Classification of the Video Type and Device Used in 360-Degree Videos from the Trajectories of its Viewers' Orientations with LSTM Neural Network Models.
Antoni OliverPere A. PalmerJavier del MolinoAntoni BibiloniPublished in: IMX (2022)
Keyphrases
- neural network model
- video content
- video data
- video sequences
- video frames
- video classification
- stationary camera
- semantic concept detection
- video database
- multi layer perceptron
- decision trees
- neural network
- video clips
- classification accuracy
- action classification
- support vector
- key frames
- video event
- video indexing
- video images
- video analysis
- video retrieval
- input video
- online video
- motion trajectories
- eye tracking data
- support vector machine
- event recognition
- video streams
- dynamic scenes
- support vector machine svm
- sports video
- video surveillance
- visual analysis
- video segments
- artificial neural networks
- probabilistic model
- moving camera
- spatiotemporal features
- content based copy detection
- video sharing
- neural models
- video dataset
- video shots
- recurrent neural networks
- moving objects
- multimedia