Multi-level action detection via learning latent structure


Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

1 Downloads (Pure)


Detecting actions in videos is still a demanding task due to large intra-class variation caused by varying pose, motion and scales. Conventional approaches use a Bag-of-Words model in the form of space-time motion feature pooling followed by learning a classifier. However, since the informative body parts motion only appear in specific regions of the body, these methods have limited capability. In this paper, we seek to learn a model of the interaction among regions of interest via a graph structure. We first discover several space-time video segments representing persistent moving body parts observed sparsely in video. Then, via learning the hidden graph structure (a subset of the graph), we identify both spatial and temporal relations between the subsets of these segments. In order to seize the more discriminative motion patterns and handle different interactions between body parts from simple to composite action, we present a multi-level action model representation. Consequently, for action classification, the classifier learned through each action model labels the test video based on the action model that gives the highest probability score. Experiments on challenging datasets, such as MSR II and UCF-Sports including complex motions and dynamic backgrounds, demonstrate the effectiveness of the proposed approach that outperforms state-of-the-art methods in this context
Original languageEnglish
Title of host publicationProceedings of the IEEE International conference on image processing (ICIP 2015)
EditorsAbhay M. Chopde, Rambabu Vatti
Place of PublicationQuebec City, Canada
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages5
ISBN (Electronic)9781479983391
ISBN (Print)9781479983391
Publication statusPublished - 27 Sept 2015
EventThe IEEE International Conference on Image Processing ICIP 2015 - Quebec, Quebec, Canada
Duration: 27 Sept 201530 Sept 2015

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880


ConferenceThe IEEE International Conference on Image Processing ICIP 2015
Abbreviated titleICIP 2015


Dive into the research topics of 'Multi-level action detection via learning latent structure'. Together they form a unique fingerprint.

Cite this