Journal ArticleDOI
Region-based Mixture Models for human action recognition in low-resolution videos
Reads0
Chats0
TLDR
The Layered Elastic Motion Tracking (LEMT) method is adopted, a hybrid feature representation is presented to integrate both of the shape and motion features, and a Region-based Mixture Model (RMM) is proposed to be utilized for action classification.About:
This article is published in Neurocomputing.The article was published on 2017-07-19. It has received 15 citations till now. The article focuses on the topics: Optical flow & Feature (machine learning).read more
Citations
More filters
Journal ArticleDOI
Spatial-temporal pyramid based Convolutional Neural Network for action recognition
TL;DR: A novel network, Spatial-Temporal Pyramid Network (S-TPNet), is proposed to extract spatial-temporal pyramid features for action recognition in videos that can be trained in an end-to-end fashion with great efficiency.
Journal ArticleDOI
Three-Stream Network With Bidirectional Self-Attention for Action Recognition in Extreme Low Resolution Videos
TL;DR: This letter presents a novel three-stream network for action recognition in extreme low resolution (LR) videos that uses the trajectory-spatial network, which is robust against visual distortion, instead of the pose information to complement the two- stream network.
Journal ArticleDOI
Class-balanced siamese neural networks
TL;DR: This paper focuses on metric learning with Siamese Neural Networks (SNN) and proposes three contributions: a tuple-based architecture, an objective function with a norm regularisation and a polar sine-based angular reformulation for cosine dissimilarity learning.
Journal ArticleDOI
Predicting short-term traffic flow in urban based on multivariate linear regression model
TL;DR: A multiple linear regression model for prediction of short-term traffic flow in urban is constructed and shows that the average prediction accuracy of the proposed method is as high as 98.48%, and the prediction time is always less than 0.7 s, which is shorter.
Journal ArticleDOI
Vector space based augmented structural kinematic feature descriptor for human activity recognition in videos
TL;DR: A vector space based augmented structural kinematic feature descriptor is proposed for human activity recognition that combines both the local and global features using augmented matrix schema and thereby increases the robustness of the descriptor.
References
More filters
Journal ArticleDOI
A Computational Approach to Edge Detection
TL;DR: There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.
Posted Content
UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
TL;DR: This work introduces UCF101 which is currently the largest dataset of human actions and provides baseline action recognition results on this new dataset using standard bag of words approach with overall performance of 44.5%.
Proceedings ArticleDOI
Learning realistic human actions from movies
TL;DR: A new method for video classification that builds upon and extends several recent ideas including local space-time features,space-time pyramids and multi-channel non-linear SVMs is presented and shown to improve state-of-the-art results on the standard KTH action dataset.
Journal ArticleDOI
On Space-Time Interest Points
TL;DR: This paper builds on the idea of the Harris and Förstner interest point operators and detects local structures in space-time where the image values have significant local variations in both space and time and illustrates how a video representation in terms of local space- time features allows for detection of walking people in scenes with occlusions and dynamic cluttered backgrounds.
Journal ArticleDOI
Actions as Space-Time Shapes
TL;DR: The method is fast, does not require video alignment, and is applicable in many scenarios where the background is known, and the robustness of the method is demonstrated to partial occlusions, nonrigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action, and low-quality video.