arXiv subjects

Wei Feng

Publications and source records attributed to Wei Feng.

At least 181 records · Page 10Linked to original sources

arXiv2023

Decarbonization patterns of residential building operations in China and India

As the two largest emerging emitters with the highest growth in operational carbon from residential buildings, the historical emission patterns and decarbonization efforts of China and India warrant further exploration. This study aims to be the first to present a carbon intensity model considering end-use performances, assessing the operational decarbonization progress of residential building in India and China over the past two decades using the improved decomposing structural decomposition approach. Results indicate (1) the overall operational carbon intensity increased by 1.4% and 2.5% in China and India, respectively, between 2000 and 2020. Household expenditure-related energy intensity and emission factors were crucial in decarbonizing residential buildings. (2) Building electrification played a significant role in decarbonizing space cooling (-87.7 in China and -130.2 kilograms of carbon dioxide (kgCO2) per household in India) and appliances (-169.7 in China and -43.4 kgCO2 per household in India). (3) China and India collectively decarbonized 1498.3 and 399.7 mega-tons of CO2 in residential building operations, respectively. In terms of decarbonization intensity, India (164.8 kgCO2 per household) nearly caught up with China (182.5 kgCO2 per household) in 2020 and is expected to surpass China in the upcoming years, given the country's robust annual growth rate of 7.3%. Overall, this study provides an effective data-driven tool for investigating the building decarbonization potential in China and India, and offers valuable insights for other emerging economies seeking to decarbonize residential buildings in the forthcoming COP28 age.

econ.GN↗

arXiv2023

Quantum simulation of Hofstadter butterfly with synthetic gauge fields on two-dimensional superconducting-qubit lattices

Motivated by recent realizations of two-dimensional (2D) superconducting-qubit lattices, we propose a protocol to simulate Hofstadter butterfly with synthetic gauge fields in superconducting circuits. Based on the existing 2D superconducting-qubit lattices, we construct a generalized Hofstadter model on zigzag lattices, which has a fractal energy spectrum similar to the original Hofstadter butterfly. By periodically modulating the resonant frequencies of qubits, we engineer a synthetic gauge field to mimic the generalized Hofstadter Hamiltonian. A spectroscopic method is used to demonstrate the Hofstadter butterfly from the time evolutions of experimental observables. We numerically simulate the dynamics of the system with realistic parameters, and the results show a butterfly spectrum clearly. Our proposal provides a promising way to realize the Hofstadter butterfly on the latest 2D superconducting-qubit lattices and will stimulate the quantum simulation of novel properties induced by magnetic fields in superconducting circuits.

quant-ph↗

arXiv2023

Learning Restoration is Not Enough: Transfering Identical Mapping for Single-Image Shadow Removal

Shadow removal is to restore shadow regions to their shadow-free counterparts while leaving non-shadow regions unchanged. State-of-the-art shadow removal methods train deep neural networks on collected shadow & shadow-free image pairs, which are desired to complete two distinct tasks via shared weights, i.e., data restoration for shadow regions and identical mapping for non-shadow regions. We find that these two tasks exhibit poor compatibility, and using shared weights for these two tasks could lead to the model being optimized towards only one task instead of both during the training process. Note that such a key issue is not identified by existing deep learning-based shadow removal methods. To address this problem, we propose to handle these two tasks separately and leverage the identical mapping results to guide the shadow restoration in an iterative manner. Specifically, our method consists of three components: an identical mapping branch (IMB) for non-shadow regions processing, an iterative de-shadow branch (IDB) for shadow regions restoration based on identical results, and a smart aggregation block (SAB). The IMB aims to reconstruct an image that is identical to the input one, which can benefit the restoration of the non-shadow regions without explicitly distinguishing between shadow and non-shadow regions. Utilizing the multi-scale features extracted by the IMB, the IDB can effectively transfer information from non-shadow regions to shadow regions progressively, facilitating the process of shadow removal. The SAB is designed to adaptive integrate features from both IMB and IDB. Moreover, it generates a finely tuned soft shadow mask that guides the process of removing shadows. Extensive experiments demonstrate our method outperforms all the state-of-the-art shadow removal approaches on the widely used shadow removal datasets.

