Multilevel Language and Vision Integration for Text-to-Clip Retrieval.
Huijuan XuKun HeBryan A. PlummerLeonid SigalStan SclaroffKate SaenkoPublished in: AAAI (2019)
Keyphrases
- information retrieval
- text retrieval
- language generation
- computational linguistics
- english text
- retrieval engine
- text to speech synthesis
- document indexing
- document analysis
- multimedia documents
- computer vision
- semantic content
- information retrieval systems
- text indexing
- english language
- retrieval systems
- cross media
- news video
- retrieval model
- native language
- programming language
- indian languages
- multimedia search
- image retrieval
- text to speech
- vision system
- natural language
- natural language processing
- image database
- structured documents
- text collections
- language learning
- video clips
- content and structure
- relevance feedback
- document retrieval
- content based retrieval
- text documents
- text queries
- keywords
- conceptual retrieval
- multimedia
- text generation
- document content
- document level
- natural language generation
- video search
- test collection
- web documents