scholarly journals Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

2016 ◽  
pp. 20-36 ◽  
Author(s):  
Limin Wang ◽  
Yuanjun Xiong ◽  
Zhe Wang ◽  
Yu Qiao ◽  
Dahua Lin ◽  
...  
Keyword(s):  
Action Recognition ◽  
Good Practices ◽  
Temporal Segment

scholarly journals Temporal Segment Networks for Action Recognition in Videos

2019 ◽  
Vol 41 (11) ◽  
pp. 2740-2755 ◽  
Author(s):  
Limin Wang ◽  
Yuanjun Xiong ◽  
Zhe Wang ◽  
Yu Qiao ◽  
Dahua Lin ◽  
...  
Keyword(s):  
Action Recognition ◽  
Temporal Segment

scholarly journals Accelerating Deep Action Recognition Networks for Real-Time Applications

2019 ◽  
Vol 9 (2) ◽  
pp. 16-31
Author(s):  
David Ivorra-Piqueres ◽  
John Alejandro Castro Vargas ◽  
Pablo Martinez-Gonzalez
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Action Recognition ◽  
Proof Of Concept ◽  
University Of Central Florida ◽  
Central Florida ◽  
Video Frames ◽  
Real Time Applications ◽  
The University ◽  
Temporal Segment

In this work, the authors propose several techniques for accelerating a modern action recognition pipeline. This article reviewed several recent and popular action recognition works and selected two of them as part of the tools used for improving the aforementioned acceleration. Specifically, temporal segment networks (TSN), a convolutional neural network (CNN) framework that makes use of a small number of video frames for obtaining robust predictions which have allowed to win the first place in the 2016 ActivityNet challenge, and MotionNet, a convolutional-transposed CNN that is capable of inferring optical flow RGB frames. Together with the last proposal, this article integrated a new software for decoding videos that takes advantage of NVIDIA GPUs. This article shows a proof of concept for this approach by training the RGB stream of the TSN network in videos loaded with NVIDIA Video Loader (NVVL) of a subset of daily actions from the University of Central Florida 101 dataset.

scholarly journals Temporal Segment Connection Network for Action Recognition

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 179118-179127
Author(s):  
Qian Li ◽  
Wenzhu Yang ◽  
Xiangyang Chen ◽  
Tongtong Yuan ◽  
Yuxia Wang
Keyword(s):  
Action Recognition ◽  
Temporal Segment

Vowel Recognition Threshold as a Function of Temporal Segmentations

1970 ◽  
Vol 13 (4) ◽  
pp. 715-724 ◽  
Author(s):  
Richard L. Powell ◽  
Oscar Tosi
Keyword(s):  
Normal Hearing ◽  
Recognition Threshold ◽  
Vowel Sound ◽  
Significant Difference ◽  
The Mean ◽  
Vowel Recognition ◽  
Temporal Segment

Vowels were segmented into 15 different temporal segments taken from the middle of the vowel and ranging from 4 to 60 msecs, then presented to 6 subjects with normal hearing. The mean temporal-segment recognition threshold of 15 msecs with a range from 9.3 msecs for the /u/ to 27.2 milliseconds for the /a/. Misidenti-fication of vowels was most often confused with the vowel sound adjacent to it on the vowel-hump diagram. There was no significant difference between the cardinal and noncardinal vowels.

Professional Good Practices Scale--Nursing Homes

2018 ◽  
Author(s):  
Gema Pérez-Rojo ◽  
C. Noriega ◽  
C. Velasco ◽  
J. López
Keyword(s):  
Nursing Homes ◽  
Good Practices

Good Practices for Courts

10.1596/25101 ◽  
2016 ◽  
Author(s):  
Heike Gramckow ◽  
Omniah Ebeid ◽  
Erica Bosio ◽  
Jorge Luis Silva Mendez
Keyword(s):  
Good Practices

Human action recognition using simple geometric features and a finite state machine

2013 ◽  
Vol 18 (2-3) ◽  
pp. 49-60 ◽  
Author(s):  
Damian Dudzńiski ◽  
Tomasz Kryjak ◽  
Zbigniew Mikrut
Keyword(s):  
Action Recognition ◽  
Finite State Machine ◽  
Recognition Rate ◽  
Human Action Recognition ◽  
Human Action ◽  
Video Stream ◽  
State Machine ◽  
Recognition Algorithm ◽  
Finite State ◽  
Correct Recognition Rate

Abstract In this paper a human action recognition algorithm, which uses background generation with shadow elimination, silhouette description based on simple geometrical features and a finite state machine for recognizing particular actions is described. The performed tests indicate that this approach obtains a 81 % correct recognition rate allowing real-time image processing of a 360 X 288 video stream.

Sign in / Sign up

Export Citation Format

Share Document