VATEX Captioning Challenge 2019: Multi-modal Information Fusion and Multi-stage Training Strategy for Video Captioning.
Ziqi ZhangYaya ShiJiutong WeiChunfeng YuanBing LiWeiming HuPublished in: CoRR (2019)
Keyphrases
- multi modal
- information fusion
- multistage
- semantic concepts
- video search
- data fusion
- fusion algorithm
- fusion method
- single stage
- video data
- multiple modalities
- multimedia
- video sequences
- soft computing
- multi modality
- fusion model
- high dimensional
- lot sizing
- video analysis
- multi source
- video retrieval
- audio visual
- decision level
- dynamic programming
- cross modal
- video content
- video frames
- uni modal
- real time
- multi sensor information fusion
- multimedia data
- optimal policy
- visual cues
- key frames
- particle filter
- evolutionary algorithm
- artificial intelligence