ML p(r)ior | Combining ConvNets with Hand-Crafted Features for Action Recognition Based on an HMM-SVM Classifier

Combining ConvNets with Hand-Crafted Features for Action Recognition Based on an HMM-SVM Classifier

2016-02-01
This paper proposes a new framework for RGB-D-based action recognition that takes advantages of hand-designed features from skeleton data and deeply learned features from depth maps, and exploits effectively both the local and global temporal information. Specifically, depth and skeleton data are firstly augmented for deep learning and making the recognition insensitive to view variance. Secondly, depth sequences are segmented using the hand-crafted features based on skeleton joints motion histogram to exploit the local temporal information. All training se gments are clustered using an Infinite Gaussian Mixture Model (IGMM) through Bayesian estimation and labelled for training Convolutional Neural Networks (ConvNets) on the depth maps. Thus, a depth sequence can be reliably encoded into a sequence of segment labels. Finally, the sequence of labels is fed into a joint Hidden Markov Model and Support Vector Machine (HMM-SVM) classifier to explore the global temporal information for final recognition.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2016-08-02

Deep convolutional networks have achieved great success for visual recognition in still images. Howe… show more
PDF

Highlights - Most important sentences from the article

2017-05-08

Deep convolutional networks have achieved great success for image recognition. However, for action r… show more
PDF

Highlights - Most important sentences from the article

2018-01-23
1801.07455 | cs.CV

Dynamics of human body skeletons convey significant information for human action recognition. Conven… show more
PDF

Highlights - Most important sentences from the article

2017-04-02

Analyzing videos of human actions involves understanding the temporal relationships among video fram… show more
PDF

Highlights - Most important sentences from the article

2014-06-09
1406.2199 | cs.CV

We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for … show more
PDF

Highlights - Most important sentences from the article

2016-11-21
1611.06678 | cs.CV

The CNN-encoding of features from entire videos for the representation of human actions has rarely b… show more
PDF

Highlights - Most important sentences from the article

2018-04-17
1804.06055 | cs.CV

Skeleton-based human action recognition has recently drawn increasing attentions with the availabili… show more
PDF

Highlights - Most important sentences from the article

2016-04-11

Recent approaches in depth-based human activity analysis achieved outstanding performance and proved… show more
PDF

Highlights - Most important sentences from the article

2018-12-06

An unsupervised human action modeling framework can provide useful pose-sequence representation, whi… show more
PDF

Highlights - Most important sentences from the article

2018-10-19

Heterogeneous data modalities can provide complementary cues for several tasks, usually leading to m… show more
PDF

Highlights - Most important sentences from the article

2019-05-12

Research on depth-based human activity analysis achieved outstanding performance and demonstrated th… show more
PDF

Highlights - Most important sentences from the article

2018-06-29

Dynamic imaging is a recently proposed action description paradigm for simultaneously capturing moti… show more
PDF

Highlights - Most important sentences from the article

2018-02-22

We propose a method for human activity recognition from RGB data that does not rely on any pose info… show more
PDF

Highlights - Most important sentences from the article

2018-11-17

The skeleton based gesture recognition is gaining more popularity due to its wide possible applicati… show more
PDF

Highlights - Most important sentences from the article

2018-10-16

Activity recognition in videos in a deep-learning setting---or otherwise---uses both static and pre-… show more
PDF

Highlights - Most important sentences from the article

2018-10-30

We propose DeepGRU, a novel end-to-end deep network model informed by recent developments in deep le… show more
PDF