A part power set model for scale-free person retrieval
Shen, Yunhang; Ji, Rongrong; Hong, Xiaopeng; Zheng, Feng; Guo, Xiaowei; Wu, Yongjian; Huang, Feiyue (2019-08-10)
Shen, Y., Ji, R., Hong, X., Zheng, F., Guo, X., Wu, Y., & Huang, F. (2019). A Part Power Set Model for Scale-Free Person Retrieval. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. Presented at the Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. https://doi.org/10.24963/ijcai.2019/471
© International Joint Conferences on Artificial Intelligence Organization 2019. The Definitive Version of Record can be found online at: https://doi.org/10.24963/ijcai.2019/471.
https://rightsstatements.org/vocab/InC/1.0/
https://urn.fi/URN:NBN:fi-fe2020062645825
Tiivistelmä
Abstract
Recently, person re-identification (re-ID) has attracted increasing research attention, which has broad application prospects in video surveillance and beyond. To this end, most existing methods highly relied on well-aligned pedestrian images and hand-engineered part-based model on the coarsest feature map. In this paper, to lighten the restriction of such fixed and coarse input alignment, an end-to-end part power set model with multi-scale features is proposed, which captures the discriminative parts of pedestrians from global to local, and from coarse to fine, enabling part-based scale-free person re-ID. In particular, we first factorize the visual appearance by enumerating $k$-combinations for all $k$ of $n$ body parts to exploit rich global and partial information to learn discriminative feature maps. Then, a combination ranking module is introduced to guide the model training with all combinations of body parts, which alternates between ranking combinations and estimating an appearance model. To enable scale-free input, we further exploit the pyramid architecture of deep networks to construct multi-scale feature maps with a feasible amount of extra cost in term of memory and time. Extensive experiments on the mainstream evaluation datasets, including Market-1501, DukeMTMC-reID and CUHK03, validate that our method achieves the state-of-the-art performance.
Kokoelmat
- Avoin saatavuus [31657]