Learning Neural Bag-of-Matrix-Summarization with Riemannian Network

Authors: Hong Liu, Jie Li, Yongjian Wu, Rongrong Ji8746-8753

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on four different classification tasks demonstrate the superior performance of the proposed method over the state-of-the-art methods.
Researcher Affiliation Collaboration Fujian Key Laboratory of Sensing and Computing for Smart City, Department of Cognitive Science, School of Information Science and Engineering, Xiamen University, Xiamen, China Peng Cheng Laboratory, Shenzhen, China Tencent Youtu Lab, Tencent Technology (Shanghai) Co.,Ltd, Shanghai, China
Pseudocode No No pseudocode or clearly labeled algorithm blocks were found in the paper.
Open Source Code No No explicit statement providing access to the source code for the methodology described in this paper was found.
Open Datasets Yes We use Acted Facial Expression in the Wild (AFEW) dataset, which collects 1, 345 video sequences of facial expressions acted by 330 actors in movies. This dataset has been divided into training, validation, and test sets, where each video is classified into one of seven expressions. Since the ground truth of the test set has not been released, we follow the setting in (Liu et al. 2014; Huang and Van Gool 2017) to evaluate the performance on the validation set. [...] We further evaluate the classification performance on the BCI Competition IV dataset 2a (BCI) 3, which is a 22-electrode EEG motor-imagery dataset. It consists of 9 subjects and 2 sessions, each subject of which has 288 four-second trials of imagined movements. [...] 3http://www.bbci.de/competition/iv/
Dataset Splits Yes This dataset has been divided into training, validation, and test sets, where each video is classified into one of seven expressions. [...] The dataset is randomly split into a training set and a testing set, with a splitting ratio of 1 : 2.
Hardware Specification Yes We implement our Riemannian Network with Bo MS using Pytorch on a single PC with Dual Core I7-3421 and 128G memory.
Software Dependencies No The paper mentions 'Pytorch' but does not specify its version number or any other software dependencies with version details.
Experiment Setup Yes We use the stochastic gradient descent to update the network parameters, and the learning rate is set to 1 × 10−3 with 5 × 10−4 weight decay. The batch size is set to 30, the weights are initialized as random semi-orthogonal matrices, as similar to the SPDNet.