Hao Wang

Hao Wang

Auto-generated profile, based on publicly available information

Hao Wang

College of Information Science and Engineering, Northeastern University, Shenyang, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
6 November 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
MLMingyuan Li
Mingyuan Li
TJTong Jia
Tong Jia
HWHao Wang
Hao Wang
BMBowen Ma
Bowen Ma
HLHui Lu
Hui Lu
DCDongyue Chen
Dongyue Chen
Prohibited item detection in X-ray images is one of the most essential and highly effective methods widely employed in various security inspection scenarios. Considering the significant overlapping phenomenon in X-ray prohibited item images, we propose an anti-overlapping detection transformer (AO-DETR) based on one of the state-of-the-art (SOTA) general object detectors, DETR with improved denoising anchor boxes (DINO). Specifically, to address the feature coupling issue caused by overlapping phenomena, we introduce the category-specific one-to-one assignment (CSA) strategy to constrain category-specific object queries in predicting prohibited items of fixed categories, which can enhance their ability to extract features specific to prohibited items of a particular category from the overlapping foreground–background features. To address the edge blurring problem caused by overlapping phenomena, we propose the look forward densely (LFD) scheme, which improves the localization accuracy of reference boxes in mid-to-high-level decoder layers and enhances the ability to locate blurry edges of the final layer. Similar to DINO, our AO-DETR provides two different versions with distinct backbones, tailored to meet diverse application requirements. Extensive experiments on the PIXray, OPIXray, and HIXray datasets demonstrate that the proposed method surpasses the SOTA object detectors, indicating its potential applications in the field of prohibited item detection. The source code will be available at: https://github.com/Limingyuan001/AO-DETR.

4 March 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
BMBowen Ma
Bowen Ma
TJTong Jia
Tong Jia
MLMingyuan Li
Mingyuan Li
SWSongsheng Wu
Songsheng Wu
HWHao Wang
Hao Wang
DCDongyue Chen
Dongyue Chen
Dual-view baggage inspection has been widely applied in real-world scenarios, where orthogonal viewpoints are deployed to capture diverse and complementary information. Compared with single-view, it can effectively improve the identification performance when rotation and overlay hinder the viewability of the objects. However, this topic has not been rigorously explored due to the scarcity of datasets. To overcome this limitation, we contribute the first fully public large-scale Dual-view X-ray dataset. Our dataset, named DvXray, contains 16,000 pairs, 32,000 X-ray images, in which 15 common classes of 5,496 prohibited items are manually labeled. Besides, we propose an approach named Adaptive Hierarchical Cross Refinement (AHCR) to establish a strong baseline for prohibited item discovery in dual-view X-ray images. AHCR hypothesizes that each input pair is sampled from one mixture distribution, hence gathering the non-overlapping and position-aware cues along the shared axis and complementarily delivering to the other in a hierarchical structure to enrich the feature discriminability of the objects of interest from background overlaps. Upon this structure, we propose an adaptive control strategy and a confidence-weighted view fusion term to make it robust to difficult samples. Extensive experiments on DvXray show that AHCR not only brings significant classification gains over various backbones, such as recent Swin Transformer and ConvNeXt, but also exhibits an impressively better ability to localize objects. In addition, AHCR performs favorably against the counterparts and some recent multi-view learning approaches, moving a step closer towards potential application in practice. Dataset and code are available at https://github.com/Mbwslib/DvXray.

