NDLI: Back-dropout transfer learning for action recognition

Content Provider	IET Digital Library
Author	Ren, Huamin Kanhabua, Nattiya Møgelmose, Andreas Liu, Weifeng Kulkarni, Kaustubh Escalera, Sergio Baró, Xavier Moeslund, Thomas B.
Abstract	Transfer learning aims at adapting a model learned from source dataset to target dataset. It is a beneficial approach especially when annotating on the target dataset is expensive or infeasible. Transfer learning has demonstrated its powerful learning capabilities in various vision tasks. Despite transfer learning being a promising approach, it is still an open question how to adapt the model learned from the source dataset to the target dataset. One big challenge is to prevent the impact of category bias on classification performance. Dataset bias exists when two images from the same category, but from different datasets, are not classified as the same. To address this problem, a transfer learning algorithm has been proposed, called negative back-dropout transfer learning (NB-TL), which utilizes images that have been misclassified and further performs back-dropout strategy on them to penalize errors. Experimental results demonstrate the effectiveness of the proposed algorithm. In particular, the authors evaluate the performance of the proposed NB-TL algorithm on UCF 101 action recognition dataset, achieving 88.9% recognition rate.
Starting Page	484
Ending Page	491
Page Count	8
ISSN	17519632
Volume Number	12
e-ISSN	17519640
Issue Number	Issue 4, Jun (2018)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-cvi/12/4
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2016.0309
Journal	IET Computer Vision
Publisher Date	2018-01-03
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Action Recognition Category Bias Classification Performance Data Handling Technique Dataset Annotation Knowledge Engineering Technique Learning in AI NB-TL Negative Back-dropout Transfer Learning Pattern Classification UCF 101 Dataset Vision Task
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

Human action recognition using weighted pooling

Converting video classification problem to image classification with global descriptors and pre-trained network

Category-wise feature extractor based on ADL method for weak-supervised object localisation

Motion boundary emphasised optical flow method for human action recognition

Deep neural network with FGL for small dataset classification

Active learning with label correlation exploration for multi-label image classification

Architecture to improve the accuracy of automatic image annotation systems

Unconstrained ear recognition using deep neural networks

Locality constrained dictionary learning for non-linear dimensionality reduction and classification

Back-dropout transfer learning for action recognition

Similar Documents

Human action recognition using weighted pooling

Converting video classification problem to image classification with global descriptors and pre-trained network

Category-wise feature extractor based on ADL method for weak-supervised object localisation

Motion boundary emphasised optical flow method for human action recognition

Deep neural network with FGL for small dataset classification

Active learning with label correlation exploration for multi-label image classification

Architecture to improve the accuracy of automatic image annotation systems

Unconstrained ear recognition using deep neural networks

Locality constrained dictionary learning for non-linear dimensionality reduction and classification

Back-dropout transfer learning for action recognition