Lei Qi

Lei Qi

Auto-generated profile, based on publicly available information

Lei Qi

Southeast University, Nanjing, Jiangsu, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2020 in IEEE Transactions on Cognitive and Developmental Systems
Verified
Journal Article
Closed access
YLYang Li
Yang Li
LWLei Wang
Lei Wang
WZWenming Zheng
Wenming Zheng
Yuan ZongYuan Zong
Yuan Zong
LQLei Qi
Lei Qi
TSTengfei Song
Tengfei Song
Neuroscience study dimond1976differing has revealed the discrepancy of emotion expression between the left and right hemispheres of human brain. Inspired by this study, in this paper, we propose a novel bi-hemispheric discrepancy model (BiHDM) to learn this discrepancy information between the two hemispheres to improve electroencephalograph (EEG) emotion recognition. Concretely, we first employ four directed recurrent neural networks (RNNs) based on two spatial orientations to traverse electrode signals on two separate brain regions. This enables the proposed model to obtain the deep representations of all the EEG electrodes’ signals that keep their intrinsic spatial dependence. Upon this representation, a pairwise subnetwork is designed to explicitly capture the discrepancy information between the two hemispheres and extract higher-level features for final classification. Furthermore, considering the presence of the domain shift between training and testing data, we incorporate a domain discriminator that adversarially induces the overall feature learning module to generate emotion-related but domain-invariant feature representation so as to further promote EEG emotion recognition. Experiments are conducted on three public EEG emotional datasets, in which we evaluate the performance of the proposed BiHDM as well as investigated the important brain areas in emotion expression and explore to use less electrodes to achieve comparable results. These experimental results jointly demonstrate the effectiveness and advantage of the proposed BiHDM model in solving the EEG emotion recognition problem.

4 October 2021 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
YSYinghuan Shi
Yinghuan Shi
JZJian Zhang
Jian Zhang
TLTong Ling
Tong Ling
JLJiwen Lu
Jiwen Lu
YZYefeng Zheng
Yefeng Zheng
Yang GaoYang Gao
Yang Gao
In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty. In this paper, we investigate a novel method of estimating uncertainty. We observe that, when assigned different misclassification costs in a certain degree, if the segmentation result of a pixel becomes inconsistent, this pixel shows a relative uncertainty in its segmentation. Therefore, we present a new semi-supervised segmentation model, namely, conservative-radical network ( CoraNet in short) based on our uncertainty estimation and separate self-training strategy. In particular, our CoraNet model consists of three major components: a conservative-radical module (CRM), a certain region segmentation network (C-SN), and an uncertain region segmentation network (UC-SN) that could be alternatively trained in an end-to-end manner. We have extensively evaluated our method on various segmentation tasks with publicly available benchmark datasets, including CT pancreas, MR endocardium, and MR multi-structures segmentation on the ACDC dataset. Compared with the current state of the art, our CoraNet has demonstrated superior performance. In addition, we have also analyzed its connection with and difference from conventional methods of uncertainty estimation in semi-supervised medical image segmentation.

3 July 2020 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
Xinqiang ChenXinqiang Chen
Xinqiang Chen
ZLZhibin Li
Zhibin Li
YYYongsheng Yang
Yongsheng Yang
LQLei Qi
Lei Qi
Ruimin KeRuimin Ke
Ruimin Ke
In recent years, unmanned aerial vehicle (UAV) has become an increasingly popular tool for traffic monitoring and data collection on highways due to its advantage of low cost, high resolution, good flexibility, and wide spatial coverage. Extracting high-resolution vehicle trajectory data from aerial videos taken by a UAV flying over target highway segment becomes a critical research task for traffic flow modeling and analysis. This study aims at proposing a novel methodological framework for automatic and accurate vehicle trajectory extraction from aerial videos. The method starts by developing an ensemble detector to detect vehicles in the target region. Then, the kernelized correlation filter is applied to track vehicles fast and accurately. After that, a mapping algorithm is proposed to transform vehicle positions from the Cartesian coordinates in image to the Frenet coordinates to extract raw vehicle trajectories along the roadway curves. The data denoising is then performed using a wavelet transform to eliminate the biased vehicle trajectory positions. Our method is tested on two aerial videos taken on different urban expressway segments in both peak and non-peak hours on weekdays. The extracted vehicle trajectories are compared with manual calibrated data to testify the framework performance. The experimental results show that the proposed method successfully extracts vehicle trajectories with a high accuracy: the measurement error of Mean Squared Deviation is 2.301 m, the Root-mean-square deviation is 0.175 m, and the Pearson correlation coefficient is 0.999. The video and trajectory data in this study are publicly accessible for serving as benchmark at https://seutraffic.com.

