Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks

Authors: Feiwu Yu, Xinxiao Wu, Yuchao Sun, Lixin Duan

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

Reproducibility Variable Result LLM Response
Research Type Experimental Comprehensive experiments on two challenging video recognition datasets (i.e. UCF101 and HMDB51) demonstrate the effectiveness of the proposed method when compared with the existing state-of-the-art domain adaptation methods.
Researcher Affiliation Academia Feiwu Yu1, Xinxiao Wu1 , Yuchao Sun1, Lixin Duan2 1 Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology 2 Big Data Research Center, University of Electronic Science and Technology of China {yufeiwu,wuxinxiao,sunyuchao}@bit.edu.cn, lxduan@uestc.edu.cn
Pseudocode Yes Algorithm 1: Hierarchical Generative Adversarial Networks
Open Source Code No The paper does not provide any concrete access information (link, explicit statement of release) to the source code for the methodology described.
Open Datasets Yes To evaluate the performance of our method, we conduct the experiments on two complex video datasets, i.e., UCF101 [Soomro et al., 2012] and HMDB51 [Yao et al., 2011]. For the UCF101 as the target video domain, the source images come from the Stanford40 dataset [Yao et al., 2011]. For the HMDB51 as the target video domain, the source image domain consists of Standford40 dataset and HII dataset [Tanisik et al., 2016], denoted by EADs dataset.
Dataset Splits Yes We split each target video into 16-frame clips without overlap, and all the clips from all the target videos construct the video-clip domain... For each dataset, we repeat the sampling for 5 times and report the average results.
Hardware Specification No The paper does not provide specific hardware details such as GPU/CPU models, memory, or detailed computer specifications used for running experiments. It mentions 'implemented based on the Caffe framework' but no hardware.
Software Dependencies No The paper mentions software like 'Caffe framework' and 'Adam solver' but does not provide specific version numbers for these or any other ancillary software components.
Experiment Setup Yes To model the two generators in Hi GAN, we deploy four-layered feed-forward neural networks activated by relu function, (i.e., 2048 1024 1024 1024 512 for Gl(f; θGl) and 512 1024 1024 2048 2048 for Gh(vf; θGh))... we set λ2 = λ4 = 100, λ1 = λ3 = 1 in Eq. (8) and Eq. (9) for all the experiments... We employ the Adam solver [Kingma and Ba, 2014] with a batch size of 64. All the networks were trained from scratch with the learning rate of 0.00002 for the low-level conditional GAN and 0.000008 for high-level conditional GAN.