cs.CV↗

arXiv2023

Dirichlet process mixture models for the Analysis of Repeated Attempt Designs

In longitudinal studies, it is not uncommon to make multiple attempts to collect a measurement after baseline. Recording whether these attempts are successful provides useful information for the purposes of assessing missing data assumptions. This is because measurements from subjects who provide the data after numerous failed attempts may differ from those who provide the measurement after fewer attempts. Previous models for these designs were parametric and/or did not allow sensitivity analysis. For the former, there are always concerns about model misspecification and for the latter, sensitivity analysis is essential when conducting inference in the presence of missing data. Here, we propose a new approach which minimizes issues with model misspecification by using Bayesian nonparametrics for the observed data distribution. We also introduce a novel approach for identification and sensitivity analysis. We re-analyze the repeated attempts data from a clinical trial involving patients with severe mental illness and conduct simulations to better understand the properties of our approach.

stat.ME↗

arXiv2023

ESimCSE Unsupervised Contrastive Learning Jointly with UDA Semi-Supervised Learning for Large Label System Text Classification Mode

The challenges faced by text classification with large tag systems in natural language processing tasks include multiple tag systems, uneven data distribution, and high noise. To address these problems, the ESimCSE unsupervised comparative learning and UDA semi-supervised comparative learning models are combined through the use of joint training techniques in the models.The ESimCSE model efficiently learns text vector representations using unlabeled data to achieve better classification results, while UDA is trained using unlabeled data through semi-supervised learning methods to improve the prediction performance of the models and stability, and further improve the generalization ability of the model. In addition, adversarial training techniques FGM and PGD are used in the model training process to improve the robustness and reliability of the model. The experimental results show that there is an 8% and 10% accuracy improvement relative to Baseline on the public dataset Ruesters as well as on the operational dataset, respectively, and a 15% improvement in manual validation accuracy can be achieved on the operational dataset, indicating that the method is effective.

cs.LG↗

arXiv2023

Dynamics simulation of braiding two Majorana-zero-modes via a quantum dot

In this work we perform real time simulations for the dynamics of braiding a pair of Majorana zero modes (MZMs) through a quantum dot in a minimal setup of pure 1D realization. We reveal the strong nonadiabatic effect when the dot energy level approaches to zero in order to achieve a geometric phase $π/4$ which is required for a full exchange between the MZMs. Rather than the strategies of nonuniformly manipulating the system according to adiabatic condition and shortcuts-to-adiabaticity, we propose and illustrate a more feasible scheme to suppress the nonadiabatic transition, meanwhile which allows for a full exchange between the Majorana modes.

cond-mat.mes-hall↗

arXiv2023

Joint Mobility Control and MEC Offloading for Hybrid Satellite-Terrestrial-Network-Enabled Robots

Benefiting from the fusion of communication and intelligent technologies, network-enabled robots have become important to support future machine-assisted and unmanned applications. To provide high-quality services for robots in wide areas, hybrid satellite-terrestrial networks are a key technology. Through hybrid networks, computation-intensive and latency-sensitive tasks can be offloaded to mobile edge computing (MEC) servers. However, due to the mobility of mobile robots and unreliable wireless network environments, excessive local computations and frequent service migrations may significantly increase the service delay. To address this issue, this paper aims to minimize the average task completion time for MEC-based offloading initiated by satellite-terrestrial-network-enabled robots. Different from conventional mobility-aware schemes, the proposed scheme makes the offloading decision by jointly considering the mobility control of robots. A joint optimization problem of task offloading and velocity control is formulated. Using Lyapunov optimization, the original optimization is decomposed into a velocity control subproblem and a task offloading subproblem. Then, based on the Markov decision process (MDP), a dual-agent reinforcement learning (RL) algorithm is proposed. The convergence and complexity of the improved RL algorithm are theoretically analyzed, and the simulation results show that the proposed scheme can effectively reduce the offloading delay.

