期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
卷 32, 期 7, 页码 4390-4403出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2021.3128214
关键词
Benchmark testing; Motion pictures; Cameras; Videos; Surveillance; Task analysis; Annotations; Person re-identification; person retrieval; person recognition; benchmark
资金
- Grant of China Postdoctoral Science Foundation [2019M660209]
This article introduces a large-scale spatio-temporal person re-identification dataset called LaST, which has larger spatial and temporal ranges and more challenging re-ID environments compared to existing datasets. The authors evaluate 14 re-ID algorithms on LaST and propose an easy-to-implement baseline algorithm. The article also demonstrates that models pre-trained on LaST can generalize well to existing datasets with short-term and cloth-changing scenarios.
Person re-identification (re-ID) in the scenario with large spatial and temporal spans has not been fully explored. This fact partially occurs because existing benchmark datasets were mainly collected with limited spatial and temporal ranges, e.g., using videos recorded in a few days by cameras in a specific region of the campus. Such limited spatial and temporal ranges make it hard to simulate the difficulties of person re-ID in real scenarios. In this work, we contribute a novel Large-scale Spatio-Temporal (LaST) person re-ID dataset, including 10,862 identities with more than 228k images. Compared with existing datasets, LaST presents more challenging and high-diversity re-ID settings and significantly larger spatial and temporal ranges. For instance, each person can appear in different cities or countries, and in various time slots from day to evening, and in different seasons from spring to winter. To our best knowledge, LaST is a novel person re-ID dataset with the largest spatio-temporal ranges. Based on LaST, we verified its challenge by conducting a comprehensive performance evaluation of 14 re-ID algorithms. We further propose an easy-to-implement baseline that works well in such challenging re-ID settings. We also verified that models pre-trained on LaST can generalize well on existing datasets with short-term and cloth-changing scenarios. We expect LaST to inspire future works toward more realistic and challenging re-ID tasks. More information about the dataset is available at https://github.com/shuxjweb/last.git.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据