Cross-View Action Recognition from Temporal Self-Similarities - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2008

Cross-View Action Recognition from Temporal Self-Similarities

Abstract

This paper concerns recognition of human actions under view changes. We explore self-similarities of action sequences over time and observe the striking stability of such measures across views. Building upon this key observation we develop an action descriptor that captures the structure of temporal similarities and dissimilarities within an action sequence. Despite this descriptor not being strictly view-invariant, we provide intuition and experimental validation demonstrating the high stability of self-similarities under view changes. Self-similarity descriptors are also shown stable under action variations within a class as well as discriminative for action recognition. Interestingly, self-similarities computed from different image features possess similar properties and can be used in a complementary fashion. Our method is simple and requires neither structure recovery nor multi-view correspondence estimation. Instead, it relies on weak geometric cues captured by self-similarities and combines them with machine learning for efficient cross-view action recognition. The method is validated on three public datasets, it has similar or superior performance compared to related methods and it performs well even in extreme conditions such as when recognizing actions from top views while using side views for training only.
Fichier principal
Vignette du fichier
PI-1895.pdf (1.09 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00289708 , version 1 (23-06-2008)

Identifiers

  • HAL Id : inria-00289708 , version 1

Cite

Imran Junejo, Emilie Dexter, Ivan Laptev, Patrick Pérez. Cross-View Action Recognition from Temporal Self-Similarities. [Research Report] PI 1895, 2008, pp.19. ⟨inria-00289708⟩
299 View
746 Download

Share

Gmail Facebook X LinkedIn More