@inproceedings{forbes-etal-2019-neural,
title = "Neural Naturalist: Generating Fine-Grained Image Comparisons",
author = "Forbes, Maxwell and
Kaeser-Chen, Christine and
Sharma, Piyush and
Belongie, Serge",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1065",
doi = "10.18653/v1/D19-1065",
pages = "708--717",
abstract = "We introduce the new Birds-to-Words dataset of 41k sentences describing fine-grained differences between photographs of birds. The language collected is highly detailed, while remaining understandable to the everyday observer (e.g., {``}heart-shaped face,{''} {``}squat body{''}). Paragraph-length descriptions naturally adapt to varying levels of taxonomic and visual distance{---}drawn from a novel stratified sampling approach{---}with the appropriate level of detail. We propose a new model called Neural Naturalist that uses a joint image encoding and comparative module to generate comparative language, and evaluate the results with humans who must use the descriptions to distinguish real images. Our results indicate promising potential for neural models to explain differences in visual embedding space using natural language, as well as a concrete path for machine learning to aid citizen scientists in their effort to preserve biodiversity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="forbes-etal-2019-neural">
<titleInfo>
<title>Neural Naturalist: Generating Fine-Grained Image Comparisons</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maxwell</namePart>
<namePart type="family">Forbes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Kaeser-Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyush</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Belongie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce the new Birds-to-Words dataset of 41k sentences describing fine-grained differences between photographs of birds. The language collected is highly detailed, while remaining understandable to the everyday observer (e.g., “heart-shaped face,” “squat body”). Paragraph-length descriptions naturally adapt to varying levels of taxonomic and visual distance—drawn from a novel stratified sampling approach—with the appropriate level of detail. We propose a new model called Neural Naturalist that uses a joint image encoding and comparative module to generate comparative language, and evaluate the results with humans who must use the descriptions to distinguish real images. Our results indicate promising potential for neural models to explain differences in visual embedding space using natural language, as well as a concrete path for machine learning to aid citizen scientists in their effort to preserve biodiversity.</abstract>
<identifier type="citekey">forbes-etal-2019-neural</identifier>
<identifier type="doi">10.18653/v1/D19-1065</identifier>
<location>
<url>https://aclanthology.org/D19-1065</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>708</start>
<end>717</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Naturalist: Generating Fine-Grained Image Comparisons
%A Forbes, Maxwell
%A Kaeser-Chen, Christine
%A Sharma, Piyush
%A Belongie, Serge
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F forbes-etal-2019-neural
%X We introduce the new Birds-to-Words dataset of 41k sentences describing fine-grained differences between photographs of birds. The language collected is highly detailed, while remaining understandable to the everyday observer (e.g., “heart-shaped face,” “squat body”). Paragraph-length descriptions naturally adapt to varying levels of taxonomic and visual distance—drawn from a novel stratified sampling approach—with the appropriate level of detail. We propose a new model called Neural Naturalist that uses a joint image encoding and comparative module to generate comparative language, and evaluate the results with humans who must use the descriptions to distinguish real images. Our results indicate promising potential for neural models to explain differences in visual embedding space using natural language, as well as a concrete path for machine learning to aid citizen scientists in their effort to preserve biodiversity.
%R 10.18653/v1/D19-1065
%U https://aclanthology.org/D19-1065
%U https://doi.org/10.18653/v1/D19-1065
%P 708-717
Markdown (Informal)
[Neural Naturalist: Generating Fine-Grained Image Comparisons](https://aclanthology.org/D19-1065) (Forbes et al., EMNLP-IJCNLP 2019)
ACL
- Maxwell Forbes, Christine Kaeser-Chen, Piyush Sharma, and Serge Belongie. 2019. Neural Naturalist: Generating Fine-Grained Image Comparisons. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 708–717, Hong Kong, China. Association for Computational Linguistics.