1 October 2019
Verified
Conference Paper
Closed access
LQLei Qi
Lei Qi
LWLei Wang
Lei Wang
JHJing Huo
Jing Huo
LZLuping Zhou
Luping Zhou
YSYinghuan Shi
Yinghuan Shi
YGYang Gao
Yang Gao
Unsupervised cross-domain person re-identification (Re-ID) faces two key issues. One is the data distribution discrepancy between source and target domains, and the other is the lack of discriminative information in target domain. From the perspective of representation learning, this paper proposes a novel end-to-end deep domain adaptation framework to address them. For the first issue, we highlight the presence of camera-level sub-domains as a unique characteristic in person Re-ID, and develop a “camera-aware” domain adaptation method via adversarial learning. With this method, the learned representation reduces distribution discrepancy not only between source and target domains but also across all cameras. For the second issue, we exploit the temporal continuity in each camera of target domain to create discriminative information. This is implemented by dynamically generating online triplets within each batch, in order to maximally take advantage of the steadily improved representation in training process. Together, the above two methods give rise to a new unsupervised domain adaptation framework for person Re-ID. Extensive experiments and ablation studies conducted on benchmark datasets demonstrate its superiority and interesting properties.

29 December 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
MDMing Dai
Ming Dai
EZEnhui Zheng
Enhui Zheng
ZFZhenhua Feng
Zhenhua Feng
LQLei Qi
Lei Qi
JZJiedong Zhuang
Jiedong Zhuang
Wankou YangWankou Yang
Wankou Yang
Unmanned Aerial Vehicles (UAVs) rely on satellite systems for stable positioning. However, due to limited satellite coverage or communication disruptions, UAVs may lose signals for positioning. In such situations, vision-based techniques can serve as an alternative, ensuring the self-positioning capability of UAVs. However, most of the existing datasets are developed for the geo-localization task of the objects captured by UAVs, rather than UAV self-positioning. Furthermore, the existing UAV datasets apply discrete sampling to synthetic data, such as Google Maps, neglecting the crucial aspects of dense sampling and the uncertainties commonly experienced in practical scenarios. To address these issues, this paper presents a new dataset, DenseUAV, that is the first publicly available dataset tailored for the UAV self-positioning task. DenseUAV adopts dense sampling on UAV images obtained in low-altitude urban areas. In total, over 27K UAV- and satellite-view images of 14 university campuses are collected and annotated. In terms of methodology, we first verify the superiority of Transformers over CNNs for the proposed task. Then we incorporate metric learning into representation learning to enhance the model’s discriminative capacity and to reduce the modality discrepancy. Besides, to facilitate joint learning from both the satellite and UAV views, we introduce a mutually supervised learning approach. Last, we enhance the Recall@K metric and introduce a new measurement, SDM@K, to evaluate both the retrieval and localization performance for the proposed task. As a result, the proposed baseline method achieves a remarkable Recall@1 score of 83.01% and an SDM@1 score of 86.50% on DenseUAV. The dataset and code have been made publicly available on https://github.com/Dmmm1997/DenseUAV.

16 August 2021 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
XHXiaoting Han
Xiaoting Han
LQLei Qi
Lei Qi
QYQian Yu
Qian Yu
ZZZiqi Zhou
Ziqi Zhou
YZYefeng Zheng
Yefeng Zheng
Yang GaoYang Gao
Yang Gao
Unsupervised domain adaptation (UDA) methods have shown their promising performance in the cross-modality medical image segmentation tasks. These typical methods usually utilize a translation network to transform images from the source domain to target domain or train the pixel-level classifier merely using translated source images and original target images. However, when there exists a large domain shift between source and target domains, we argue that this asymmetric structure, to some extent, could not fully eliminate the domain gap. In this paper, we present a novel deep symmetric architecture of UDA for medical image segmentation, which consists of a segmentation sub-network, and two symmetric source and target domain translation sub-networks. To be specific, based on two translation sub-networks, we introduce a bidirectional alignment scheme via a shared encoder and two private decoders to simultaneously align features 1) from source to target domain and 2) from target to source domain, which is able to effectively mitigate the discrepancy between domains. Furthermore, for the segmentation sub-network, we train a pixel-level classifier using not only original target images and translated source images, but also original source images and translated target images, which could sufficiently leverage the semantic information from the images with different styles. Extensive experiments demonstrate that our method has remarkable advantages compared to the state-of-the-art methods in three segmentation tasks, such as cross-modality cardiac, BraTS, and abdominal multi-organ segmentation.