NDLI: Dimensionality reduction of Fisher vectors for human action recognition

Content Provider	IET Digital Library
Author	Oruganti, Venkata Ramana Murthy Goecke, Roland
Abstract	Automatic analysis of human behaviour in large collections of videos is rapidly gaining interest, even more so with the advent of file sharing sites such as YouTube. From one perspective, it can be observed that the size of feature vectors used for human action recognition from videos has been increasing enormously in the last five years, in the order of ∼100–500K. One possible reason might be the growing number of action classes/videos and hence the requirement of discriminating features (that usually end up to be higher-dimensional for larger databases). In this study, the authors review and investigate feature projection as a means to reduce the dimensions of the high-dimensional feature vectors and show their effectiveness in terms of performance. They hypothesise that dimensionality reduction techniques often unearth latent structures in the feature space and are effective in applications such as the fusion of high-dimensional features of different types; and action recognition in untrimmed videos. They conduct all the authors’ experiments using a Bag-of-Words framework for consistency and results are presented on large class benchmark databases such as the HMDB51 and UCF101 datasets.
Starting Page	392
Ending Page	397
Page Count	6
ISSN	17519632
Volume Number	10
e-ISSN	17519640
Issue Number	Issue 5, Aug (2016)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-cvi/10/5
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2015.0091
Journal	IET Computer Vision
Publisher Date	2016-02-26
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Action Class Action Video Bag-of-word Framework Computer Vision And Image Processing Technique Dimensionality Reduction Technique Feature Projection File Sharing Site Fisher Vector Gesture Recognition High-dimensional Feature Vector HMDB51 Dataset Human Action Recognition Human Behaviour Automatic Analysis Image Recognition Large-class Benchmark Database UCF101 Dataset Untrimmed Videos Video Signal Processing YouTube
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Fully convolutional networks for action recognition

Meta-action descriptor for action recognition in RGBD video

Depth-based end-to-end deep network for human action recognition

Motion boundary emphasised optical flow method for human action recognition

Pedestrian motion recognition via Conv-VLAD integrated spatial-temporal-relational network

Recognising human interaction from videos by a discriminative model

Dimensionality reduction by LPP-L21

Two-layer discriminative model for human activity recognition

Hand gesture recognition using DWT and F-ratio based feature descriptor

Dimensionality reduction of Fisher vectors for human action recognition

Similar Documents

Fully convolutional networks for action recognition

Meta-action descriptor for action recognition in RGBD video

Depth-based end-to-end deep network for human action recognition

Motion boundary emphasised optical flow method for human action recognition

Pedestrian motion recognition via Conv-VLAD integrated spatial-temporal-relational network

Recognising human interaction from videos by a discriminative model

Dimensionality reduction by LPP-L21

Two-layer discriminative model for human activity recognition

Hand gesture recognition using DWT and F-ratio based feature descriptor

Dimensionality reduction of Fisher vectors for human action recognition