Multi-Modal Hierarchical Attention-Based Dense Video Captioning.
Hemalatha MunusamyC. Chandra SekharPublished in: ICIP (2023)
Keyphrases
- multi modal
- semantic concepts
- video search
- video data
- video sequences
- multiple modalities
- video streams
- audio visual
- multi modality
- video content
- video database
- multimedia
- cross modal
- high dimensional
- humanoid robot
- image annotation
- object recognition
- video analysis
- video clips
- key frames
- multimedia data
- spatial and temporal
- image representation