• xmlui.mirage2.page-structure.header.title
    • français
    • English
  • Help
  • Login
  • Language 
    • Français
    • English
View Item 
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesTypeThis CollectionBy Issue DateAuthorsTitlesType

My Account

LoginRegister

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors
Thumbnail

Mid-level features and spatio-temporal context for activity recognition

Yuan, Fei; Xia, Gui-Song; Sahbi, Hichem; Prinet, Véronique (2012), Mid-level features and spatio-temporal context for activity recognition, Pattern Recognition, 45, 12, p. 4182-4191. http://dx.doi.org/10.1016/j.patcog.2012.05.001

View/Open
yuan-pr2012-action.pdf (11.25Mb)
Type
Article accepté pour publication ou publié
Date
2012
Journal name
Pattern Recognition
Volume
45
Number
12
Publisher
Elsevier
Pages
4182-4191
Publication identifier
http://dx.doi.org/10.1016/j.patcog.2012.05.001
Metadata
Show full item record
Author(s)
Yuan, Fei
Xia, Gui-Song
Sahbi, Hichem
Prinet, Véronique
Abstract (EN)
Local spatio-temporal features have been shown to be effective and robust in order to represent simple actions. However, for high level human activities with long-range motion or multiple interactive body parts and persons, the limitation of low-level features blows up because of their localness. This paper addresses the problem by suggesting a framework that computes mid-level features and takes into account their contextual information. First, we represent human activities by a set of mid-level components, referred to as activity components, which have consistent structure and motion in spatial and temporal domain respectively. These activity components are extracted hierarchically from videos, i.e., extracting key-points, grouping them into trajectories and finally clustering trajectories into components. Second, to further exploit the interdependencies of the activity components, we introduce a spatio-temporal context kernel (STCK), which not only captures local properties of features but also considers their spatial and temporal context information. Experiments conducted on two challenging activity recognition datasets show that the proposed approach outperforms standard spatio-temporal features and our STCK context kernel improves further the performance.
Subjects / Keywords
Activity recognition; Mid-level features; Activity components; Spatio-temporal context kernels

Related items

Showing items related by title and author.

  • Thumbnail
    Statistical Mid-Level Features for Building-up Area Extraction From Full Polarimetric SAR Imagery 
    Yang, Wen; Liu, Y.; Xia, Gui-Song; Xu, X. (2012) Article accepté pour publication ou publié
  • Thumbnail
    An accurate and contrast invariant junction detector 
    Xia, Gui-Song; Delon, Julie; Gousseau, Yann (2012) Communication / Conférence
  • Thumbnail
    Synthesizing and Mixing Stationary Gaussian Texture Models 
    Aujol, Jean-François; Peyré, Gabriel; Ferradans, Sira; Xia, Gui-Song (2014) Article accepté pour publication ou publié
  • Thumbnail
    SAR-based Terrain Classification using Weakly Supervised Hierarchical Markov Aspect Models 
    Xia, Gui-Song; Triggs, Bill; Dai, Dengxin; Yang, Wen (2012) Article accepté pour publication ou publié
  • Thumbnail
    Optimal Transport Mixing of Gaussian Texture Models 
    Aujol, Jean-François; Peyré, Gabriel; Xia, Gui-Song; Ferradans, Sira (2012) Document de travail / Working paper
Dauphine PSL Bibliothèque logo
Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16
Phone: 01 44 05 40 94
Contact
Dauphine PSL logoEQUIS logoCreative Commons logo