Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning

Authors: Dezhao Luo, Chang Liu, Yu Zhou, Dongbao Yang, Can Ma, Qixiang Ye, Weiping Wang11701-11708

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on commonly used benchmarks show that the trained models outperform the state-of-the-art self-supervised models with significant margins.
Researcher Affiliation Academia 1Institute of Information Engineering, Chinese Academy of Sciences 2School of Cyber Security, University of Chinese Academy of Sciences 3University of Chinese Academy of Sciences
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes The experiments are conducted on UCF101 (Soomro, Zamir, and Shah 2012) and HMDB51 (Jhuang et al. 2011) datasets.
Dataset Splits No The paper refers to dataset usage and evaluation on splits (e.g., "fine-tune the action recognition model on UCF101", "The classification accuracy over 3 splits are averaged"), but it does not specify explicit percentages or sample counts for training/validation/test splits needed for reproduction.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with versions) needed to replicate the experiment.
Experiment Setup Yes We set the initial learning rate to be 0.01, momentum to be 0.9 and stop training after 300 epochs. ... Each frame is resized to 128 x 171 and randomly cropped to 112 x 112.