Metric Embedded Discriminative Vocabulary Learning for High-Level Person Representation

Authors: Yang Yang, Zhen Lei, Shifeng Zhang, Hailin Shi, Stan Li

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experimental results on person re-identification demonstrate the effectiveness of our proposed algorithm.
Researcher Affiliation Academia Yang Yang, Zhen Lei, Shifeng Zhang, Hailin Shi, Stan Z. Li Center for Biometrics and Security Research & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China {yang.yang, zlei, shifeng.zhang, hailin.shi, szli}@nlpr.ia.ac.cn
Pseudocode Yes Algorithm 1 Metric Embedded Discriminative Vocabulary Learning
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes VIPe R dataset (Gray, Brennan, and Tao 2007), PRID 450S dataset (Roth et al. 2014)
Dataset Splits No In all experiments, half image pairs are randomly selected for training and the remaining are employed for test. The paper specifies train and test splits, but does not explicitly mention a separate validation split.
Hardware Specification No The paper does not provide specific hardware details (like GPU/CPU models or memory) used for running its experiments.
Software Dependencies No The paper mentions general software or tools but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes In our evaluations, we set α and β in Eq 8 to 0.5 and 0.2, respectively. The number of basis vectors in B is set to 120 and the iteration number T to 4. Before using KISSME, we employ PCA to reduce the 120-dimensional high-level features to 70 for both datasets. When SAC is compared, we set γ to 0.05.