Efficient Multi-Task Scene Analysis with RGB-D Transformers

Author:

Fischedick Söhnke Benedikt1ORCID,Seichter Daniel1,Schmidt Robin1,Rabes Leonard1,Gross Horst-Michael1

Affiliation:

1. Ilmenau University of Technology,Neuroinformatics and Cognitive Robotics Lab,Ilmenau,Germany,98684

Publisher

IEEE

Reference56 articles.

1. ImageNet Large Scale Visual Recognition Challenge

2. An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale;dosovitskiy;Proc of ICLR,0

3. Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

4. SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers;xie;Proc of NeurIPS,0

5. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Cited by 6 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. A fusiform network of indoor scene classification with the stylized semantic description for service-robot applications;Expert Systems with Applications;2024-07

2. Cascading context enhancement network for RGB-D semantic segmentation;Multimedia Tools and Applications;2024-04-15

3. Improved RGB-D Indoor Semantic Segmentation using Cascaded Loss Fusion;2024 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR);2024-01-17

4. Joint Depth Prediction and Semantic Segmentation with Multi-View SAM;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03

5. OHO: A Multi-Modal, Multi-Purpose Dataset for Human-Robot Object Hand-Over;Sensors;2023-09-11

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