muSSP: Efficient Min-cost Flow Algorithm for Multi-object Tracking

Authors: Congchao Wang, Yizhi Wang, Yinxue Wang, Chiung-Ting Wu, Guoqiang Yu

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

Reproducibility Variable Result LLM Response
Research Type Experimental We conducted three sets of experiments for the detailed analysis of efficiency improvement.
Researcher Affiliation Academia Department of Electrical and Computer Engineering, Virginia Tech {ccwang, yzwang, yxwang90, ctwu, yug}@vt.edu
Pseudocode No The paper provides flowcharts and diagrams to illustrate the algorithm, but no explicit pseudocode blocks or algorithms labeled as such.
Open Source Code No The paper does not provide any statement about releasing source code or a link to a code repository for the methodology described.
Open Datasets Yes We selected four public datasets including three natural image MOT datasets (ETHZ (BAHNHOF and JELMOLI) [8], KITTI-Car [11], MOT CVPR 2019 Challenge[6]) and one particle tracking dataset (ISBI12 Particle Tracking Challenge (PTC) [5]).
Dataset Splits No The paper mentions using public datasets and detection results from them but does not specify any training, validation, or test dataset splits.
Hardware Specification Yes All the experiments were based on... on a single core of 2.40GHz Xeon(R) CPU E5-2630.
Software Dependencies No The paper mentions that 'SSP and our mu SSP were implemented in C++' and 'Follow Me was re-implemented from their python package in C++', but it does not specify any version numbers for compilers, libraries, or other software dependencies.
Experiment Setup Yes The graph has 5866 vertices and 36688 edges, and the algorithm runs totally 400 iterations.