Dynamic Graph Representation for Occlusion Handling in Biometrics

Authors: Min Ren, Yunlong Wang, Zhenan Sun, Tieniu Tan11940-11947

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments conducted on iris and face demonstrate the superiority of the proposed framework, which boosts the accuracy of occluded biometrics recognition by a large margin comparing with baseline methods.
Researcher Affiliation Academia 1University of Chinese Academy of Sciences, 2CRIPAC NLPR CASIA, Beijing, P.R. China
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.
Open Datasets Yes Four databases are used for experiments: (1) ND Cross Sensor Iris 2013 Dataset-LG4000. It contains 29,986 iris samples from 1,352 classes. (2) CASIA Iris Image Database V4-Distance. It contains 2,446 iris samples from 284 classes. (3) CASIA-Iris-M1-S2. It contains 6,000 iris samples from 400 classes. (4) CASIA Iris Image Database V4-Lamp. This database contains 16,212 iris samples from 819 classes. [...] The CASIA-Web Face (Yi et al. 2014) is adopted as the training database.
Dataset Splits No The paper mentions training and testing sets, but does not explicitly detail a separate validation dataset split with specific percentages or counts.
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 does not provide specific ancillary software details with version numbers.
Experiment Setup No The paper describes the architecture of the convolutional blocks (e.g., 'Conv Block 1 contains four convolutional layers'), but does not provide specific experimental setup details such as hyperparameters (learning rate, batch size, epochs, optimizers).