cs.IT↗

arXiv2023

Combining the Silhouette and Skeleton Data for Gait Recognition

Gait recognition, a long-distance biometric technology, has aroused intense interest recently. Currently, the two dominant gait recognition works are appearance-based and model-based, which extract features from silhouettes and skeletons, respectively. However, appearance-based methods are greatly affected by clothes-changing and carrying conditions, while model-based methods are limited by the accuracy of pose estimation. To tackle this challenge, a simple yet effective two-branch network is proposed in this paper, which contains a CNN-based branch taking silhouettes as input and a GCN-based branch taking skeletons as input. In addition, for better gait representation in the GCN-based branch, we present a fully connected graph convolution operator to integrate multi-scale graph convolutions and alleviate the dependence on natural joint connections. Also, we deploy a multi-dimension attention module named STC-Att to learn spatial, temporal and channel-wise attention simultaneously. The experimental results on CASIA-B and OUMVLP show that our method achieves state-of-the-art performance in various conditions.

cs.CV↗

arXiv2023

MMFormer: Multimodal Transformer Using Multiscale Self-Attention for Remote Sensing Image Classification

To benefit the complementary information between heterogeneous data, we introduce a new Multimodal Transformer (MMFormer) for Remote Sensing (RS) image classification using Hyperspectral Image (HSI) accompanied by another source of data such as Light Detection and Ranging (LiDAR). Compared with traditional Vision Transformer (ViT) lacking inductive biases of convolutions, we first introduce convolutional layers to our MMFormer to tokenize patches from multimodal data of HSI and LiDAR. Then we propose a Multi-scale Multi-head Self-Attention (MSMHSA) module to address the problem of compatibility which often limits to fuse HSI with high spectral resolution and LiDAR with relatively low spatial resolution. The proposed MSMHSA module can incorporate HSI to LiDAR data in a coarse-to-fine manner enabling us to learn a fine-grained representation. Extensive experiments on widely used benchmarks (e.g., Trento and MUUFL) demonstrate the effectiveness and superiority of our proposed MMFormer for RS image classification.

cs.CV↗

arXiv2023

Continuous Sign Language Recognition with Correlation Network

Human body trajectories are a salient cue to identify actions in the video. Such body trajectories are mainly conveyed by hands and face across consecutive frames in sign language. However, current methods in continuous sign language recognition (CSLR) usually process frames independently, thus failing to capture cross-frame trajectories to effectively identify a sign. To handle this limitation, we propose correlation network (CorrNet) to explicitly capture and leverage body trajectories across frames to identify signs. In specific, a correlation module is first proposed to dynamically compute correlation maps between the current frame and adjacent frames to identify trajectories of all spatial patches. An identification module is then presented to dynamically emphasize the body trajectories within these correlation maps. As a result, the generated features are able to gain an overview of local temporal movements to identify a sign. Thanks to its special attention on body trajectories, CorrNet achieves new state-of-the-art accuracy on four large-scale datasets, i.e., PHOENIX14, PHOENIX14-T, CSL-Daily, and CSL. A comprehensive comparison with previous spatial-temporal reasoning methods verifies the effectiveness of CorrNet. Visualizations demonstrate the effects of CorrNet on emphasizing human body trajectories across adjacent frames.

cs.CV↗

arXiv2023

Generation of long-lived $W$ states via reservoir engineering in dissipatively coupled systems

Very recently, dissipative coupling was discovered, which develops and broadens methods for controlling and utilizing light-matter interactions. Here, we propose a scheme to generate the tripartite $W$ state in a dissipatively coupled system, where one qubit and two resonators simultaneously interact with a common reservoir. With appropriate parameters, we find the $W$ state is a dark state of the system. By driving the qubit, the dissipatively coupled system will evolve from the ground state to the tripartite $W$ state. Because the initial state is the ground state of the system and no measurement is required, our scheme is easy to implement in experiments. Moreover, the $W$ state decouples from the common reservoir and thus has a very long lifetime. This scheme is applicable to a wide class of dissipatively coupled systems, and we specifically illustrate how to prepare the $W$ state in a hybrid qubit-photon-magnon system by using this scheme.

