Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (6) · 5901-5909
DOI: 10.1609/aaai.v39i6.32630 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Kai Lv und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
Vehicle re-identification aims to match vehicles across non-overlapping camera views. Many existing methods extract features from one specific image, and these methods lack view-invariance when comparing vehicles of different orientations. As a result, discriminative parts obscured by viewpoint changes cannot contribute effectively to matching. This work presents a novel keypoint-based framework for vehicle Re-ID. We propose to explicitly model the intrinsic structural relationships between vehicle components via knowledge graph. By establishing connection between keypoints, our approach aims to leverage such prior to match vehicles even when some parts are not directly comparable due to orientation inconsistencies. Specifically, given query and gallery images, we first detect visible keypoints. Then, a transformer-based model infers features for non-overlapped keypoints by conditioning on visible correspondences defined in the knowledge graph. The final representation integrates visible and inferred features. Extensive experiments demonstrate our method outperforms state-of-the-arts on standard benchmarks under cross-view matching scenarios. To our knowledge, this is the first work introducing structural priors via keypoint knowledge graphs for view-invariant vehicle re-identification.
Zitieren
APA
Lv, K., Li, Y., Chen, Z., Wang, S., Han, S., & Lin, Y. (2025). Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification. Proceedings of the AAAI Conference on Artificial Intelligence, 39(6), 5901-5909. https://doi.org/10.1609/aaai.v39i6.32630
Vancouver
Lv K, Li Y, Chen Z, Wang S, Han S, Lin Y. Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(6):5901-5909. doi:10.1609/aaai.v39i6.32630
BibTeX
@article{Lv2025,
author = {Lv, Kai and Li, Yunlong and Chen, Zhuo and Wang, Shuo and Han, Sheng and Lin, Youfang},
title = {Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {6},
pages = {5901--5909},
doi = {10.1609/aaai.v39i6.32630}
}
EUVIMED