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

Video captioning with text -based dynamic attention and step-by-step learning

Xiao, Huanhou; Shi, Jinglun*
PATTERN RECOGNITION LETTERS2020-5DOI: 10.1016/j.patrec.2020.03.001
10被引4阅读
引用收藏
分享

摘要

Automatically describing video content with natural language has been attracting much attention in computer vision and natural language processing communities. Most existing methods predict one word at a time, and by feeding the last generated word back as input at the next time, while the other generated words are not fully exploited. Furthermore, traditional methods optimize the model using all the training samples in each epoch without considering their learning situations, which leads to a lot of unnecessary training and can not target the difficult samples. To address these issues, we propose a text-based dynamic attention model named TDAM, which imposes a dynamic attention mechanism on all the generated words with the motivation to improve the context semantic information and enhance the overall control of the whole sentence. Moreover, the text-based dynamic attention mechanism and the visual attention mechanism are linked together to focus on the important words. They can benefit from each other during training. In addition, the model is trained through two steps: "starting from scratch" and "checking for gaps". The former uses all the samples to optimize the model, while the latter only trains for samples with poor control. Experimental results on the popular datasets MSVD and MSR-VTT demonstrate that our non-ensemble model outperforms the state-of-the-art video captioning benchmarks.

学科与关键词

关键词
Dynamic attentionContext semantic informationVideo captioning
相关
加载中…
  • Describing Video With Attention-Based Bidirectional LSTM
    Bin, Yi; Yang, Yang*; Shen, Fumin; Xie, Ning; Shen, Heng Tao; Li, XuelongIEEE Transactions on Cybernetics, 2019, 49(7): 2631-2641.被引 11
  • Exploring diverse and fine-grained caption for video by incorporating convolutional architecture into LSTM-based model
    Xiao, Huanhou; Xu, Junwei; Shi, Jinglun*PATTERN RECOGNITION LETTERS, 2020, 129: 173-180.被引 9
  • Stacked Multimodal Attention Network for Context-Aware Video Captioning
    Zheng, Yi; Zhang, Yuejie*; Feng, Rui; Zhang, Tao*; Fan, WeiguoIEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(1): 31-42.被引 12
查看全部 →

发表信息

论文状态
公开发表
期刊
PATTERN RECOGNITION LETTERS
发表日期
2020-05
卷期
第 133 卷
页码
305-312
DOI
10.1016/j.patrec.2020.03.001
语言
ENGLISH
期刊收录
NSL.SCIE
期刊等级
3区
成果收录
SCIE
资助标注
National Natural Science Foundation of China [61671213]

作者

  • X

    Xiao, Huanhou (第一作者)

  • S

    Shi, Jinglun (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