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