scholarly journals LaM-2SRN: A Method Which Can Enhance Local Features and Detect Moving Objects for Action Recognition

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 192703-192712
Author(s):  
Yangyang Qiao ◽  
Whenhua Cui ◽  
Tianwei Shi
Keyword(s):  
Action Recognition ◽  
Moving Objects ◽  
Local Features

Scalable local features and hybrid classifiers for improving action recognition

2019 ◽  
Vol 36 (4) ◽  
pp. 3357-3372
Author(s):  
Van-Huy Pham ◽  
Kang-Hyun Jo ◽  
Van-Dung Hoang
Keyword(s):  
Action Recognition ◽  
Local Features ◽  
Hybrid Classifiers

LF-EME: Local features with elastic manifold embedding for human action recognition

2013 ◽  
Vol 99 ◽  
pp. 144-153 ◽  
Author(s):  
Xiaoyu Deng ◽  
Xiao Liu ◽  
Mingli Song ◽  
Jun Cheng ◽  
Jiajun Bu ◽  
...  
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Local Features ◽  
Manifold Embedding

scholarly journals Representation for Action Recognition Using Trajectory-Based Low-Level Local Feature and Mid-Level Motion Feature

2017 ◽  
Vol 2017 ◽  
pp. 1-7
Author(s):  
Xiaoqiang Li ◽  
Dan Wang ◽  
Yin Zhang
Keyword(s):  
Action Recognition ◽  
Human Action ◽  
Local Features ◽  
Layer Model ◽  
Motion Feature ◽  
Low Level ◽  
Level Characteristic ◽  
Key Factor ◽  
Two Layer Model ◽  
Part Model

The dense trajectories and low-level local features are widely used in action recognition recently. However, most of these methods ignore the motion part of action which is the key factor to distinguish the different human action. This paper proposes a new two-layer model of representation for action recognition by describing the video with low-level features and mid-level motion part model. Firstly, we encode the compensated flow (w-flow) trajectory-based local features with Fisher Vector (FV) to retain the low-level characteristic of motion. Then, the motion parts are extracted by clustering the similar trajectories with spatiotemporal distance between trajectories. Finally the representation for action video is the concatenation of low-level descriptors encoding vector and motion part encoding vector. It is used as input to the LibSVM for action recognition. The experiment results demonstrate the improvements on J-HMDB and YouTube datasets, which obtain 67.4% and 87.6%, respectively.

scholarly journals Multi-Scale Locality-Constrained Spatiotemporal Coding for Local Feature Based Human Action Recognition

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Bin Wang ◽  
Yu Liu ◽  
Wei Wang ◽  
Wei Xu ◽  
Maojun Zhang
Keyword(s):  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Local Features ◽  
Local Feature ◽  
Multi Scale ◽  
Spatiotemporal Feature ◽  
Group Information ◽  
Feature Based ◽  
Relationship Of

We propose a Multiscale Locality-Constrained Spatiotemporal Coding (MLSC) method to improve the traditional bag of features (BoF) algorithm which ignores the spatiotemporal relationship of local features for human action recognition in video. To model this spatiotemporal relationship, MLSC involves the spatiotemporal position of local feature into feature coding processing. It projects local features into a sub space-time-volume (sub-STV) and encodes them with a locality-constrained linear coding. A group of sub-STV features obtained from one video with MLSC and max-pooling are used to classify this video. In classification stage, the Locality-Constrained Group Sparse Representation (LGSR) is adopted to utilize the intrinsic group information of these sub-STV features. The experimental results on KTH, Weizmann, and UCF sports datasets show that our method achieves better performance than the competing local spatiotemporal feature-based human action recognition methods.

scholarly journals Robust Action Recognition Using Multi-Scale Spatial-Temporal Concatenations of Local Features as Natural Action Structures

PLoS ONE ◽  
2012 ◽  
Vol 7 (10) ◽  
pp. e46686 ◽  
Author(s):  
Xiaoyuan Zhu ◽  
Meng Li ◽  
Xiaojian Li ◽  
Zhiyong Yang ◽  
Joe Z. Tsien
Keyword(s):  
Action Recognition ◽  
Local Features ◽  
Natural Action ◽  
Multi Scale

scholarly journals Fusing $${\mathcal {R}}$$ R Features and Local Features with Context-Aware Kernels for Action Recognition

2015 ◽  
Vol 118 (2) ◽  
pp. 151-171 ◽  
Author(s):  
Chunfeng Yuan ◽  
Baoxin Wu ◽  
Xi Li ◽  
Weiming Hu ◽  
Stephen Maybank ◽  
...  
Keyword(s):  
Action Recognition ◽  
Local Features ◽  
Context Aware
Sign in / Sign up

Export Citation Format

Share Document