Super-resolution-based part collaboration network for vehicle re-identification

Li, Jianming; Cong, Yue; Zhou, Luping; Tian, Zhihong; Qiu, Jing

doi:10.1007/s11280-022-01060-z

Cited by 8 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consider Gope and Hwang's scheme as an example-when an attacker obstructs the transmitted message returned by the sensor node, the GWN and sensornode hash values become asynchronous. Thus, designing a lightweight authentication scheme that achieves user anonymity, forward secrecy, and resistance to asynchronization attacks simultaneously is a significant challenge for WSNs [38]. To meet these security requirements, researchers have proposed numerous lightweight anonymous authentication schemes with forward secrecy.…”

Section: Related Workmentioning

confidence: 99%

An Anonymous Authentication Scheme Based on Chinese Residue Theorem in Wireless Body Area Networks

et al. 2023

View full text Add to dashboard Cite

Considering the resource limitations of low-cost wireless sensors, there is a growing inclination to utilize cryptographic primitives that are optimized for efficiency, such as symmetric key encryption/decryption and hash functions, when designing authentication schemes. However, designing a lightweight authentication scheme that can meet various security requirements poses a significant challenge. In recent years, numerous lightweight authentication schemes have been proposed in order to address these security needs. Nevertheless, recent research has revealed that many of these schemes exhibit security vulnerabilities and design deficiencies, including challenges related to asynchronization and impractical gateway-node search operations. Due to the inadequate security of existing schemes, this study introduces a novel privacy-preserving authentication scheme that aims to provide adaptive resilience against desynchronization attacks in wireless body area networks (WBANs). The proposed scheme utilizes lightweight cryptographic modules to optimize efficiency. To ensure user anonymity, the Chinese Remainder Theorem technique is employed, whereas forward secrecy and resistance to desynchronization attacks are achieved through the use of one-way hash chains and serial numbers, respectively. Through extensive analysis and comparisons, the proposed scheme is demonstrated to strike a fine balance between security and efficiency.

show abstract

Section: Related Workmentioning

confidence: 99%

An Anonymous Authentication Scheme Based on Chinese Residue Theorem in Wireless Body Area Networks

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Currently, there are many fault localization methods for program crashes and program logic errors [10][11][12][13][14]. However, there is less research on module loss errors and framework interface layer errors in runtime errors.…”

Section: Introductionmentioning

confidence: 99%

Source File Tracking Localization: A Fault Localization Method for Deep Learning Frameworks

Ma,

Yang,

Zhang

2023

Electronics

View full text Add to dashboard Cite

Deep learning has been widely used in computer vision, natural language processing, speech recognition, and other fields. If there are errors in deep learning frameworks, such as missing module errors and GPU/CPU result discrepancy errors, it will cause many application problems. We propose a source-based fault location method, SFTL (Source File Tracking Localization), to improve the fault location efficiency of these two types of errors in deep learning frameworks. We screened 3410 crash reports on GitHub and conducted fault location experiments based on those reports. The experimental results show that the SFTL method has a high accuracy, which can help deep learning framework developers quickly locate faults and improve the stability and reliability of models.

show abstract

“…Vehicle re-identification (ReID) [ 1 ], including cross-camera recognition and vehicle placement and tracking, is critical for road safety and intelligent transportation [ 2 ]. Re-identification refers to recognizing the same vehicles in non-overlapping view domains and across camera networks [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

Learning for Data Synthesis: Joint Local Salient Projection and Adversarial Network Optimization for Vehicle Re-Identification

Chen

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

The problem of vehicle re-identification in surveillance scenarios has grown in popularity as a research topic. Deep learning has been successfully applied in re-identification tasks in the last few years due to its superior performance. However, deep learning approaches require a large volume of training data, and it is particularly crucial in vehicle re-identification tasks to have a sufficient amount of varying image samples for each vehicle. To collect and construct such a large and diverse dataset from natural environments is labor intensive. We offer a novel image sample synthesis framework to automatically generate new variants of training data by augmentation. First, we use an attention module to locate a local salient projection region in an image sample. Then, a lightweight convolutional neural network, the parameter agent network, is responsible for generating further image transformation states. Finally, an adversarial module is employed to ensure that the images in the dataset are distorted, while retaining their structural identities. This adversarial module helps to generate more appropriate and difficult training samples for vehicle re-identification. Moreover, we select the most difficult sample and update the parameter agent network accordingly to improve the performance. Our method draws on the adversarial networks strategy and the self-attention mechanism, which can dynamically decide the region selection and transformation degree of the synthesis images. Extensive experiments on the VeRi-776, VehicleID, and VERI-Wild datasets achieve good performance. Specifically, our method outperforms the state-of-the-art in MAP accuracy on VeRi-776 by 2.15%. Moreover, on VERI-Wil, a significant improvement of 7.15% is achieved.

show abstract

Super-resolution-based part collaboration network for vehicle re-identification

Cited by 8 publications

References 44 publications

An Anonymous Authentication Scheme Based on Chinese Residue Theorem in Wireless Body Area Networks

An Anonymous Authentication Scheme Based on Chinese Residue Theorem in Wireless Body Area Networks

Source File Tracking Localization: A Fault Localization Method for Deep Learning Frameworks

Learning for Data Synthesis: Joint Local Salient Projection and Adversarial Network Optimization for Vehicle Re-Identification

Contact Info

Product

Resources

About