M3: Multimodal Memory Modelling for Video Captioning.
Junbo WangWei WangYan HuangLiang WangTieniu TanPublished in: CVPR (2018)
Keyphrases
- multimedia
- video data
- video sequences
- video content
- video streams
- memory requirements
- video analysis
- multi modal
- story segmentation
- digital video
- real time
- multimodal information
- video frames
- real time video
- computing power
- video retrieval
- multimedia data
- spatial and temporal
- video segmentation
- motion estimation
- limited memory
- broadcast news
- key frames
- online video
- multiple modalities