Skip to Main Content Area
CPS-VO
Contact Support
Browse
Calendar
Announcements
Repositories
Groups
Search
Search for Content
Search for a Group
Search for People
Search for a Project
Tagcloud
› Go to login screen
Not a member?
Click here to register!
Forgot username or password?
Cyber-Physical Systems Virtual Organization
Read-only archive of site from September 29, 2023.
CPS-VO
action recognition
biblio
Human Action Recognition in Video Using DB-LSTM and ResNet
Submitted by grigby1 on Mon, 01/11/2021 - 1:01pm
learning (artificial intelligence)
video-content-based monitoring
video signal processing
video processing
video frames
Scalability
ResNet152
Resiliency
resilience
recurrent neural nets
PyTorch
pubcrawl
object detection
Metrics
man-machine interaction
action recognition
image sequences
Image Processing
image motion analysis
human action recognition method
feature extraction
deep video
deep neural networks
deep bidirectional LSTM networks
DB-LSTM network
DB-LSTM
convolutional neural networks
convolutional neural network
convolutional neural nets
CNN architecture
biblio
Recognition of Visually Perceived Compositional Human Actions by Multiple Spatio-Temporal Scales Recurrent Neural Networks
Submitted by grigby1 on Mon, 10/05/2020 - 1:01pm
RGB input data
MSTRNN model aid
multiple spatio-temporal scales recurrent neural network model
multiple timescale recurrent dynamics
neural activities
pubcrawl
recurrent neural nets
recurrent neural network
Recurrent neural networks
learning (artificial intelligence)
spatio-temporal constraints
spatio-temporal information extraction
Spatiotemporal phenomena
symbol grounding
Training
visualization
visually perceived compositional human action recognition
different compositionality levels
Biological neural networks
Compositionality
conventional convolutional neural network model
convolution
Convolutional codes
convolutional neural network (CNN)
critical spatio-temporal information
deep learning model
action recognition
dynamic vision processing
feature extraction
feedforward neural nets
gesture recognition
human action datasets
image motion analysis
image representation
biblio
Simple, Efficient and Effective Encodings of Local Deep Features for Video Action Recognition
Submitted by grigby1 on Mon, 11/19/2018 - 11:20am
action recognition
deep feature encoding
deep video
Metrics
pubcrawl
resilience
Resiliency
Scalability
video classification
biblio
Incremental knowledge acquisition and self-learning for autonomous video surveillance
Submitted by K_Hooper on Wed, 04/04/2018 - 8:56am
unlabeled video streams
knowledge acquisition
object detection
pubcrawl
Resiliency
safety purpose
Scalability
self-learning
Self-Organizing Maps
standard machine learning pipelines
Intelligent Video Analysis
Unsupervised Learning
unsupervised machine learning
video feed
video frame
video signal processing
video stream
video streaming
video surveillance
video surveillance systems
Hazards
Anomaly Detection
autonomous video surveillance
benchmark video dataset
Change detection
Clustering algorithms
cognition
event detection
feature extraction
hazard detection
action recognition
Heuristic algorithms
Human behavior
imperative security
incremental knowledge acquisition
incremental learning
incremental machine learning
Industry 4.0
industry/smart factory settings
intelligent high-level video analysis
biblio
"Reconstruction-free inference on compressive measurements"
Submitted by grigby1 on Tue, 02/21/2017 - 12:10pm
Image reconstruction
SWIR
subNyquist sampling rates
SPC
spatial-multiplexing cameras
single-pixel camera
signal-to-noise ratios
short-wave infrared region
reconstruction-free inference
pubcrawl170104
pseudorandom spatial masks
nonlinear feature extraction
inference mechanisms
imaging devices
action recognition
Image coding
high-level visual inference problems
high-dimensional signals
feature extraction
face recognition
Face
Databases
correlational features
Correlation
compressive measurements
compressive cameras
coded measurements
Cameras