quant-ph↗

arXiv2022

Joint Communication and Sensing: Models and Potential of Using MIMO

The sixth-generation (6G) network is envisioned to integrate communication and sensing functions, so as to improve the spectrum efficiency (SE) and support explosive novel applications. Although the similarities of wireless communication and radio sensing lay the foundation for their combination, there is still considerable incompatible interest between them. To simultaneously guarantee the communication capacity and the sensing accuracy, the multiple-input and multiple-output (MIMO) technique plays an important role due to its unique capability of spatial beamforming and waveform shaping. However, the configuration of MIMO also brings high hardware cost, high power consumption, and high signal processing complexity. How to efficiently apply MIMO to achieve balanced communication and sensing performance is still open. In this survey, we discuss joint communication and sensing (JCAS) in the context of MIMO. We first outline the roles of MIMO in the process of wireless communication and radar sensing. Then, we present current advances in both communication and sensing coexistence and integration in detail. Three novel JCAS MIMO models are subsequently discussed by combining cutting-edge technologies, i.e., cloud random access networks (C-RANs), unmanned aerial vehicles (UAVs) and reconfigurable intelligent surfaces (RISs). Examined from the practical perspective, the potential and challenges of MIMO in JCAS are summarized, and promising solutions are provided. Motivated by the great potential of the Internet of Things (IoT), we also specify JCAS in IoT scenarios and discuss the uniqueness of applying JCAS to IoT. In the end, open issues are outlined to envisage a ubiquitous, intelligent and secure JCAS network in the near future.

eess.SP↗

arXiv2022

Sparta: Spatially Attentive and Adversarially Robust Activation

Adversarial training (AT) is one of the most effective ways for improving the robustness of deep convolution neural networks (CNNs). Just like common network training, the effectiveness of AT relies on the design of basic network components. In this paper, we conduct an in-depth study on the role of the basic ReLU activation component in AT for robust CNNs. We find that the spatially-shared and input-independent properties of ReLU activation make CNNs less robust to white-box adversarial attacks with either standard or adversarial training. To address this problem, we extend ReLU to a novel Sparta activation function (Spatially attentive and Adversarially Robust Activation), which enables CNNs to achieve both higher robustness, i.e., lower error rate on adversarial examples, and higher accuracy, i.e., lower error rate on clean examples, than the existing state-of-the-art (SOTA) activation functions. We further study the relationship between Sparta and the SOTA activation functions, providing more insights about the advantages of our method. With comprehensive experiments, we also find that the proposed method exhibits superior cross-CNN and cross-dataset transferability. For the former, the adversarially trained Sparta function for one CNN (e.g., ResNet-18) can be fixed and directly used to train another adversarially robust CNN (e.g., ResNet-34). For the latter, the Sparta function trained on one dataset (e.g., CIFAR-10) can be employed to train adversarially robust CNNs on another dataset (e.g., SVHN). In both cases, Sparta leads to CNNs with higher robustness than the vanilla ReLU, verifying the flexibility and versatility of the proposed method.

cs.LG↗

arXiv2022

Self-Emphasizing Network for Continuous Sign Language Recognition

Hand and face play an important role in expressing sign language. Their features are usually especially leveraged to improve system performance. However, to effectively extract visual representations and capture trajectories for hands and face, previous methods always come at high computations with increased training complexity. They usually employ extra heavy pose-estimation networks to locate human body keypoints or rely on additional pre-extracted heatmaps for supervision. To relieve this problem, we propose a self-emphasizing network (SEN) to emphasize informative spatial regions in a self-motivated way, with few extra computations and without additional expensive supervision. Specifically, SEN first employs a lightweight subnetwork to incorporate local spatial-temporal features to identify informative regions, and then dynamically augment original features via attention maps. It's also observed that not all frames contribute equally to recognition. We present a temporal self-emphasizing module to adaptively emphasize those discriminative frames and suppress redundant ones. A comprehensive comparison with previous methods equipped with hand and face features demonstrates the superiority of our method, even though they always require huge computations and rely on expensive extra supervision. Remarkably, with few extra computations, SEN achieves new state-of-the-art accuracy on four large-scale datasets, PHOENIX14, PHOENIX14-T, CSL-Daily, and CSL. Visualizations verify the effects of SEN on emphasizing informative spatial and temporal features. Code is available at https://github.com/hulianyuyy/SEN_CSLR

