C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video Retrieval.
Andrew RouditchenkoYung-Sung ChuangNina ShvetsovaSamuel ThomasRogério FerisBrian KingsburyLeonid KarlinskyDavid HarwathHilde KuehneJames R. GlassPublished in: CoRR (2022)
Keyphrases
- cross lingual
- video retrieval
- cross modal
- video search
- machine translation
- language modeling
- multi modal
- visual content
- video data
- information retrieval
- semantic gap
- text classification
- content based retrieval
- retrieval systems
- knowledge base
- multimedia databases
- text mining
- image retrieval
- video content
- text documents
- natural language processing
- text retrieval
- news articles
- document clustering
- key frames
- high level