Skip to Main content Skip to Navigation
New interface
Conference papers

Trajectory based Primitive Events for learning and recognizing Activity

Abstract : This paper proposes a framework to recognize and classify loosely constrained activities with minimal supervision. The framework use basic trajectory information as input and goes up to video interpretation. The work reduces the gap between low-level information and semantic interpretation, building an intermediate layer composed Primitive Events. The proposed representation for primitive events aims at capturing small meaningful motions over the scene with the advantage of been learnt in an unsupervised manner. We propose the modelling of an activity using Primitive Events as the main descriptors. The activity model is built in a semi-supervised way using only real tracking data. Finally we validate the descriptors by recognizing and labelling modelled activities in a home-care application dataset.
Document type :
Conference papers
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download
Contributor : Guido Pusiol Connect in order to contact the contributor
Submitted on : Friday, July 16, 2010 - 7:48:58 PM
Last modification on : Friday, February 4, 2022 - 3:16:39 AM
Long-term archiving on: : Friday, October 22, 2010 - 3:24:24 PM


Files produced by the author(s)


  • HAL Id : inria-00503209, version 1



Guido Pusiol, François Bremond, Monique Thonnat. Trajectory based Primitive Events for learning and recognizing Activity. Second IEEE International Workshop on Tracking Humans for the Evaluation of their Motion in Image Sequences (THEMIS2009), Sep 2009, Kyoto, Japan. ⟨inria-00503209⟩



Record views


Files downloads