Scale-Adaptive Low-Resolution Person Re-Identification via Learning a Discriminating Surface

Authors: Zheng Wang, Ruimin Hu, Yi Yu, Junjun Jiang, Chao Liang, Jinqiao Wang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on two simulated datasets and one public dataset demonstrate the effectiveness of the proposed framework. In this section, we first demonstrate the influence brought by the scale-adaptive low-resolution problem. Then, the proposed method is evaluated.
Researcher Affiliation Academia 1State Key Laboratory of Software Engineering, School of Computer, Wuhan University, China 2Digital Content and Media Sciences Research Division, National Institute of Informatics, Japan 3School of Computer Science, China University of Geosciences, China 4National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences {wangzwhu, hrm, cliang}@whu.edu.cn, yiyu@nii.ac.jp, junjun0595@163.com, jqwang@nlpr.ia.ac.cn
Pseudocode No The paper describes the method procedurally in text (e.g., in Section 3) and visually in Figure 3, but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any statements about releasing source code or provide a link to a code repository.
Open Datasets Yes The evaluation is run on two simulated person datasets SALR-VIPe R and SALR-PRID, which are based on the VIPe R dataset [Gray et al., 2007] and the PRID450S dataset [Roth et al., 2014] respectively, and one public dataset the CAVIAR dataset [Cheng et al., 2011].
Dataset Splits Yes All datasets are randomly divided into training set and testing set. Persons for training and testing are respectively 532 and 100 (SALR-VIPe R), 400 and 50 (SALRPRID), and 44 and 10 (CAVIAR).
Hardware Specification No The paper does not specify any details about the hardware used for running the experiments.
Software Dependencies No The paper mentions methods like Random Forest, PCA, and KISSME but does not provide specific version numbers for any software, libraries, or programming languages used.
Experiment Setup Yes Feature Representation. In order to compare the distance of two images with different resolutions, we represent each image feature with the same dimension. As Sec.2 does, we divide each image, regardless of its resolution, into 24 patches (3 columns * 8 rows). For each patch, a 64 dimension HSV feature is extracted. Then, each image is represented by a 1536 dimension feature. To accelerate the process and reduce noise, we conducted principal component analysis (PCA) to obtain a relatively low dimensional representation, i.e. 300 for the SALR-VIPe R and SALR-PRID datasets, and 100 for the CAVIAR dataset.