Adaptively Converting Auxiliary Attributes and Textual Embedding for Video Captioning Based on BiLSTM.
Shuqin ChenXian ZhongLin LiWenxuan LiuCheng GuLuo ZhongPublished in: Neural Process. Lett. (2020)
Keyphrases
- multimedia
- textual descriptions
- video content
- video data
- video sequences
- video streams
- real time
- video analysis
- vector space
- attribute values
- video retrieval
- video database
- video frames
- multimedia data
- digital video
- video clips
- visual content
- online video
- semantic labels
- computer vision
- multi attribute
- video surveillance
- video processing
- video segments
- video images
- low level
- real time video
- image retrieval
- natural language