Y Chen, X Hu, W Fan, L Shen, Z Zhang, X Liu… - Knowledge-Based …, 2020 - Elsevier
Abstract Density Peak (DPeak) clustering algorithm is not applicable for large scale data, due to two quantities, ie, ρ and δ, are both obtained by brute force algorithm with complexity …
We analyze the drawbacks of DBSCAN and its variants, and find the grid technique, which is used in Fast-DBSCAN and ρ-approximate DBSCAN, is almost useless in high dimensional …
F Shen, Y Xie, J Zhu, X Zhu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Transformers are more and more popular in computer vision, which treat an image as a sequence of patches and learn robust global features from the sequence. However, pure …
Z Zheng, T Ruan, Y Wei, Y Yang… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
One fundamental challenge of vehicle re-identification (re-id) is to learn robust and discriminative visual representation, given the significant intra-class vehicle variations …
Vehicle Re-identification (re-id) over surveillance camera network with non-overlapping field of view is an exciting and challenging task in intelligent transportation systems (ITS). Due to …
Y Chen, L Zhou, S Pei, Z Yu, Y Chen… - IEEE transactions on …, 2019 - ieeexplore.ieee.org
Large-scale data clustering is an essential key for big data problem. However, no current existing approach is “optimal” for big data due to high complexity, which remains it a great …
TS Chen, CT Liu, CW Wu, SY Chien - … , Glasgow, UK, August 23–28, 2020 …, 2020 - Springer
Vehicle re-identification (re-ID) focuses on matching images of the same vehicle across different cameras. It is fundamentally challenging because differences between vehicles are …
Z Yu, J Pei, M Zhu, J Zhang, J Li - Information Processing & Management, 2022 - Elsevier
With the continuous development of intelligent transportation systems, vehicle-related fields have emerged a research boom in detection, tracking, and retrieval. Vehicle re-identification …
F Shen, J Zhu, X Zhu, Y Xie… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Existing vehicle re-identification methods commonly use spatial pooling operations to aggregate feature maps extracted via off-the-shelf backbone networks, such as visual …