A Spatio-Temporal-Frequency Transformer Framework for Near-Field Target Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914396145451008 |
|---|---|
| author | Zhao, Zongyao Wang, Zhaolin Han, Lincong Jin, Jing Huang, Kaibin |
| author_facet | Zhao, Zongyao Wang, Zhaolin Han, Lincong Jin, Jing Huang, Kaibin |
| contents | A target recognition framework relying on near-field integrated sensing and communication (ISAC) systems is proposed. By exploiting the distance-dependent spatial signatures provided by the near-field spherical wavefront, high-accuracy sensing is realized in a bandwidth-efficient manner. A spatio--temporal--frequency (STF) transformer framework is introduced for target recognition using electromagnetic features found in the wireless channel response. In particular, a lightweight spatial encoder is employed to extract features from the antenna array for each frame and subcarrier. These features are then fused by a time-frequency transformer head with positional embeddings to model temporal dynamics and cross-subcarrier correlations. Simulation results demonstrate that strong target recognition performance can be achieved even with limited bandwidth resources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14829 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Spatio-Temporal-Frequency Transformer Framework for Near-Field Target Recognition Zhao, Zongyao Wang, Zhaolin Han, Lincong Jin, Jing Huang, Kaibin Signal Processing A target recognition framework relying on near-field integrated sensing and communication (ISAC) systems is proposed. By exploiting the distance-dependent spatial signatures provided by the near-field spherical wavefront, high-accuracy sensing is realized in a bandwidth-efficient manner. A spatio--temporal--frequency (STF) transformer framework is introduced for target recognition using electromagnetic features found in the wireless channel response. In particular, a lightweight spatial encoder is employed to extract features from the antenna array for each frame and subcarrier. These features are then fused by a time-frequency transformer head with positional embeddings to model temporal dynamics and cross-subcarrier correlations. Simulation results demonstrate that strong target recognition performance can be achieved even with limited bandwidth resources. |
| title | A Spatio-Temporal-Frequency Transformer Framework for Near-Field Target Recognition |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2603.14829 |