Language Models for Semantic Extraction and Filtering in Video Action Recognition.
Evelyne TzoukermannJan NeumannJana KoseckaCornelia FermüllerIan PereraFrank FerraroBenjamin SappRizwan ChaudhryGautam SinghPublished in: Language-Action Tools for Cognitive Artificial Agents (2011)
Keyphrases
- language model
- action recognition
- human actions
- action classification
- spatial temporal
- video database
- video dataset
- action detection
- language modeling
- n gram
- static images
- bag of words
- recognizing human actions
- recognition of human actions
- document retrieval
- space time interest points
- human activities
- probabilistic model
- video sequences
- retrieval model
- computer vision
- query expansion
- activity recognition
- information retrieval
- semantic concepts
- motion history images
- test collection
- video data
- semantic information
- relevance model
- video streams
- multimedia
- smoothing methods
- information extraction
- space time
- video content
- spatio temporal
- natural language
- automatic speech recognition
- text retrieval
- video shots
- video retrieval
- human motion