A Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance

By Xinchen Liu, Wu Liu, Tao Mei, Huadong Ma. European Conference on Computer Vision, 2016

566 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/027f6e9b9c196747d2cc7fad42d07940f00486bb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Xiaogang Wang
2. Yi Yang
3. Luc Van Gool
4. Hongsheng Li
5. Dacheng Tao
6. Ming-Hsuan Yang
7. Wanli Ouyang
8. Bernt Schiele

In Media Technology

1. Tao Mei
2. Hongsheng Li
3. Shuai Yi
4. Xiaogang Wang
5. Wu Liu
6. Xinchen Liu
7. Huadong Ma
8. Jing Shao

Citations in the corpus

• Metaverse for Social Good: A University Campus Prototype (2021, background): “AI facilitates our physical lives in many areas, including intelligent transportation [20], smart healthcare [26], environmental monitoring [19], and public safety [13].”
• CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification (2019, methodology): “VeRi-776 [29] has been the most widely used benchmark for vehicle ReID, because of the high quality of annotations and the availability of camera geometry.”
• VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild (2019, methodology): “The straightforward method is to identify vehicles by the recognition of license plates [10][4].”
• PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance (2018, methodology): “For each query, the left three rows are the results of FACT, FACT+Plate-SNN, and FACT+Plate-SNN+STR in [22],”
• Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID (2020, unknown): “Dataset # train IDs # train images # test IDs # query images # cameras # total images Market-1501 [58] 751 12,936 750 3,368 6 32,217 MSMT17 [46] 1,041 32,621 3,060 11,659 15 126,441 PersonX [39]* 410 9,840 856 5,136 6 45,792 VeRi-776 [28] 575 37,746 200 1,678 20 51,003 VehicleID [27] 13,164 113,346 ”
• An Edge Traffic Flow Detection Scheme Based on Deep Learning in an Intelligent Transportation System (2021, methodology): “We trained the network on a vehicle reidentification dataset (VeRi [51], [52] dataset).”
• Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-Temporal Path Proposals (2017, methodology): “Note that our approach did not utilize the plate information in the images as that in [28].”
• Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification (2017, methodology): “Datasets used for training the proposed model, including (a) VeRi-776 [9], (b) VehicleID [8], (c) BoxCars21k [17],and (d) CompCars [23].”