NDLI: Fully convolutional networks for action recognition

Content Provider	IET Digital Library
Author	Yu, Sheng Cheng, Yun Xie, Li Li, Shao Zi
Abstract	Human action recognition is an important and challenging topic in computer vision. Recently, convolutional neural networks (CNNs) have established impressive results for many image recognition tasks. The CNNs usually contain million parameters which prone to overfit when training on small datasets. Therefore, the CNNs do not produce superior performance over traditional methods for action recognition. In this study, the authors design a novel two-stream fully convolutional networks architecture for action recognition which can significantly reduce parameters while keeping performance. To utilise the advantage of spatial-temporal features, a linear weighted fusion method is used to fuse two-stream networks’ feature maps and a video pooling method is adopted to construct the video-level features. At the meantime, the authors also demonstrate that the improved dense trajectories has significant impact for action recognition. The authors’ method can achieve the state-of-the-art performance on two challenging datasets UCF101 (93.0%) and HMDB51 (70.2%).
Starting Page	744
Ending Page	749
Page Count	6
ISSN	17519632
Volume Number	11
e-ISSN	17519640
Issue Number	Issue 8, Dec (2017)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-cvi/11/8
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2017.0005
Journal	IET Computer Vision
Publisher Date	2017-07-06
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	CNN Computer Vision Computer Vision And Image Processing Technique Convolutional Neural Network Feature Maps Gesture Recognition HMDB51 Human Action Recognition Image Fusion Image Recognition Image Recognition Task Linear Weighted Fusion Method Neural Computing Technique Neural Nets Sensor Fusion Spatial-temporal Feature Two-stream Fully Convolutional Network Architecture Two-stream Network UCF101 Video Pooling Method Video-level Feature
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

Dual attention convolutional network for action recognition

Attention-based spatial–temporal hierarchical ConvLSTM network for action recognition in videos

Gesture recognition algorithm based on multi-scale feature fusion in RGB-D images

RGB-D static gesture recognition based on convolutional neural network

Fusing HOG and convolutional neural network spatial–temporal features for video-based facial expression recognition

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

Dynamic gesture recognition based on feature fusion network and variant ConvLSTM

Enhanced pooling method for convolutional neural networks based on optimal search theory

Multi-stream 3D CNN structure for human action recognition trained by limited data

Fully convolutional networks for action recognition

Similar Documents

Dual attention convolutional network for action recognition

Attention-based spatial–temporal hierarchical ConvLSTM network for action recognition in videos

Gesture recognition algorithm based on multi-scale feature fusion in RGB-D images

RGB-D static gesture recognition based on convolutional neural network

Fusing HOG and convolutional neural network spatial–temporal features for video-based facial expression recognition

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

Dynamic gesture recognition based on feature fusion network and variant ConvLSTM

Enhanced pooling method for convolutional neural networks based on optimal search theory

Multi-stream 3D CNN structure for human action recognition trained by limited data

Fully convolutional networks for action recognition