Visual Data Synthesis via GAN for Zero-Shot Video Classification

Authors: Chenrui Zhang, Yuxin Peng

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on four video datasets demonstrate that our approach can improve the zero-shot video classification performance significantly.
Researcher Affiliation Academia Institute of Computer Science and Technology, Peking University, Beijing 100871, China
Pseudocode Yes Algorithm 1 Training process of the proposed framework
Open Source Code No The paper links to PyTorch (1http://pytorch.org/) but does not provide a specific link or statement about releasing the source code for their proposed methodology.
Open Datasets Yes HMDB51 [Kuehne et al., 2013], UCF101 [Soomro et al., 2012], Olympic Sports [Niebles et al., 2010] and Columbia Consumer Video (CCV) [Jiang et al., 2011]
Dataset Splits Yes 50/50 for every dataset, i.e., video feature of 50% categories are used for model training and the other 50% categories are held unseen until test time. We take the average accuracy and standard deviation as evaluation metrics and report the results over 50 independent splits generated randomly.
Hardware Specification No The paper does not explicitly mention the hardware specifications (e.g., specific GPU or CPU models) used for running the experiments.
Software Dependencies No Our model is implemented with PyTorch1. We adopt GloVe [Pennington et al., 2014] trained on Wikipedia with more than 2.2 million unique vocabularies to obtain semantic embedding and its dimension is 300.
Experiment Setup Yes We train our framework for 300 epochs using Adam optimizer with momentum 0.9. We initialize the learning rate to 0.01 and decay it every 50 epochs by a factor of 0.5. Both λ1 and λ2 are set to 1.