End-to-end Multi-modal Video Temporal Grounding.
Yi-Wen ChenYi-Hsuan TsaiMing-Hsuan YangPublished in: CoRR (2021)
Keyphrases
- multi modal
- end to end
- scalable video
- video search
- semantic concepts
- spatial and temporal
- temporal information
- temporal correlation
- video sequences
- multi modality
- multimedia
- video data
- admission control
- high bandwidth
- video content
- multiple modalities
- audio visual
- cross modal
- video streams
- real time
- congestion control
- high dimensional
- transport layer
- application layer
- rate allocation
- video frames
- text localization and recognition
- visual data
- video analysis
- key frames
- image sequences
- uni modal