Do the best of all together: Hierarchical spatial-frequency fusion transformers for animal re-identification
文献类型：期刊论文
| 作者 | Zheng, Wenbo1; Wang, Fei-Yue2
|
| 刊名 | INFORMATION FUSION
 |
| 出版日期 | 2025 |
| 卷号 | 113页码:24 |
| 关键词 | Animal re-identification Transformer Spatial-frequency feature learning Hierarchy |
| ISSN号 | 1566-2535 |
| DOI | 10.1016/j.inffus.2024.102612 |
| 通讯作者 | Zheng, Wenbo(zwb2022@whut.edu.cn) |
| 英文摘要 | Animal re-identification is fundamental in the ecology and ethology community for understanding the Earth's ecosystems. Due to the uncertainty of photographing animals in the wild, such as the position and angle of capture and the variations in animal individuals as well as in their poses and habitats, building image-based visual models for re-identifying animal individuals is a challenging task. We propose a novel framework, hierarchical spatial-frequency fusion transformers, , to address animal re-identification. We first use spatial and frequency representation learning to capture effective deep features and then employ hierarchical transformer-based representation learning to consolidate low-level detailed information into highlevel semantic information from a global perspective. Through this process, we construct a deeply supervised nonlinear aggregation method to enhance finer multi-scale, multi-level and cross-domain features. Our method illustrates the case of "do the best of all together", meaning that only when both the frequency and spatial domains are combined can we achieve the best performance. The experimental results demonstrate that our approach achieves significantly higher performance than other state-of-the-art methods. |
| WOS关键词 | NEURAL-NETWORKS |
| 资助项目 | Natural Science Foun-dation of China[62303361] ; Hainan Provincial Natural Science Foundation of China[623QN266] ; Hainan Provincial Natural Science Foundation of China[231002531131826] ; Fundamental Research Funds for the Central Universities, China[WUT: 233110002] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001291018000001 |
| 出版者 | ELSEVIER |
| 资助机构 | Natural Science Foun-dation of China ; Hainan Provincial Natural Science Foundation of China ; Fundamental Research Funds for the Central Universities, China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/59321]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
| 通讯作者 | Zheng, Wenbo |
| 作者单位 | 1.Wuhan Univ Technol, Sch Comp Sci & Artificial Intelligence, Wuhan 430070, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zheng, Wenbo,Wang, Fei-Yue. Do the best of all together: Hierarchical spatial-frequency fusion transformers for animal re-identification[J]. INFORMATION FUSION,2025,113:24. |
| APA | Zheng, Wenbo,&Wang, Fei-Yue.(2025).Do the best of all together: Hierarchical spatial-frequency fusion transformers for animal re-identification.INFORMATION FUSION,113,24. |
| MLA | Zheng, Wenbo,et al."Do the best of all together: Hierarchical spatial-frequency fusion transformers for animal re-identification".INFORMATION FUSION 113(2025):24. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。