Keyframe Segmentation and Positional Encoding for Video-guided Machine Translation Challenge 2020.
Tosho HirasawaZhishen YangMamoru KomachiNaoaki OkazakiPublished in: CoRR (2020)
Keyphrases
- machine translation
- video content
- key frames
- video database
- video clips
- language independent
- image segmentation
- video shots
- target language
- cross lingual
- video data
- word sense disambiguation
- video frames
- word alignment
- video sequences
- language processing
- information extraction
- natural language processing
- language resources
- statistical machine translation
- cross language information retrieval
- natural language generation
- natural language
- brazilian portuguese
- chinese english
- video retrieval
- video streams
- video search
- word segmentation
- query translation
- multimedia
- machine transliteration
- machine translation system
- word level
- parallel corpora
- action recognition
- multilingual documents
- probabilistic model