Learning Non-Uniform Hypergraph for Multi-Object Tracking

Authors: Longyin Wen, Dawei Du, Shengkun Li, Xiao Bian, Siwei Lyu8981-8988

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

Reproducibility Variable Result LLM Response
Research Type Experimental Several experiments are carried out on various challenging datasets (i.e., PETS09, Parking Lot sequence, Subway Face, and MOT16 benchmark), to demonstrate that our method achieves favorable performance against the state-of-the-art MOT methods.
Researcher Affiliation Collaboration 1JD Finance, Mountain View, CA, USA 2University at Albany, State University of New York, NY, USA 3GE Global Research, NY, USA
Pseudocode Yes Algorithm 1 Compute the local maximizer y
Open Source Code Yes The source code of the proposed method is available at https: //github.com/longyin880815.
Open Datasets Yes We conduct experiments on several popular MOT evaluation datasets, i.e., the multi-pedestrian tracking (Wen et al. 2016) (including the PETS09 and Parking Lot sequences), MOT2016 (Milan et al. 2016), and multi-face tracking (Wen et al. 2016) datasets
Dataset Splits No The paper mentions using a 'training set to learn the parameters' and 'testing set for evaluation', but does not explicitly describe a separate 'validation' dataset or split for hyperparameter tuning or model selection.
Hardware Specification Yes To demonstrate the running time of NT, we run it five times using a single thread on a laptop with a 2.8 GHz Intel processor and 16 GB memory.
Software Dependencies No The paper states, 'We implement the NT algorithm in C++ without any code optimization,' but does not provide specific version numbers for C++ or any libraries used.
Experiment Setup Yes We set D = 4 in our experiments, and the learned weights of different degree of hyperedge are λ1 = 0.58535, λ2 = [0.15576, 3.0332, 0.34388], λ3 = 1.2879, and λ4 = 0.22324. The batch size τ in near-online tracking is set to 7. The minimal size of the sub-hypergraph is set as ˆα = 2. We fix all parameters to these values in the experiments.