MRCap: Multi-modal and Multi-level Relationship-based Dense Video Captioning.
Wei ChenJianwei NiuXuefeng LiuPublished in: ICME (2023)
Keyphrases
- multi modal
- video search
- semantic concepts
- multi modality
- video data
- video streams
- multimedia
- audio visual
- video content
- image annotation
- video sequences
- video frames
- high dimensional
- cross modal
- multiple modalities
- video database
- multimedia data
- spatial and temporal
- video analysis
- single modality
- image processing
- particle filter