Multi-modal Capsule Routing for Actor and Action Video Segmentation Conditioned on Natural Language Queries.
Bruce McIntoshKevin DuarteYogesh Singh RawatMubarak ShahPublished in: CoRR (2018)
Keyphrases
- multi modal
- video segmentation
- natural language queries
- natural language interface
- video sequences
- natural language
- conceptual graphs
- video frames
- video analysis
- segmentation method
- search engine
- relevant documents
- audio visual
- high dimensional
- image annotation
- video data
- video search
- visual information
- segmentation algorithm
- keywords
- structured queries
- image sequences
- image segmentation