Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval.
Yue YangJoongwon KimArtemis PanagopoulouMark YatskarChris Callison-BurchPublished in: CoRR (2021)
Keyphrases
- video retrieval
- video database
- semantic gap
- video data
- image and video retrieval
- visual content
- lifelog
- content based retrieval
- video content
- video indexing
- video shots
- video search
- database
- concept detection
- natural language
- key frames
- retrieval systems
- multimedia
- databases
- concept based video retrieval
- video collections
- video clips
- interactive retrieval
- data model
- video sequences
- multi modal
- content based video retrieval
- semantic video
- semantic concept detection
- semantic video retrieval