VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding.
Hu XuGargi GhoshPo-Yao HuangDmytro OkhonkoArmen AghajanyanFlorian MetzeLuke ZettlemoyerChristoph FeichtenhoferPublished in: CoRR (2021)
Keyphrases
- text understanding
- natural language understanding
- natural language text
- natural language processing
- entity identification
- computational linguistics
- video data
- artificial intelligence
- supervised learning
- topic modeling
- knowledge representation
- natural language
- domain knowledge
- training set
- association rules
- expert systems
- metadata
- search engine