Skip to main navigation Skip to search Skip to main content

Modeling the relationship of action, object, and scene

  • Beijing Institute of Technology

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

Abstract

In the task of action recognition, object and scene can provide rich source of contextual information for analyzing human actions, as human actions often occur under particular scene settings with certain related objects. Therefore, we try to utilize the contextual object and scene for improving the performance of action recognition. Specifically, a latent structural SVM is introduced to build the co-occurrence relationship among action, object and scene, in which the object class label and scene class label are treated as latent variables. Using this framework, we can simultaneously predict action class labels, object class labels as well as scene class labels. Moreover, we use a mid-level discriminative feature to separately describe the information of action, object and scene. The feature is actually a set of decision values from the pre-learned classifiers of each class, measuring the likelihood that the input video belongs to the corresponding class. In this paper, we use SVM as action and scene pre-learned classifiers, and use deformable part-based object detector as the object pre-learned classifier, so that object location can be obtained as a by-product. Experimental results on UCF Sports, YouTube and UCF50 datasets demonstrate the effectiveness of the proposed approach.

Original languageEnglish
Title of host publication2014 22nd International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2005-2010
Number of pages6
ISBN (Electronic)9781479952083
DOIs
Publication statusPublished - 4 Dec 2014
Externally publishedYes
Event22nd International Conference on Pattern Recognition, ICPR 2014 - Stockholm, Sweden
Duration: 24 Aug 2014 → 28 Aug 2014

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Conference

Conference22nd International Conference on Pattern Recognition, ICPR 2014
Country/TerritorySweden
CityStockholm
Period24/08/14 → 28/08/14

Keywords

  • Action recognition
  • Context modeling
  • LSSVM
  • Object detection
  • Scene recognition

Fingerprint

Dive into the research topics of 'Modeling the relationship of action, object, and scene'. Together they form a unique fingerprint.

Cite this