Choosing basic-level concept names using visual and language context

Alexander Mathews; Lexing Xie; Xuming He

doi:10.1109/WACV.2015.85

Choosing basic-level concept names using visual and language context

Alexander Mathews, Lexing Xie, Xuming He

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

14 Citations (Scopus)

Abstract

We study basic-level categories for describing visual concepts, and empirically observe context-dependant basic level names across thousands of concepts. We propose methods for predicting basic-level names using a series of classification and ranking tasks, producing the first large scale catalogue of basic-level names for hundreds of thousands of images depicting thousands of visual concepts. We also demonstrate the usefulness of our method with a picture-to-word task, showing strong improvement over recent work by Ordonez et al, by modeling of both visual and language context. Our study suggests that a model for naming visual concepts is an important part of any automatic image/video captioning and visual story-telling system.

Original language	English
Title of host publication	Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	595-602
Number of pages	8
ISBN (Electronic)	9781479966820
DOIs	https://doi.org/10.1109/WACV.2015.85
Publication status	Published - 19 Feb 2015
Event	2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015 - Waikoloa, United States Duration: 5 Jan 2015 → 9 Jan 2015

Publication series

Name	Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015

Conference

Conference	2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015
Country/Territory	United States
City	Waikoloa
Period	5/01/15 → 9/01/15

Access to Document

10.1109/WACV.2015.85

Cite this

Mathews, A., Xie, L., & He, X. (2015). Choosing basic-level concept names using visual and language context. In Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015 (pp. 595-602). Article 7045939 (Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WACV.2015.85

Mathews, Alexander ; Xie, Lexing ; He, Xuming. / Choosing basic-level concept names using visual and language context. Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 595-602 (Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015).

@inproceedings{6a61a938e71e485d844422d538aa006b,

title = "Choosing basic-level concept names using visual and language context",

abstract = "We study basic-level categories for describing visual concepts, and empirically observe context-dependant basic level names across thousands of concepts. We propose methods for predicting basic-level names using a series of classification and ranking tasks, producing the first large scale catalogue of basic-level names for hundreds of thousands of images depicting thousands of visual concepts. We also demonstrate the usefulness of our method with a picture-to-word task, showing strong improvement over recent work by Ordonez et al, by modeling of both visual and language context. Our study suggests that a model for naming visual concepts is an important part of any automatic image/video captioning and visual story-telling system.",

author = "Alexander Mathews and Lexing Xie and Xuming He",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015 ; Conference date: 05-01-2015 Through 09-01-2015",

year = "2015",

month = feb,

day = "19",

doi = "10.1109/WACV.2015.85",

language = "English",

series = "Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "595--602",

booktitle = "Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015",

address = "United States",

}

Mathews, A, Xie, L & He, X 2015, Choosing basic-level concept names using visual and language context. in Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015., 7045939, Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015, Institute of Electrical and Electronics Engineers Inc., pp. 595-602, 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015, Waikoloa, United States, 5/01/15. https://doi.org/10.1109/WACV.2015.85

Choosing basic-level concept names using visual and language context. / Mathews, Alexander; Xie, Lexing; He, Xuming.
Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 595-602 7045939 (Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Choosing basic-level concept names using visual and language context

AU - Mathews, Alexander

AU - Xie, Lexing

AU - He, Xuming

PY - 2015/2/19

Y1 - 2015/2/19

N2 - We study basic-level categories for describing visual concepts, and empirically observe context-dependant basic level names across thousands of concepts. We propose methods for predicting basic-level names using a series of classification and ranking tasks, producing the first large scale catalogue of basic-level names for hundreds of thousands of images depicting thousands of visual concepts. We also demonstrate the usefulness of our method with a picture-to-word task, showing strong improvement over recent work by Ordonez et al, by modeling of both visual and language context. Our study suggests that a model for naming visual concepts is an important part of any automatic image/video captioning and visual story-telling system.

AB - We study basic-level categories for describing visual concepts, and empirically observe context-dependant basic level names across thousands of concepts. We propose methods for predicting basic-level names using a series of classification and ranking tasks, producing the first large scale catalogue of basic-level names for hundreds of thousands of images depicting thousands of visual concepts. We also demonstrate the usefulness of our method with a picture-to-word task, showing strong improvement over recent work by Ordonez et al, by modeling of both visual and language context. Our study suggests that a model for naming visual concepts is an important part of any automatic image/video captioning and visual story-telling system.

UR - http://www.scopus.com/inward/record.url?scp=84925435397&partnerID=8YFLogxK

U2 - 10.1109/WACV.2015.85

DO - 10.1109/WACV.2015.85

M3 - Conference contribution

T3 - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015

SP - 595

EP - 602

BT - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015

Y2 - 5 January 2015 through 9 January 2015

ER -

Mathews A, Xie L, He X. Choosing basic-level concept names using visual and language context. In Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 595-602. 7045939. (Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015). doi: 10.1109/WACV.2015.85

Choosing basic-level concept names using visual and language context

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this