An Analysis of Action Recognition Datasets for Language and Vision Tasks

Spandana Gella; Frank Keller

doi:10.18653/v1/P17-2011

An Analysis of Action Recognition Datasets for Language and Vision Tasks

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

Abstract / Description of output

A large amount of recent research has focused on tasks that combine language
and vision, resulting in a proliferation of datasets and methods. One such task
is action recognition, whose applications include image annotation, scene understanding and image retrieval. In this survey, we categorize the existing approaches based on how they conceptualize this problem and provide a detailed review of existing datasets, highlighting their diversity as well as advantages and disadvantages. We focus on recently developed datasets which link visual information with linguistic resources and provide a fine-grained syntactic and semantic analysis of actions in images.

Original language	English
Title of host publication	Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Short Papers)
Publisher	Association for Computational Linguistics
Pages	64-71
Number of pages	8
ISBN (Print)	978-1-945626-76-0
DOIs	https://doi.org/10.18653/v1/P17-2011
Publication status	Published - 4 Aug 2017
Event	55th annual meeting of the Association for Computational Linguistics (ACL) - Vancouver, Canada Duration: 30 Jul 2017 → 4 Aug 2017 http://acl2017.org/

Conference

Conference	55th annual meeting of the Association for Computational Linguistics (ACL)
Abbreviated title	ACL 2017
Country/Territory	Canada
City	Vancouver
Period	30/07/17 → 4/08/17
Internet address	http://acl2017.org/

Access to Document

10.18653/v1/P17-2011

acl17Accepted author manuscript, 415 KB

http://aclweb.org/anthology/P17-2011Licence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{f2e37a2541fd47a4bdb72f1e773b396a,

title = "An Analysis of Action Recognition Datasets for Language and Vision Tasks",

abstract = "A large amount of recent research has focused on tasks that combine languageand vision, resulting in a proliferation of datasets and methods. One such taskis action recognition, whose applications include image annotation, scene understanding and image retrieval. In this survey, we categorize the existing approaches based on how they conceptualize this problem and provide a detailed review of existing datasets, highlighting their diversity as well as advantages and disadvantages. We focus on recently developed datasets which link visual information with linguistic resources and provide a fine-grained syntactic and semantic analysis of actions in images.",

author = "Spandana Gella and Frank Keller",

year = "2017",

month = aug,

day = "4",

doi = "10.18653/v1/P17-2011",

language = "English",

isbn = "978-1-945626-76-0",

pages = "64--71",

booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Short Papers)",

publisher = "Association for Computational Linguistics",

note = "55th annual meeting of the Association for Computational Linguistics (ACL), ACL 2017 ; Conference date: 30-07-2017 Through 04-08-2017",

url = "http://acl2017.org/",

}

Gella, S & Keller, F 2017, An Analysis of Action Recognition Datasets for Language and Vision Tasks. in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Short Papers). Association for Computational Linguistics, pp. 64-71, 55th annual meeting of the Association for Computational Linguistics (ACL), Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-2011

TY - GEN

T1 - An Analysis of Action Recognition Datasets for Language and Vision Tasks

AU - Gella, Spandana

AU - Keller, Frank

PY - 2017/8/4

Y1 - 2017/8/4

N2 - A large amount of recent research has focused on tasks that combine languageand vision, resulting in a proliferation of datasets and methods. One such taskis action recognition, whose applications include image annotation, scene understanding and image retrieval. In this survey, we categorize the existing approaches based on how they conceptualize this problem and provide a detailed review of existing datasets, highlighting their diversity as well as advantages and disadvantages. We focus on recently developed datasets which link visual information with linguistic resources and provide a fine-grained syntactic and semantic analysis of actions in images.

AB - A large amount of recent research has focused on tasks that combine languageand vision, resulting in a proliferation of datasets and methods. One such taskis action recognition, whose applications include image annotation, scene understanding and image retrieval. In this survey, we categorize the existing approaches based on how they conceptualize this problem and provide a detailed review of existing datasets, highlighting their diversity as well as advantages and disadvantages. We focus on recently developed datasets which link visual information with linguistic resources and provide a fine-grained syntactic and semantic analysis of actions in images.

U2 - 10.18653/v1/P17-2011

DO - 10.18653/v1/P17-2011

M3 - Conference contribution

SN - 978-1-945626-76-0

SP - 64

EP - 71

BT - Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Short Papers)

PB - Association for Computational Linguistics

T2 - 55th annual meeting of the Association for Computational Linguistics (ACL)

Y2 - 30 July 2017 through 4 August 2017

ER -

An Analysis of Action Recognition Datasets for Language and Vision Tasks

Abstract / Description of output

Conference

Access to Document

Fingerprint

Cite this