Scenario-Aware Recurrent Transformer for Goal-Directed Video Captioning.
Xin ManDeqiang OuyangXiangpeng LiJingkuan SongJie ShaoPublished in: ACM Trans. Multim. Comput. Commun. Appl. (2022)
Keyphrases
- goal directed
- video data
- multimedia
- fuzzy logic
- video retrieval
- video sequences
- digital video
- real time
- video streams
- video frames
- video clips
- video surveillance
- video images
- real time video
- video segmentation
- video analysis
- real world
- video content
- decision making
- feed forward
- video database
- autonomous robots
- fault diagnosis
- genetic algorithm
- automated planning
- online video
- temporal information
- multimedia data
- human activities
- mobile robot
- event recognition