Xin-Yu Zhang

Xin-Yu Zhang

Auto-generated profile, based on publicly available information

Xin-Yu Zhang

Southeast University, Nanjing, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
9 April 2021 in IEEE Access
Verified
Journal Article
Open access
ZWZhuang-Zhuang Wang
Zhuang-Zhuang Wang
KXKai Xie
Kai Xie
XZXin-Yu Zhang
Xin-Yu Zhang
HCHua-Quan Chen
Hua-Quan Chen
CWChang Wen
Chang Wen
JHJian-Biao He
Jian-Biao He
Small-object detection is a basic and challenging problem in computer vision tasks. It is widely used in pedestrian detection, traffic sign detection, and other fields. This paper proposes a deep learning small-object detection method based on image super-resolution to improve the speed and accuracy of small-object detection. First, we add a feature texture transfer (FTT) module at the input end to improve the image resolution at this end as well as to remove the noise in the image. Then, in the backbone network, using the Darknet53 framework, we use dense blocks to replace residual blocks to reduce the number of network structure parameters to avoid unnecessary calculations. Then, to make full use of the features of small targets in the image, the neck uses a combination of SPPnet and PANnet to complete this part of the multi-scale feature fusion work. Finally, the problem of image background and foreground imbalance is solved by adding the foreground and background balance loss function to the YOLOv4 loss function part. The results of the experiment conducted using our self-built dataset show that the proposed method has higher accuracy and speed compared with the currently available small-target detection methods.

28 October 2024
Verified
Conference Paper
Open access
JGJiawei Ge
Jiawei Ge
Jiuxin CaoJiuxin Cao
Jiuxin Cao
XZXuelin Zhu
Xuelin Zhu
XZXinyu Zhang
Xinyu Zhang
CLChang Liu
Chang Liu
BLBo Liu
Bo Liu
Vision-Language Tracking (VLT) requires locating a specific target in video sequences, given a natural language prompt and an initial object box. Despite recent advancements, existing approaches heavily rely on expensive and time-consuming human annotations. To mitigate this limitation, directly generating pseudo labels from raw videos seems to be a straightforward solution; however, it inevitably introduces undesirable noise during the training process. Moreover, we insist that an efficient tracker should excel in tracking the target, regardless of the temporal direction. Building upon these insights, we propose the pioneering semi-supervised learning scheme for VLT task, representing a crucial step towards reducing the dependency on high-quality yet costly labeled data. Specifically, drawing inspiration from the natural attributes of a video (i.e., space, time, and semantics), our approach progressively leverages inherent consistencies from these aspects: (1) Spatially, each frame and any object cropped from it naturally form an image-bbox (bounding box) pair for self-training; (2) Temporally, bidirectional tracking trajectories should exhibit minimal differences; (3) Semantically, the correlation between visual and textual features is expected to remain consistent. Furthermore, the framework is validated with a simple yet effective tracker we devised, named ATTracker (Asymmetrical Transformer Tracker). It modifies the self-attention operation in an asymmetrical way, striving to enhance target-related features while suppressing noise. Extensive experiments confirm that our ATTracker serves as a robust baseline, outperforming fully supervised base trackers. By unveiling the potential of learning with limited annotations, this study aims to attract attention and pave the way for Semi-supervised Vision-Language Tracking (SS-VLT).

3 May 2021 in IEEE Access
Verified
Journal Article
Open access
YZYun-Feng Zhou
Yun-Feng Zhou
KXKai Xie
Kai Xie
XZXin-Yu Zhang
Xin-Yu Zhang
CWChang Wen
Chang Wen
JHJian-Biao He
Jian-Biao He
Recognizing potentially hazardous objects is crucial in the field of transportation, especially in assisted and unmanned driving. However, most existing studies do not focus on defensive driving as they only identify accidents ahead of the vehicle in which they are not involved. In this paper, a driving assistance system is proposed to predict the risk score of potential targets ahead of the vehicle and provide an early warning, which relies on a deep architecture called Fusion-Residual Predictive Network (FRPN) that fused multi-scale residual features and improved adversarial learning. This architecture provides an environment for the generator to perform joint learning from ground-truth images and discriminators with gradient penalty constraints. The deeper convolutional neural network can greatly improve the quality of the image by fusing residual features. Several deep convolutional neural network models were used to evaluate the method on various datasets; among them, the prediction model based on the VGG network, with peak signal-to-noise ratio of 32.67 and structural similarity index of 0.921, respectively, yielded the best results. Subsequently, we utilize the tracking model to design a risk score evaluation method based on the location of the target and it have an improvement in ability to give early warning with 1.95s earlier in the best case. These results prove that our method can effectively reduce the risk of traffic accidents.

13 October 2021 in IEEE Access
Verified
Journal Article
Open access
HFHao Fang
Hao Fang
JLJun-Qing Liu
Jun-Qing Liu
KXKai Xie
Kai Xie
PWPeng Wu
Peng Wu
XZXin-Yu Zhang
Xin-Yu Zhang
JHJian-Biao He
Jian-Biao He
Head pose estimation based on a single image is a challenging endeavor because of the complex background conditions and characteristics of the human face. In this report, we propose a Multi stage Regression-Capsule Network (MR-CapsNet) to predict head posture based on a single image input. In the study, we used the residual attention block and squeeze-and-excitation block to extract features in three levels. CapsNet overcomes the shortcomings of the traditional convolutional neural network and implements module aggregation to describe the spatial relationship of features after aggregation, in addition to realizing a compact and robust model using a multi-stage regression scheme. We tested our method on the AFLW2000 and BIWI datasets obtaining mean absolute errors of 4.26% and 3.95%, respectively. In addition, we discuss the accuracy of our method in the case of eye or mouth occlusion. The results of comprehensive experiments reveal that our method can accurately predict head posture.

22 June 2022 in IEEE Access
Verified
Journal Article
Open access
XZXin-Yu Zhang
Xin-Yu Zhang
KXKai Xie
Kai Xie
MLMei-Ran Li
Mei-Ran Li
CWChang Wen
Chang Wen
JHJian-Biao He
Jian-Biao He
Image inpainting techniques have been greatly improved by relying on structure and texture priors. However, damaged original images or rough predictions cannot provide sufficient texture information and accurate structural priors, leading to a drop in image quality. Moreover, from the perspective of human visual perception, it is important to pay attention to facial symmetry and facial attribute consistency. In this paper, we present a face inpainting system with iteration structure, guided by generative facial priors contained in pretrained GANs and predicted semantic information. Specifically, generative facial priors generated by the GAN inversion techniques introduce sufficient textures and features to assist inpainting; semantic maps are able to provide facial structural information and semantic categories of different pixels for face reconstruction. In particular, we iteratively refine images multiple times, updating semantic maps at each iteration. The Weighted Prior-Guidance Modulation layer (WPGM) is devised for incorporating priors into networks through spatial modulation. We also propose facial feature self-symmetry loss to constrain the symmetry of faces in feature space. Experiments on CelebA-HQ and LaPa datasets demonstrate the superiority of our model for facial detail and attribute consistency. Meanwhile, under the background of COVID-19, it is worth trying recognition via inpainting to deal with recognition challenges brought by mask occlusion. Relevant experiments show that our inpainting model does help to recognition tasks to a certain degree, with higher accuracy.