682 citations · 2.5k across the 94 of their papers we have counts for
29 papers · 1 filter
ELSA: Enhanced Local Self-Attention for Vision Transformer
Jingkai Zhou, Pichao Wang, Fan Wang +3
Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning. The performance of local self-attention (LSA) is just on par w…
Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition
Benjia Zhou, Pichao Wang, Jun Wan +6
Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors. Although previous RGB-D-based motion recognitio…
On the Dilution of Precision for Time Difference of Arrival with Station Deployment
Fengyun Zhang, Hao Li, Yulong Ding +2
The paper aims to reveal the relationship between the performance of moving object tracking algorithms and the tracking anchors (station) deployment. The Dilution of Precision (DoP…
Design and Implementation of Real-Time Localization System (RTLS) based on UWB and TDoA Algorithm
Fengyun Zhang, Li Yang, Yuhuan Liu +3
Nowadays, accurate localization plays an essential role in many fields, like target tracking and path planning. The challenges of indoor localization include inadequate localizatio…
TransZero: Attribute-guided Transformer for Zero-Shot Learning
Shiming Chen, Ziming Hong, Yang Liu +6
Zero-shot learning (ZSL) aims to recognize novel classes by transferring semantic knowledge from seen classes to unseen ones. Semantic knowledge is learned from attribute descripti…
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation
Zhaoyuan Yin, Pichao Wang, Fan Wang +4
Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations. Most existing methods are bottom-up ap…
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
Hao Luo, Pichao Wang, Yi Xu +5
Transformer-based supervised pre-training achieves great performance in person re-identification (ReID). However, due to the domain gap between ImageNet and ReID datasets, it usual…
Quantum key distribution over 658 km fiber with distributed vibration sensing
Jiu-Peng Chen, Chi Zhang, Yang Liu +11
Twin-field quantum key distribution (TF-QKD) promises ultra-long secure key distribution which surpasses the rate distance limit and can reduce the number of the trusted nodes in l…
2nd Place Solution to Google Landmark Retrieval 2021
Zhang Yuqi, Xu Xianzhe, Chen Weihua +4
This paper presents the 2nd place solution to the Google Landmark Retrieval 2021 Competition on Kaggle. The solution is based on a baseline with training tricks from person re-iden…
HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning
Shiming Chen, Guo-Sen Xie, Yang Liu +5
Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to unseen ones. Typically, to guarantee desirable knowledge…
Scaled ReLU Matters for Training Vision Transformers
Pichao Wang, Xue Wang, Hao Luo +5
Vision transformers (ViTs) have been an alternative design paradigm to convolutional neural networks (CNNs). However, the training of ViTs is much harder than CNNs, as it is sensit…
Dash: Semi-Supervised Learning with Dynamic Thresholding
Yi Xu, Lei Shang, Jinxing Ye +5
While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use eith…
Efficient force field and energy emulation through partition of permutationally equivalent atoms
Hao Li, Musen Zhou, Jessalyn Sebastian +2
Gaussian process (GP) emulator has been used as a surrogate model for predicting force field and molecular potential, to overcome the computational bottleneck of molecular dynamics…
LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation
Dewei Hu, Can Cui, Hao Li +3
Optical coherence tomography (OCT) is a non-invasive imaging technique widely used for ophthalmology. It can be extended to OCT angiography (OCT-A), which reveals the retinal vascu…
Magnetization-tuned topological quantum phase transition in MnBi2Te4 devices
Jun Ge, Yanzhao Liu, Pinyuan Wang +7
Recently, the intrinsic magnetic topological insulator MnBi2Te4 has attracted enormous research interest due to the great success in realizing exotic topological quantum states, su…
Phase-Programmable Gaussian Boson Sampling Using Stimulated Squeezed Light
Han-Sen Zhong, Yu-Hao Deng, Jian Qin +23
The tantalizing promise of quantum computational speedup in solving certain problems has been strongly supported by recent experimental evidence from a high-fidelity 53-qubit super…
Cross-Lingual Transfer Learning for Statistical Type Inference
Zhiming Li, Xiaofei Xie, Haoliang Li +3
Hitherto statistical type inference systems rely thoroughly on supervised learning approaches, which require laborious manual effort to collect and label large amounts of data. Mos…
KVT: k-NN Attention for Boosting Vision Transformers
Pichao Wang, Xue Wang, Fan Wang +4
Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transforme…
Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection
Cangning Fan, Fangyi Zhang, Peng Liu +5
Previous transfer methods for anomaly detection generally assume the availability of labeled data in source or target domains. However, such an assumption is not valid in most real…
City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones
Chong Liu, Yuqi Zhang, Hao Luo +6
Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions. This paper describes our solution to the Track 3…
Why Does Multi-Epoch Training Help?
Yi Xu, Qi Qian, Hao Li +1
Stochastic gradient descent (SGD) has become the most attractive optimization method in training large-scale deep neural networks due to its simplicity, low computational cost in e…
Unsupervised Visual Representation Learning by Online Constrained K-Means
Qi Qian, Yuanhong Xu, Juhua Hu +2
Cluster discrimination is an effective pretext task for unsupervised representation learning, which often consists of two phases: clustering and discrimination. Clustering is to as…
An Efficient Training Approach for Very Large Scale Face Recognition
Kai Wang, Shuo Wang, Panpan Zhang +7
Face recognition has achieved significant progress in deep learning era due to the ultra-large-scale and welllabeled datasets. However, training on the outsize datasets is time-con…
Direct visualization of edge state in even-layer MnBi2Te4 at zero magnetic field
Weiyan Lin, Yang Feng, Yongchao Wang +12
Being the first intrinsic antiferromagnetic(AFM) topological insulator(TI), MnBi2Te4 is argued to be a topological axion state in its even-layer form due to the antiparallel magnet…