ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition

Author:

Massiceti Daniela1,Zintgraf Luisa2,Bronskill John3,Theodorou Lida4,Harris Matthew Tobias4,Cutrell Edward1,Morrison Cecily1,Hofmann Katja1,Stumpf Simone4

Affiliation:

1. Microsoft Research

2. University of Oxford

3. University of Cambridge

4. City, University of London

Funder

Microsoft

Publisher

IEEE

Reference52 articles.

1. ImageNet Large Scale Visual Recognition Challenge

2. Fast and flexible multi-task classification using conditional neural adaptive processes;requeima;Proceedings of the 33rd Annual Conference on Neural Information Processing Systems (NeurIPS),2019

3. Meta-curvature;park;Proceedings of the 33rd Annual Conference on Neural Information Processing Systems (NeurIPS),2019

4. Automated Flower Classification over a Large Number of Classes

5. ORBIT: A real-world few-shot dataset for teachable object recognition collected from people who are blind or low vision;massiceti,2021

Cited by 16 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. Find My Things: Personalized Accessibility through Teachable AI for People who are Blind or Low Vision;Extended Abstracts of the CHI Conference on Human Factors in Computing Systems;2024-05-11

2. A Benchmark Grocery Dataset of Realworld Point Clouds From Single View;2024 International Conference on 3D Vision (3DV);2024-03-18

3. Deep Neighborhood Structure-Preserving Hashing for Large-Scale Image Retrieval;IEEE Transactions on Multimedia;2024

4. Few-Shot Learning With Class Imbalance;IEEE Transactions on Artificial Intelligence;2023-10

5. Training AI to Recognize Objects of Interest to the Blind and Low Vision Community;2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC);2023-07-24

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