logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Continual Learning for Image Captioning in Hindi

delete2025-10-01
delete0
PRE
AI
S
Santosh Kumar Mishra *
S
Sriparna Saha
P
Pushpak Bhattacharyya
DOI：10.1145/3749641delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
持续学习，又称增量学习或终身学习，是一种学习范式，使智能体能够在不损害先前所学知识保留的情况下获取新信息。持续学习研究已产生多种防止深度神经网络灾难性遗忘的方法。显然，循环模型的持续学习从未被用于解决印地语的图像描述问题。本研究提出了一种新颖的方法，在生成印地语图像描述的背景下应用持续学习。鉴于其在南亚的广泛使用以及在印度的官方地位，印地语在全球范围内排名第三。我们系统地研究了基于长短期记忆（LSTM）和门控循环单元（GRU）模型的图像描述持续学习。在持续图像描述问题中，我们采用了一种基于注意力的方法，明确解决了词汇的瞬态特性。使用MS-COCO数据集，我们采用我们的方法来解决增量图像描述问题。我们的发现表明，所提出的方法可以按顺序学习五个描述任务，而不会忘记已经学过的任务。
Keyword:
Continual learning
hindi
image captioning
attention

期刊

A
ACM Transactions on Asian and Low-Resource Language Information Processing
IF:
0
论文数:
56
被引数:
0

机构

I
indian institute of technology system (iit system)
学者数:
9.5W
论文数: 9.9W
被引数: 93
I
indian institute of technology (iit) - patna
学者数:
1.8K
论文数: 1.6K
被引数: 0
引用论文

引用论文

Toward Training Recurrent Neural Networks for Lifelong Learning
errNeural Computation
IF0
err2020-01-01
err0
PREAI
errShagun Sodhani; Sarath Chandar; Yoshua Bengio
err分享
err收藏
Fast, Diverse and Accurate Image Captioning Guided by Part-Of-Speech
err2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2019-06-01
err0
errOAAI
errAditya Deshpande; Jyoti Aneja; Liwei Wang; Alexander G. Schwing; David Forsyth
err分享
err收藏
Towards Accurate Text-based Image Captioning with Content Diversity Exploration通过内容多样性探索实现准确的基于文本的图像字幕
err2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2021-06-01
err0
errOAAI
errGuanghui Xu; Shuaicheng Niu; Mingkui Tan; Yucheng Luo; Qing Du; Qi Wu
err分享
err收藏
Comprehending and Ordering Semantics for Image Captioning
err2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2022-06-01
err0
errOAAI
errYehao Li; Yingwei Pan; Ting Yao; Tao Mei
err分享
err收藏
Show and tell: A neural image caption generator显示和告诉: 神经图像标题生成器
err2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2015-06-01
err0
errOAAI
errOriol Vinyals; Alexander Toshev; Samy Bengio; Dumitru Erhan
err分享
err收藏
Long Short-Term Memory长短期记忆
errNeural Computation
IF0
err1997-11-01
err0
PREAI
errSepp Hochreiter; Jürgen Schmidhuber
err分享
err收藏
Knowing What to Learn: A Metric-Oriented Focal Mechanism for Image Captioning
errIEEE Transactions on Image Processing
IF0
err2022-01-01
err0
PREAI
errJiayi Ji; Yiwei Ma; Xiaoshuai Sun; Yiyi Zhou; Yongjian Wu; Rongrong Ji
err分享
err收藏
Deep visual-semantic alignments for generating image descriptions
err2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2015-06-01
err0
errOAAI
errAndrej Karpathy; Li Fei-Fei
err分享
err收藏
Learning With Sharing: An Edge-Optimized Incremental Learning Method for Deep Neural Networks
errIEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
IF5.4
err2023-04-01
err4
errOAAI
errHussain, Muhammad Awais; Huang, Shih-An; Tsai, Tsung-Han
err分享
err收藏
Image captioning in Hindi language using transformer networks使用transformer网络在印地语中的图像字幕
errCOMPUTERS & ELECTRICAL ENGINEERING
IF4.9
err2021-06-01
err16
PREAI
errMishra, Santosh Kumar; Dhir, Rijul; Saha, Sriparna; Bhattacharyya, Pushpak; Singh, Amit Kumar
err分享
err收藏
学者 查看更多内容