Spatio-Temporal Grids for Daily Living Action Recognition

Abstract : This paper address the recognition of short-term daily living actions from RGB-D videos. The existing approaches ignore spatio-temporal contextual relationships in the action videos. So, we propose to explore the spatial layout to better model the appearance. In order to encode temporal information, we divide the action sequence into temporal grids. We address the challenge of subject invariance by applying clustering on the appearance features and velocity features to partition the temporal grids. We validate our approach on four public datasets. The results show that our method is competitive with the state-of-the-art.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-01939320
Contributor : Srijan Das <>
Submitted on : Thursday, November 29, 2018 - 1:21:02 PM
Last modification on : Friday, November 30, 2018 - 1:22:35 AM

File

ICVGIP_HAL_Version.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Srijan Das, Kaustubh Sakhalkar, Michal Koperski, Francois Bremond. Spatio-Temporal Grids for Daily Living Action Recognition. 11th Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP-2018), Dec 2018, Hyderabad, India. ⟨10.1145/3293353.3293376⟩. ⟨hal-01939320⟩

Share

Metrics

Record views

97

Files downloads

137