Beyond Spatial Pyramid Matching: Space-time Extended Descriptor for Action Recognition

10/15/2015
by   Zhenzhong Lan, et al.
0

We address the problem of generating video features for action recognition. The spatial pyramid and its variants have been very popular feature models due to their success in balancing spatial location encoding and spatial invariance. Although it seems straightforward to extend spatial pyramid to the temporal domain (spatio-temporal pyramid), the large spatio-temporal diversity of unconstrained videos and the resulting significantly higher dimensional representations make it less appealing. This paper introduces the space-time extended descriptor, a simple but efficient alternative way to include the spatio-temporal location into the video features. Instead of only coding motion information and leaving the spatio-temporal location to be represented at the pooling stage, location information is used as part of the encoding step. This method is a much more effective and efficient location encoding method as compared to the fixed grid model because it avoids the danger of over committing to artificial boundaries and its dimension is relatively low. Experimental results on several benchmark datasets show that, despite its simplicity, this method achieves comparable or better results than spatio-temporal pyramid.

READ FULL TEXT
research
08/29/2014

Temporal Extension of Scale Pyramid and Spatial Pyramid Matching for Action Recognition

Historically, researchers in the field have spent a great deal of effort...
research
03/15/2022

Learning Spatio-Temporal Downsampling for Effective Video Upscaling

Downsampling is one of the most basic image processing operations. Impro...
research
12/03/2014

Gradient Boundary Histograms for Action Recognition

This paper introduces a high efficient local spatiotemporal descriptor, ...
research
05/09/2017

Deep Spatio-temporal Manifold Network for Action Recognition

Visual data such as videos are often sampled from complex manifold. We p...
research
07/24/2022

MAR: Masked Autoencoders for Efficient Action Recognition

Standard approaches for video recognition usually operate on the full in...
research
11/24/2014

Beyond Gaussian Pyramid: Multi-skip Feature Stacking for Action Recognition

Most state-of-the-art action feature extractors involve differential ope...
research
10/01/2012

Combined Descriptors in Spatial Pyramid Domain for Image Classification

Recently spatial pyramid matching (SPM) with scale invariant feature tra...

Please sign up or login with your details

Forgot password? Click here to reset