ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Scripted Video Generation With a Bottom-Up Generative Adversarial Network

Chen, Qi; Wu, Qi; Chen, Jian; Wu, Qingyao; van den Hengel, Anton; Tan, Mingkui*
IEEE Transactions on Image Processing2020DOI: 10.1109/TIP.2020.3003227
12被引9阅读
引用收藏
分享

摘要

Generating videos given a text description (such as a script) is non-trivial due to the intrinsic complexity of image frames and the structure of videos. Although Generative Adversarial Networks (GANs) have been successfully applied to generate images conditioned on a natural language description, it is still very challenging to generate realistic videos in which the frames are required to follow both spatial and temporal coherence. In this paper, we propose a novel Bottom-up GAN (BoGAN) method for generating videos given a text description. To ensure the coherence of the generated frames and also make the whole video match the language descriptions semantically, we design a bottom-up optimisation mechanism to train BoGAN. Specifically, we devise a region-level loss via attention mechanism to preserve the local semantic alignment and draw details in different sub-regions of video conditioned on words which are most relevant to them. Moreover, to guarantee the matching between text and frame, we introduce a frame-level discriminator, which can also maintain the fidelity of each frame and the coherence across frames. Last, to ensure the global semantic alignment between whole video and given text, we apply a video-level discriminator. We evaluate the effectiveness of the proposed BoGAN on two synthetic datasets (i.e., SBMG and TBMG) and two real-world datasets (i.e., MSVD and KTH).

学科与关键词

关键词
Generative adversarial networksvideo generationsemantic alignmenttemporal coherence
相关
加载中…
  • Diverse video captioning through latent variable expansion
    Xiao, Huanhou; Shi, Jinglun*PATTERN RECOGNITION LETTERS, 2022, 160: 19-25.被引 2
  • Attentional Generative Adversarial Networks With Representativeness and Diversity for Generating Text to Realistic Image
    Tian, Anjie; Lu, Lu*IEEE Access, 2020, 8: 9587-9596.被引 1
  • Verbal-Person Nets: Pose-Guided Multi-Granularity Language-to-Person Generation
    Liu, Deyin; Wu, Lin*; Zheng, Feng; Liu, Lingqiao; Wang, MengIEEE Transactions on Neural Networks and Learning Systems, 2023, 34(11): 8589-8601.被引 11
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Image Processing
发表日期
2020
卷期
第 29 卷
页码
7454-7467
DOI
10.1109/TIP.2020.3003227
语言
ENGLISH
期刊收录
NSL.SCIE
期刊等级
1区
成果收录
SCIE
资助标注
Key-Area Research and Development Program of Guangdong Province [2018B010107001]; National Natural Science Foundation of China (NSFC) through the Key Project [61836003]; Guangdong Project [2017ZT07X183]; Fundamental Research Funds for the Central Universities [D2191240]; Guangdong Basic and Applied Basic Research Foundation [2019B1515130001]; Guangdong Special Branch Plans Young Talent with Scientific and Technological Innovation [2016TQ03X445]; Guangzhou Science and Technology Planning Project [201904010197]

作者

  • C

    Chen, Qi (第一作者)

  • W

    Wu, Qi

查看全部 6 位作者收起作者
  • C

    Chen, Jian

  • W

    Wu, Qingyao

  • v

    van den Hengel, Anton

  • T

    Tan, Mingkui (通讯)

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417