Direct Measure Matching for Crowd Counting

Authors: Hui Lin, Xiaopeng Hong, Zhiheng Ma, Xing Wei, Yunfeng Qiu, Yaowei Wang, Yihong Gong

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on four challenging crowd counting datasets namely Shanghai Tech, UCF-QNRF, JHU++ and NWPU have validated the proposed method.
Researcher Affiliation Collaboration Hui Lin1 , Xiaopeng Hong1,4 , Zhiheng Ma2 , Xing Wei3 , Yunfeng Qiu3 , Yaowei Wang4 , Yihong Gong3 1School of Cyber Science and Engineering, Xi an Jiaotong University; 2College of Artificial Intelligence, Xi an Jiaotong University; 3School of Software Engineering, Xi an Jiaotong University; 4Pengcheng Laboratory, Shenzhen
Pseudocode Yes Algorithm 1: S3 Optimization
Open Source Code No The paper states that the code is implemented by Pytorch but does not provide any link or explicit statement about releasing the source code for the described method.
Open Datasets Yes Shanghai Tech [Zhang et al., 2016]... UCF-QNRF [Idrees et al., 2018]... JHU-CROWD++ [Sindagi et al., 2020]... NWPU-CROWD [Wang et al., 2020b]
Dataset Splits Yes Shanghai Tech [Zhang et al., 2016] includes Part A and Part B. In Part A... 300 images are divided for training and the remaining 182 images are for testing. In Part B... 400 images are divided for training and the remaining 316 images are for testing. UCF-QNRF [Idrees et al., 2018]... The training set contains 1,201 images and the testing set includes the rest 334 images. JHU-CROWD++ [Sindagi et al., 2020] includes 4,372 images with 1.51 million annotated points. 2,272 images are chosen for training; 500 images are for validation; and the rest 1,600 images are for testing. NWPU-CROWD [Wang et al., 2020b]... 3,109 images are divided into training set; 500 images are in validation set; and the remaining 1,500 images are in testing.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments (e.g., GPU models, CPU types).
Software Dependencies No The paper mentions 'Pytorch' but does not provide a specific version number for it or any other software dependencies.
Experiment Setup No The paper does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or system-level training settings needed for reproduction.