O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. Berg, и L. Fei-Fei. (2014)cite arxiv:1409.0575Comment: 43 pages, 16 figures. v3 includes additional comparisons with PASCAL VOC (per-category comparisons in Table 3, distribution of localization difficulty in Fig 16), a list of queries used for obtaining object detection images (Appendix C), and some additional references.
Аннотация
The ImageNet Large Scale Visual Recognition Challenge is a benchmark in
object category classification and detection on hundreds of object categories
and millions of images. The challenge has been run annually from 2010 to
present, attracting participation from more than fifty institutions.
This paper describes the creation of this benchmark dataset and the advances
in object recognition that have been possible as a result. We discuss the
challenges of collecting large-scale ground truth annotation, highlight key
breakthroughs in categorical object recognition, provide a detailed analysis of
the current state of the field of large-scale image classification and object
detection, and compare the state-of-the-art computer vision accuracy with human
accuracy. We conclude with lessons learned in the five years of the challenge,
and propose future directions and improvements.
cite arxiv:1409.0575Comment: 43 pages, 16 figures. v3 includes additional comparisons with PASCAL VOC (per-category comparisons in Table 3, distribution of localization difficulty in Fig 16), a list of queries used for obtaining object detection images (Appendix C), and some additional references
%0 Journal Article
%1 russakovsky2014imagenet
%A Russakovsky, Olga
%A Deng, Jia
%A Su, Hao
%A Krause, Jonathan
%A Satheesh, Sanjeev
%A Ma, Sean
%A Huang, Zhiheng
%A Karpathy, Andrej
%A Khosla, Aditya
%A Bernstein, Michael
%A Berg, Alexander C.
%A Fei-Fei, Li
%D 2014
%K from:lukasbarth imported ma_ss22_ts
%T ImageNet Large Scale Visual Recognition Challenge
%U http://arxiv.org/abs/1409.0575
%X The ImageNet Large Scale Visual Recognition Challenge is a benchmark in
object category classification and detection on hundreds of object categories
and millions of images. The challenge has been run annually from 2010 to
present, attracting participation from more than fifty institutions.
This paper describes the creation of this benchmark dataset and the advances
in object recognition that have been possible as a result. We discuss the
challenges of collecting large-scale ground truth annotation, highlight key
breakthroughs in categorical object recognition, provide a detailed analysis of
the current state of the field of large-scale image classification and object
detection, and compare the state-of-the-art computer vision accuracy with human
accuracy. We conclude with lessons learned in the five years of the challenge,
and propose future directions and improvements.
@article{russakovsky2014imagenet,
abstract = {The ImageNet Large Scale Visual Recognition Challenge is a benchmark in
object category classification and detection on hundreds of object categories
and millions of images. The challenge has been run annually from 2010 to
present, attracting participation from more than fifty institutions.
This paper describes the creation of this benchmark dataset and the advances
in object recognition that have been possible as a result. We discuss the
challenges of collecting large-scale ground truth annotation, highlight key
breakthroughs in categorical object recognition, provide a detailed analysis of
the current state of the field of large-scale image classification and object
detection, and compare the state-of-the-art computer vision accuracy with human
accuracy. We conclude with lessons learned in the five years of the challenge,
and propose future directions and improvements.},
added-at = {2022-07-05T18:51:53.000+0200},
author = {Russakovsky, Olga and Deng, Jia and Su, Hao and Krause, Jonathan and Satheesh, Sanjeev and Ma, Sean and Huang, Zhiheng and Karpathy, Andrej and Khosla, Aditya and Bernstein, Michael and Berg, Alexander C. and Fei-Fei, Li},
biburl = {https://www.bibsonomy.org/bibtex/2f8d66129d3611641bbce448ed0e2a33a/lukasbarth},
description = {ImageNet Large Scale Visual Recognition Challenge},
interhash = {83cea6471796e9c42b527cc29318f9df},
intrahash = {f8d66129d3611641bbce448ed0e2a33a},
keywords = {from:lukasbarth imported ma_ss22_ts},
note = {cite arxiv:1409.0575Comment: 43 pages, 16 figures. v3 includes additional comparisons with PASCAL VOC (per-category comparisons in Table 3, distribution of localization difficulty in Fig 16), a list of queries used for obtaining object detection images (Appendix C), and some additional references},
timestamp = {2022-07-05T18:51:53.000+0200},
title = {ImageNet Large Scale Visual Recognition Challenge},
url = {http://arxiv.org/abs/1409.0575},
year = 2014
}