cs.CV↗

arXiv2022

Multi-Label Continual Learning using Augmented Graph Convolutional Network

Multi-Label Continual Learning (MLCL) builds a class-incremental framework in a sequential multi-label image recognition data stream. The critical challenges of MLCL are the construction of label relationships on past-missing and future-missing partial labels of training data and the catastrophic forgetting on old classes, resulting in poor generalization. To solve the problems, the study proposes an Augmented Graph Convolutional Network (AGCN++) that can construct the cross-task label relationships in MLCL and sustain catastrophic forgetting. First, we build an Augmented Correlation Matrix (ACM) across all seen classes, where the intra-task relationships derive from the hard label statistics. In contrast, the inter-task relationships leverage hard and soft labels from data and a constructed expert network. Then, we propose a novel partial label encoder (PLE) for MLCL, which can extract dynamic class representation for each partial label image as graph nodes and help generate soft labels to create a more convincing ACM and suppress forgetting. Last, to suppress the forgetting of label dependencies across old tasks, we propose a relationship-preserving constrainter to construct label relationships. The inter-class topology can be augmented automatically, which also yields effective class representations. The proposed method is evaluated using two multi-label image benchmarks. The experimental results show that the proposed way is effective for MLCL image recognition and can build convincing correlations across tasks even if the labels of previous tasks are missing.

cs.CV↗

arXiv2022

From Indoor To Outdoor: Unsupervised Domain Adaptive Gait Recognition

Gait recognition is an important AI task, which has been progressed rapidly with the development of deep learning. However, existing learning based gait recognition methods mainly focus on the single domain, especially the constrained laboratory environment. In this paper, we study a new problem of unsupervised domain adaptive gait recognition (UDA-GR), that learns a gait identifier with supervised labels from the indoor scenes (source domain), and is applied to the outdoor wild scenes (target domain). For this purpose, we develop an uncertainty estimation and regularization based UDA-GR method. Specifically, we investigate the characteristic of gaits in the indoor and outdoor scenes, for estimating the gait sample uncertainty, which is used in the unsupervised fine-tuning on the target domain to alleviate the noises of the pseudo labels. We also establish a new benchmark for the proposed problem, experimental results on which show the effectiveness of the proposed method. We will release the benchmark and source code in this work to the public.

cs.CV↗

arXiv2022

A Benchmark of Video-Based Clothes-Changing Person Re-Identification

Person re-identification (Re-ID) is a classical computer vision task and has achieved great progress so far. Recently, long-term Re-ID with clothes-changing has attracted increasing attention. However, existing methods mainly focus on image-based setting, where richer temporal information is overlooked. In this paper, we focus on the relatively new yet practical problem of clothes-changing video-based person re-identification (CCVReID), which is less studied. We systematically study this problem by simultaneously considering the challenge of the clothes inconsistency issue and the temporal information contained in the video sequence for the person Re-ID problem. Based on this, we develop a two-branch confidence-aware re-ranking framework for handling the CCVReID problem. The proposed framework integrates two branches that consider both the classical appearance features and cloth-free gait features through a confidence-guided re-ranking strategy. This method provides the baseline method for further studies. Also, we build two new benchmark datasets for CCVReID problem, including a large-scale synthetic video dataset and a real-world one, both containing human sequences with various clothing changes. We will release the benchmark and code in this work to the public.

cs.CV↗

arXiv2022

Panoramic Human Activity Recognition

To obtain a more comprehensive activity understanding for a crowded scene, in this paper, we propose a new problem of panoramic human activity recognition (PAR), which aims to simultaneous achieve the individual action, social group activity, and global activity recognition. This is a challenging yet practical problem in real-world applications. For this problem, we develop a novel hierarchical graph neural network to progressively represent and model the multi-granularity human activities and mutual social relations for a crowd of people. We further build a benchmark to evaluate the proposed method and other existing related methods. Experimental results verify the rationality of the proposed PAR problem, the effectiveness of our method and the usefulness of the benchmark. We will release the source code and benchmark to the public for promoting the study on this problem.

cs.CV↗