NDLI: Multi-level action detection via learning latent structure

Content Provider	IEEE Xplore Digital Library
Author	Bozorgtabar, B. Goecke, R.
Copyright Year	2015
Description	Author affiliation: IHCC, Australian Nat. Univ., Canberra, ACT, Australia (Goecke, R.) \|\| HCC Lab., Univ. of Canberra, Canberra, ACT, Australia (Bozorgtabar, B.)
Abstract	Detecting actions in videos is still a demanding task due to large intra-class variation caused by varying pose, motion and scales. Conventional approaches use a Bag-of-Words model in the form of space-time motion feature pooling followed by learning a classifier. However, since the informative body parts motion only appear in specific regions of the body, these methods have limited capability. In this paper, we seek to learn a model of the interaction among regions of interest via a graph structure. We first discover several space-time video segments representing persistent moving body parts observed sparsely in video. Then, via learning the hidden graph structure (a subset of the graph), we identify both spatial and temporal relations between the subsets of these segments. In order to seize the more discriminative motion patterns and handle different interactions between body parts from simple to composite action, we present a multi-level action model representation. Consequently, for action classification, the classifier learned through each action model labels the test video based on the action model that gives the highest probability score. Experiments on challenging datasets, such as MSR II and UCF-Sports including complex motions and dynamic backgrounds, demonstrate the effectiveness of the proposed approach that outperforms state-of-the-art methods in this context.
Starting Page	3004
Ending Page	3008
File Size	1297196
Page Count	5
File Format	PDF
e-ISBN	9781479983391
DOI	10.1109/ICIP.2015.7351354
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-09-27
Publisher Place	Canada
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Videos Motion segmentation Feature extraction Deformable models Correlation Tracking Trajectory latent structure Action detection pooling regions multi-level video representation
Content Type	Text
Resource Type	Article

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

KLT Feature Based Vehicle Detection and Tracking in Airborne Videos

Tracking Salient Keypoints for Human Action Recognition

Human movement summarization and depiction from videos

Video jitter analysis for automatic bootleg detection

MULTI-LEVEL ACTION DETECTION VIA LEARNING LATENT STRUCTURE

Hierarchical Feature Pooling with Structure Learning: A New Method for Pedestrian Detection

A study of relative motion point trajectories for action recognition

Real-Time Tracking via Deformable Structure Regression Learning

Predictive multiple motion fields for trajectory completion: Application to surveillance systems

Multi-level action detection via learning latent structure

Similar Documents

KLT Feature Based Vehicle Detection and Tracking in Airborne Videos

Tracking Salient Keypoints for Human Action Recognition

Human movement summarization and depiction from videos

Video jitter analysis for automatic bootleg detection

MULTI-LEVEL ACTION DETECTION VIA LEARNING LATENT STRUCTURE

Hierarchical Feature Pooling with Structure Learning: A New Method for Pedestrian Detection

A study of relative motion point trajectories for action recognition

Real-Time Tracking via Deformable Structure Regression Learning

Predictive multiple motion fields for trajectory completion: Application to surveillance systems

Multi-level action detection via learning latent structure