Learning Spatio-Temporal Representations for Action Recognition: A Genetic Programming Approach
Created by W.Langdon from
gp-bibliography.bib Revision:1.8098
- @Article{Liu:2015:Cybernetics,
-
author = "Li Liu and Ling Shao and Xuelong Li and Ke Lu",
-
journal = "IEEE Transactions on Cybernetics",
-
title = "Learning Spatio-Temporal Representations for Action
Recognition: A Genetic Programming Approach",
-
year = "2016",
-
volume = "46",
-
number = "1",
-
pages = "158--170",
-
keywords = "genetic algorithms, genetic programming, Action
recognition, feature extraction, feature learning,
spatio-temporal descriptors",
-
DOI = "doi:10.1109/TCYB.2015.2399172",
-
ISSN = "2168-2267",
-
abstract = "Extracting discriminative and robust features from
video sequences is the first and most critical step in
human action recognition. In this paper, instead of
using handcrafted features, we automatically learn
spatio-temporal motion features for action recognition.
This is achieved via an evolutionary method, i.e.,
genetic programming (GP), which evolves the motion
feature descriptor on a population of primitive 3D
operators (e.g., 3D-Gabor and wavelet). In this way,
the scale and shift invariant features can be
effectively extracted from both colour and optical flow
sequences. We intend to learn data adaptive descriptors
for different datasets with multiple layers, which
makes fully use of the knowledge to mimic the physical
structure of the human visual cortex for action
recognition and simultaneously reduce the GP searching
space to effectively accelerate the convergence of
optimal solutions. In our evolutionary architecture,
the average cross-validation classification error,
which is calculated by an support-vector-machine
classifier on the training set, is adopted as the
evaluation criterion for the GP fitness function. After
the entire evolution procedure finishes, the
best-so-far solution selected by GP is regarded as the
(near-)optimal action descriptor obtained. The
GP-evolving feature extraction method is evaluated on
four popular action datasets, namely KTH, HMDB51, UCF
YouTube, and Hollywood2. Experimental results show that
our method significantly outperforms other types of
features, either hand-designed or machine-learnt.",
-
notes = "Also known as \cite{7042326}",
- }
Genetic Programming entries for
Li Liu
Ling Shao
Xuelong Li
Ke Lu
Citations