Mirror Representation for Modeling View-Specific Transform in Person Re-Identification
Authors: Ying-Cong Chen, Wei-Shi Zheng, Jianhuang Lai
IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | we particularly show that kernel marginal fisher analysis significantly outperforms the current state-ofthe-art methods through extensive experiments on VIPe R, PRID450S and CUHK01. |
| Researcher Affiliation | Academia | Ying-Cong Chen , Wei-Shi Zheng , , , Jianhuang Lai , School of Information Science and Technology, Sun Yat-sen University, China Guangdong Provincial Key Laboratory of Computational Science Guandong Key Laboratory of Information Security Technology chyingc@mail2.sysu.edu.cn, wszheng@ieee.org, stsljh@mail.sysu.edu.cn |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described, such as a specific repository link, explicit code release statement, or code in supplementary materials. |
| Open Datasets | Yes | Our experiments were conducted on three publicably available datasets: PRID450S [Roth et al., 2014], VIPe R [Gray et al., 2007] and CUHK01 [Li et al., 2012]. |
| Dataset Splits | Yes | Our experiments follow the same single-shot protocol: each time half of the pedestrians were selected randomly to form the training set, and the remaining pedestrian images were used to form the gallery set and testing set. For CUHK01, each pedestrian has 2 images for each view; we randomly selected one of them to form the gallery. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers). |
| Experiment Setup | Yes | In order to balance the scale of the objective function when applying our mirror representation Eq. 9), λ is set as 10 6, 10 2, 10 2 and 0.5 for KPCCA, KMFA, PCCA and MFA respectively. To obtain statistically significant results, we repeated the procedure 10 times and reported the average results. |