RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search

Authors: Yang Bai, Min Cao, Daming Gao, Ziqiang Cao, Chen Chen, Zhenfeng Fan, Liqiang Nie, Min Zhang

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments demonstrate that Ra Sa outperforms existing state-of-the-art methods by 6.94%, 4.45% and 15.35% in terms of Rank@1 on CUHK-PEDES, ICFG-PEDES and RSTPReid datasets, respectively.
Researcher Affiliation Academia 1School of Computer Science and Technology, Soochow University 2Institute of Automation, Chinese Academy of Sciences 3Institute of Computing Technology, Chinese Academy of Sciences 4Harbin Institute of Technology, Shenzhen
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Code is available at: https://github.com/Flame-Chasers/Ra Sa.
Open Datasets Yes We conduct experiments on three text-based person search datasets: CUHK-PEDES [Li et al., 2017], ICFG-PEDES [Ding et al., 2021] and RSTPReid [Zhu et al., 2021].
Dataset Splits No The paper mentions evaluating on 'test images' and discusses dataset usage, but it does not provide specific train/validation/test dataset split percentages, sample counts, or explicit citations for predefined splits in the main text.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions software components like ALBEF, TCL, CLIP, BERT, and Distil BERT, but does not provide specific version numbers for any of them.
Experiment Setup Yes The best result is achieved at pw = 0.1. ... Ra Sa performs best at pm = 0.3. ... Empirical results show that Ra Sa performs best when they are set as 0.5.