Visual Relation-Aware Unsupervised Video Captioning.
Puzhao JiMeng CaoYuexian ZouPublished in: ICANN (3) (2022)
Keyphrases
- visual data
- visual analysis
- visual cues
- video sequences
- content based video retrieval
- unsupervised manner
- multimedia
- video clips
- video streams
- video data
- data driven
- visual information
- video analysis
- supervised learning
- unsupervised learning
- visual features
- video indexing
- video search
- video indexing and retrieval
- news video
- digital video
- semi supervised
- video database
- video retrieval
- video content
- video frames
- high level
- real time video
- multi modal
- space time
- video segmentation
- visual perception
- multimedia data
- low level
- video images
- visual saliency
- real time
- visual speech