Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation.
Xueliang ZhaoYuxuan WangChongyang TaoChenshuo WangDongyan ZhaoPublished in: CoRR (2022)
Keyphrases
- multi modal
- semantic concepts
- video search
- multi modality
- image annotation
- cross modal
- natural language
- video shots
- multimedia
- multiple modalities
- video sequences
- video frames
- video data
- high dimensional
- visual concepts
- video streams
- semantic web
- image processing
- high level
- similarity measure
- semantic search
- dialogue system
- higher level
- audio visual
- video retrieval
- semantic similarity
- video content