30 March 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
HWHao Wang
Hao Wang
QWQilong Wang
Qilong Wang
HZHongzhi Zhang
Hongzhi Zhang
QHQinghua Hu
Qinghua Hu
WZWangmeng Zuo
Wangmeng Zuo
Object detection is usually solved by learning a deep architecture involving classification and localization tasks, where feature learning for these two tasks is shared using the same backbone model. Recent works have shown that suitable disentanglement of classification and localization tasks has the great potential to improve performance of object detection. Despite the promising performance, existing feature disentanglement methods usually suffer from two limitations. First, most of them only focus on the disentangled proposals or predication heads for classification and localization tasks after RPN. While little consideration has been given to that the features for these two different tasks actually are obtained by a shared backbone model before RPN. Second, they are suggested for two-stage objectors and are not applicable to one-stage methods. To overcome these limitations, this paper presents a novel fully task-specific feature learning method for one-stage object detection. Specifically, our method first learns disentangled features for classification and localization tasks using two separated backbone models, where auxiliary classification and localization heads are inserted at the end of the two backbone models for providing a fully task-specific features for classification and localization. Then, a feature interaction module is developed for aligning and fusing task-specific features, which are further used to produce the final detection result. Experiments on MS COCO show that our proposed method (dubbed CrabNet) can achieve clear improvement over counterparts with increasing limited inference time, while performing favorably against state-of-the-arts.

26 July 2023 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
SDShizhuo Deng
Shizhuo Deng
JCJiaqi Chen
Jiaqi Chen
DTDa Teng
Da Teng
CYChuangui Yang
Chuangui Yang
DCDongyue Chen
Dongyue Chen
HWHao Wang
Hao Wang
Sensor-based Human Activity Recognition (HAR) is widely used in daily life and is the basic-level bridge to virtual healthcare in the metaverse. The current challenge is the low recognition accuracy for personalized users on smart wearable devices. The limited resource cannot support large deep learning models updated locally. Besides, integrating and transmitting sensor data to the cloud would reduce the efficiency. Considering the tradeoff between performance and complexity, we propose a Lightweight Human Activity Recognition (LHAR) framework. In LHAR, we combine the cross-people HAR task with the lightweight model task. LHAR framework is designed on the teacher-student architecture and the student network consists of multiple depthwise separable convolution layers to achieve fewer parameters. The dark knowledge distilled from the complex teacher model enhances the generalization ability of LHAR. To achieve effective knowledge distillation, we propose two optimization methods. Firstly, we train the teacher model by ensemble learning to promote teacher performance. Secondly, a multi-channel data augmentation method is proposed for the diversity of the dataset, which is a plug-in operation for the ensemble teacher model. In the experiments, we compare LHAR with state-of-art models in comparison evaluation, ablation study and the hyperparameter analysis, which proves the better performance of LHAR in efficiency and effectiveness.

1 February 2021 in Pattern Recognition
Verified
Journal Article
Closed access
HWHao Wang
Hao Wang
QWQilong Wang
Qilong Wang
PLPeihua Li
Peihua Li
WZWangmeng Zuo
Wangmeng Zuo

17 November 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
MLMingyuan Li
Mingyuan Li
BMBowen Ma
Bowen Ma
HWHao Wang
Hao Wang
DCDongyue Chen
Dongyue Chen
TJTong Jia
Tong Jia
X-ray prohibited items detection is an essential and highly effective method that has been widely used in inspection scenarios. To satisfy the practical demand for high accuracy in security auxiliary diagnosis systems, we propose a Geometry-Aware X-ray Prohibited Items Detector (GADet) based on the classic and advanced general object detector, YOLOX. Specifically, we first analyze and discover that the relationship between diagonal length and prohibited items category in X-ray images is highly robust and distinctive. Therefore, we introduce the Physical Diagonal Length Constraint (PDLC), which can utilize this underlying relationship to align classification and localization tasks in object detection. In addition, although the general label assignment strategies for natural images can alleviate the foreground-background class imbalance, they can not handle the unique foreground-background overlapping phenomenon in X-ray images. Thus, we propose the IoU-Aware Label Assignment (IAA), which can assist the network to concentrate on learning how to extract informative features from overlapping foreground and background. Similar to YOLOX, our GADet offers three different versions, including small, large, and extreme for adapting different application requirements. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art object detection methods, indicating its potential applications in the prohibited items detection field. The source code will be released at https://github.com/Limingyuan001/GADet.