Deconvolutional Generative Adversarial Networks with Application to Video Generation | |
Yu HY(俞宏远)1,3; Huang Y(黄岩)1,3; Pi, Lihong2; Wang L(王亮)1,3 | |
2019 | |
会议日期 | 2019年 |
会议地点 | 西安 |
英文摘要 | This paper proposes a novel model for video generation and especially makes the attempt to deal with the problem of video generation from text descriptions, i.e., synthesizing realistic videos conditioned on given texts. Existing video generation methods cannot be easily adapted to handle this task well, due to the frame discontinuity issue and their text-free generation schemes. To address these problems, we propose a recurrent deconvolutional generative adversarial network (RD-GAN), which includes a recurrent deconvolutional network (RDN) as the generator and a 3D convolutional neural network (3D-CNN) as the discriminator. The RDN is a deconvolutional version of conventional recurrent neural network, which can well model the long-range temporal dependency of generated video frames and make good use of conditional information. The proposed model can be jointly trained by pushing the RDN to generate realistic videos so that the 3D-CNN cannot distinguish them from real ones. We apply the proposed RD-GAN to a series of tasks including conventional video generation, conditional video generation, video prediction and video classification, and demonstrate its effectiveness by achieving well performance. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48520] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Wang L(王亮) |
作者单位 | 1.自动化研究所,NLPR,CRIPAC 2.The Institute of Microelectronics, Tsinghua University (THU) 3.中国科学院大学 |
推荐引用方式 GB/T 7714 | Yu HY,Huang Y,Pi, Lihong,et al. Deconvolutional Generative Adversarial Networks with Application to Video Generation[C]. 见:. 西安. 2019年. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论