Simultaneous Feature and Sample Reduction for Image-Set Classification
Authors: Man Zhang, Ran He, Dong Cao, Zhenan Sun, Tieniu Tan
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on three commonly used image-set datasets show that the proposed method for the tasks of face recognition from image sets is efficient and effective. |
| Researcher Affiliation | Academia | Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition, Institute of Automation, CAS Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing 100190, China |
| Pseudocode | Yes | Algorithm 1: Simultaneous Feature and Sample Reduction (SFSR) |
| Open Source Code | No | The paper does not provide any explicit statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | Experiments are performed on two standard image-set classification datasets, i.e., the Honda/UCSD dataset (Lee et al. 2003), the CMU Mobo Dataset (Gross and Shi 2001), and one large-scale dataset (the number of comparisons is larger than 900 million), i.e., the You Tube Celebrities Dataset (Kim et al. 2008). |
| Dataset Splits | Yes | We make use of the standard training/testing protocol in (Wang et al. 2008)(Zhang, He, and Davis 2014): 20 sequences are used for training and the remaining 39 sequences for testing. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., GPU/CPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers, such as programming languages or libraries, used for the implementation or experiments. |
| Experiment Setup | Yes | Throughout this paper, λ1 and λ2, training and selected based on the datasets, are empirically set to 1 and 0.1, respectively. ... Initialize B0 by PCA+ITQ |