A Multiview-Based Parameter Free Framework for Group Detection

Authors: Xuelong Li, Mulin Chen, Feiping Nie, Qi Wang

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on various real world datasets demonstrate the effectiveness of the proposed approach, and show its superiority against state-of-the-art group detection techniques.
Researcher Affiliation Academia School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, Xi an 710072, Shaanxi, P. R. China
Pseudocode No The paper describes algorithmic steps and mathematical formulations for its methods, such as solving a quadratic programming problem or an iterative algorithm, but it does not present any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement about releasing open-source code or a link to a code repository for the methodology described.
Open Datasets Yes In this work, the CUHK Crowd Dataset (Shao, Loy, and Wang 2014) is used to verify the proposed framework s performance on group detection. The proposed SMC is evaluated on four standard multiview datasets, MSRC-v1 (Winn and Jojic 2005), Digits (van Breukelen et al. 1998), Caltech101-7 and Caltech101-20 (Li, Fergus, and Perona 2007).
Dataset Splits No The paper mentions using datasets for evaluation and comparison, but it does not specify any training, validation, or test dataset splits (e.g., percentages or specific subsets) nor does it describe a cross-validation setup.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments.
Software Dependencies No The paper mentions employing a 'generalized Kandae Lucas-Tomasi (g KLT) tracker' and referring to 'quadratic programming (QP) problem' solvers and 'convex optimization packages', but it does not list any specific software names with version numbers for reproducibility.
Experiment Setup No The paper discusses parameters like 'k' and 'r' and their impact on performance, and states that 'competitors use their respective optimal parameters,' but it does not provide concrete hyperparameters (e.g., learning rate, batch size) or detailed system-level training settings for its own methods or the comparisons.