DCMSTRD: End-to-end Dense Captioning via Multi-Scale Transformer Decoding-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

DCMSTRD: End-to-end Dense Captioning via Multi-Scale Transformer Decoding

Published:2024 Issue: Volume:26 Page:7581-7593
ISSN:1520-9210
Container-title:IEEE Transactions on Multimedia
language:
Short-container-title:IEEE Trans. Multimedia

Author:

Shao Zhuang¹^ORCID,Han Jungong²^ORCID,Debattista Kurt³^ORCID,Pang Yanwei⁴^ORCID

Affiliation:

1. School of Engineering, Newcastle University, Newcastle upon Tyne, U.K.

2. Department of Computer Science, University of Sheffield, Sheffield, U.K.

3. Warwick Manufacturing Group, University of Warwick, U.K.

4. School of Electrical and Information Engineering, Tianjin University, Tianjin, China

Funder

National Key Research and Development Program of China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx7/6046/10384483/10444947.pdf?arnumber=10444947

Reference59 articles.

1. Multi-Level Policy and Reward-Based Deep Reinforcement Learning Framework for Image Captioning

2. Scene Graph Refinement Network for Visual Question Answering

3. Referring Image Segmentation by Generative Adversarial Learning

4. Deep learning for video object segmentation: a review

5. Hierarchical Soft Quantization for Skeleton-Based Human Action Recognition

Cited by 11 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. TransEffiVisNet – an image captioning architecture for auditory assistance for the visually impaired;Multimedia Tools and Applications;2024-08-23

2. A new multimodal sentiment analysis for images containing textual information;Multimedia Tools and Applications;2024-08-15

3. A pavement crack segmentation method based on deformable convolution and enhanced perceive network;Multimedia Tools and Applications;2024-07-26

4. Consistency-aware unsupervised label learning for cross-domain person re-identification;Multimedia Tools and Applications;2024-07-25

5. EDSD: efficient driving scenes detection based on Swin Transformer;Multimedia Tools and Applications;2024-07-20

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号京ICP备18003416号-3