NeurIPS 2020. Code can be found at https://github.com/boschresearch/hierarchical_anomaly_detection

Higher-order topological phases give rise to new bulk and boundary physics, as well as new classes of topological phase transitions. While the realization of higher-order topological phases has been confirmed in many platforms by detecting the existence of gapless boundary modes, a direct determination of the higher-order topology and related topological phase transitions through the bulk in experiments has still been lacking. To bridge the gap, in this work we carry out the simulation of a two-dimensional second-order topological phase in a superconducting qubit. Owing to the great flexibility and controllability of the quantum simulator, we observe the realization of higher-order topology directly through the measurement of the pseudo-spin texture in momentum space of the bulk for the first time, in sharp contrast to previous experiments based on the detection of gapless boundary modes in real space. Also through the measurement of the evolution of pseudo-spin texture with parameters, we further observe novel topological phase transitions from the second-order topological phase to the trivial phase, as well as to the first-order topological phase with nonzero Chern number. Our work sheds new light on the study of higher-order topological phases and topological phase transitions., Comment: 8+8 pages; 4+7 figures