CaltechAUTHORS
  A Caltech Library Service

Describing Common Human Visual Actions in Images

Ronchi, Matteo Ruggero and Perona, Pietro (2015) Describing Common Human Visual Actions in Images. In: British Machine Vision Conference 2015. BMVA Press , Durham, UK, 52.1-52.12. ISBN 1-901725-53-7. https://resolver.caltech.edu/CaltechAUTHORS:20150827-113206063

[img] PDF - Published Version
See Usage Policy.

6Mb
[img] Archive (ZIP) - Supplemental Material
See Usage Policy.

1260Kb
[img] PDF - Supplemental Material
See Usage Policy.

1382Kb
[img] PDF - Submitted Version
See Usage Policy.

8Mb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20150827-113206063

Abstract

Which common human actions and interactions are recognizable in monocular still images? Which involve objects and/or other people? How many is a person performing at a time? We address these questions by exploring the actions and interactions that are detectable in the images of the MS COCO dataset. We make two main contributions. First, a list of 140 common ‘visual actions’, obtained by analyzing the largest online verb lexicon currently available for English (VerbNet) and human sentences used to describe images in MS COCO. Second, a complete set of annotations for those ‘visual actions’, composed of subject-object and associated verb, which we call COCO-a (a for ‘actions’). COCO-a is larger than existing action datasets in terms of number instances of actions, and is unique because it is data-driven, rather than experimenter-biased. Other unique features are that it is exhaustive, and that all subjects and objects are localized. A statistical analysis of the accuracy of our annotations and of each action, interaction and subject-object combination is provided.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://dx.doi.org/10.5244/C.29.52DOIArticle
http://vision.caltech.edu/~mronchi/projects/Cocoa/AuthorUNSPECIFIED
https://arxiv.org/abs/1506.02203arXivDiscussion Paper
ORCID:
AuthorORCID
Perona, Pietro0000-0002-7583-5809
Contact Email Address:mronchi@caltech.edu
Additional Information:© 2015. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
Subject Keywords:Human actions, common images, action recognition
Record Number:CaltechAUTHORS:20150827-113206063
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20150827-113206063
Official Citation:Matteo Ruggero Ronchi and Pietro Perona. Describing Common Human Visual Actions in Images. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 52.1-52.12. BMVA Press, September 2015.
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:59927
Collection:CaltechAUTHORS
Deposited By: Matteo Ruggero Ronchi
Deposited On:28 Aug 2015 18:37
Last Modified:03 Oct 2019 08:51

Repository Staff Only: item control page