Structured prediction with output embeddings for semantic image annotation

Ariadna Quattoni; Arnau Ramisa; Pranava Swaroop Madhyastha; Edgar Simo-Serra; Francesc Moreno-Noguer

doi:10.18653/v1/n16-1068

Structured prediction with output embeddings for semantic image annotation

Ariadna Quattoni, Arnau Ramisa, Pranava Swaroop Madhyastha, Edgar Simo-Serra, Francesc Moreno-Noguer

基幹理工学部

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

We address the task of annotating images with semantic tuples. Solving this problem requires an algorithm able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key challenge. We propose handling this sparsity by incorporating feature representations of both the inputs (images) and outputs (argument classes) into a factorized log-linear model.

本文言語	English
ホスト出版物のタイトル	2016 Conference of the North American Chapter of the Association for Computational Linguistics
ホスト出版物のサブタイトル	Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference
出版社	Association for Computational Linguistics (ACL)
ページ	552-557
ページ数	6
ISBN（電子版）	9781941643914
DOI	https://doi.org/10.18653/v1/n16-1068
出版ステータス	Published - 2016
イベント	15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - San Diego, United States 継続期間: 2016 6月 12 → 2016 6月 17

出版物シリーズ

名前	2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference

Other

Other	15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016
国/地域	United States
City	San Diego
Period	16/6/12 → 16/6/17

ASJC Scopus subject areas

コンピュータサイエンスの応用
言語学および言語
言語および言語学

文献へのアクセス

10.18653/v1/n16-1068

他のファイルとリンク

引用スタイル

Quattoni, A., Ramisa, A., Madhyastha, P. S., Simo-Serra, E., & Moreno-Noguer, F. (2016). Structured prediction with output embeddings for semantic image annotation. In 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference (pp. 552-557). (2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/n16-1068

Structured prediction with output embeddings for semantic image annotation. / Quattoni, Ariadna; Ramisa, Arnau; Madhyastha, Pranava Swaroop その他.
2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. Association for Computational Linguistics (ACL), 2016. p. 552-557 (2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference).

研究成果: Conference contribution

Quattoni, A, Ramisa, A, Madhyastha, PS, Simo-Serra, E & Moreno-Noguer, F 2016, Structured prediction with output embeddings for semantic image annotation. in 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 552-557, 15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016, San Diego, United States, 16/6/12. https://doi.org/10.18653/v1/n16-1068

Quattoni A, Ramisa A, Madhyastha PS, Simo-Serra E, Moreno-Noguer F. Structured prediction with output embeddings for semantic image annotation. In 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. Association for Computational Linguistics (ACL). 2016. p. 552-557. (2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference). doi: 10.18653/v1/n16-1068

Quattoni, Ariadna ; Ramisa, Arnau ; Madhyastha, Pranava Swaroop その他. / Structured prediction with output embeddings for semantic image annotation. 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference. Association for Computational Linguistics (ACL), 2016. pp. 552-557 (2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference).

@inproceedings{7a41924c131d44bd8d165a02b8342d05,

title = "Structured prediction with output embeddings for semantic image annotation",

abstract = "We address the task of annotating images with semantic tuples. Solving this problem requires an algorithm able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key challenge. We propose handling this sparsity by incorporating feature representations of both the inputs (images) and outputs (argument classes) into a factorized log-linear model.",

author = "Ariadna Quattoni and Arnau Ramisa and Madhyastha, {Pranava Swaroop} and Edgar Simo-Serra and Francesc Moreno-Noguer",

note = "Funding Information: This work was partly funded by the Spanish MINECO project RobInstruct TIN2014-58178-R and by the ERA-net CHISTERA projects VISEN PCIN- 2013-047 and I-DRESS PCIN-2015-147. The authors are grateful to the Nvidia donation program for its support with GPU cards. Publisher Copyright: {\textcopyright}2016 Association for Computational Linguistics.; 15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 ; Conference date: 12-06-2016 Through 17-06-2016",

year = "2016",

doi = "10.18653/v1/n16-1068",

language = "English",

series = "2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference",

publisher = "Association for Computational Linguistics (ACL)",

pages = "552--557",

booktitle = "2016 Conference of the North American Chapter of the Association for Computational Linguistics",

}

TY - GEN

T1 - Structured prediction with output embeddings for semantic image annotation

AU - Quattoni, Ariadna

AU - Ramisa, Arnau

AU - Madhyastha, Pranava Swaroop

AU - Simo-Serra, Edgar

AU - Moreno-Noguer, Francesc

N1 - Funding Information: This work was partly funded by the Spanish MINECO project RobInstruct TIN2014-58178-R and by the ERA-net CHISTERA projects VISEN PCIN- 2013-047 and I-DRESS PCIN-2015-147. The authors are grateful to the Nvidia donation program for its support with GPU cards. Publisher Copyright: ©2016 Association for Computational Linguistics.

PY - 2016

Y1 - 2016

N2 - We address the task of annotating images with semantic tuples. Solving this problem requires an algorithm able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key challenge. We propose handling this sparsity by incorporating feature representations of both the inputs (images) and outputs (argument classes) into a factorized log-linear model.

AB - We address the task of annotating images with semantic tuples. Solving this problem requires an algorithm able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key challenge. We propose handling this sparsity by incorporating feature representations of both the inputs (images) and outputs (argument classes) into a factorized log-linear model.

UR - http://www.scopus.com/inward/record.url?scp=84994137617&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994137617&partnerID=8YFLogxK

U2 - 10.18653/v1/n16-1068

DO - 10.18653/v1/n16-1068

M3 - Conference contribution

AN - SCOPUS:84994137617

T3 - 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference

SP - 552

EP - 557

BT - 2016 Conference of the North American Chapter of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

T2 - 15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016

Y2 - 12 June 2016 through 17 June 2016

ER -

Structured prediction with output embeddings for semantic image annotation

抄録

出版物シリーズ

Other

ASJC Scopus subject areas

文献へのアクセス

他のファイルとリンク

フィンガープリント

引用スタイル