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: ICASSP (2023)
Keyphrases
- cross lingual
- video retrieval
- cross modal
- video search
- machine translation
- language modeling
- multi modal
- content based retrieval
- visual content
- semantic gap
- video content
- key frames
- text classification
- knowledge base
- semantic information
- information retrieval
- video data
- image retrieval
- news articles
- text documents
- retrieval systems
- text mining
- document clustering
- language model
- transfer learning
- visual similarity
- image classification