Imperial College London


Faculty of EngineeringDepartment of Electrical and Electronic Engineering

Reader in Computer Vision



+44 (0)20 7594 6220k.mikolajczyk




Electrical EngineeringSouth Kensington Campus






BibTex format

author = {De, Campos T and Barnard, M and Mikolajczyk, K and Kittler, J and Yan, F and Christmas, W and Windridge, D},
doi = {10.1109/WACV.2011.5711524},
pages = {344--351},
title = {An evaluation of bags-of-words and spatio-temporal shapes for action recognition},
url = {},
year = {2011}

RIS format (EndNote, RefMan)

AB - Bags-of-visual-Words (BoW) and Spatio-Temporal Shapes (STS) are two very popular approaches for action recognition from video. The former (BoW) is an un-structured global representation of videos which is built using a large set of local features. The latter (STS) uses a single feature located on a region of interest (where the actor is) in the video. Despite the popularity of these methods, no comparison between them has been done. Also, given that BoW and STS differ intrinsically in terms of context inclusion and globality/locality of operation, an appropriate evaluation framework has to be designed carefully. This paper compares these two approaches using four different datasets with varied degree of space-time specificity of the actions and varied relevance of the contextual background. We use the same local feature extraction method and the same classifier for both approaches. Further to BoW and STS, we also evaluated novel variations of BoW constrained in time or space. We observe that the STS approach leads to better results in all datasets whose background is of little relevance to action classification. © 2010 IEEE.
AU - De,Campos T
AU - Barnard,M
AU - Mikolajczyk,K
AU - Kittler,J
AU - Yan,F
AU - Christmas,W
AU - Windridge,D
DO - 10.1109/WACV.2011.5711524
EP - 351
PY - 2011///
SP - 344
TI - An evaluation of bags-of-words and spatio-temporal shapes for action recognition
UR -
ER -