TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search
This work addresses the challenge of retrieving person images from textual descriptions, offering a practical solution for applications like surveillance, but it is incremental as it builds on existing local alignment methods with simplifications.
The paper tackles the problem of text-based person search by proposing TIPCB, a simple end-to-end framework that uses dual-path local alignment and multi-stage cross-modal matching, achieving state-of-the-art performance with improvements of 3.69%, 2.95%, and 2.31% in Top-1, Top-5, and Top-10 metrics on the CUHK-PEDES dataset.
Text-based person search is a sub-task in the field of image retrieval, which aims to retrieve target person images according to a given textual description. The significant feature gap between two modalities makes this task very challenging. Many existing methods attempt to utilize local alignment to address this problem in the fine-grained level. However, most relevant methods introduce additional models or complicated training and evaluation strategies, which are hard to use in realistic scenarios. In order to facilitate the practical application, we propose a simple but effective end-to-end learning framework for text-based person search named TIPCB (i.e., Text-Image Part-based Convolutional Baseline). Firstly, a novel dual-path local alignment network structure is proposed to extract visual and textual local representations, in which images are segmented horizontally and texts are aligned adaptively. Then, we propose a multi-stage cross-modal matching strategy, which eliminates the modality gap from three feature levels, including low level, local level and global level. Extensive experiments are conducted on the widely-used benchmark dataset (CUHK-PEDES) and verify that our method outperforms the state-of-the-art methods by 3.69%, 2.95% and 2.31% in terms of Top-1, Top-5 and Top-10. Our code has been released in https://github.com/OrangeYHChen/TIPCB.