OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition.
Tom Tongjia ChenHongshan YuZhengeng YangZechuan LiWei SunChen ChenPublished in: CoRR (2023)
Keyphrases
- spatio temporal
- spatial and temporal
- spatial temporal
- action recognition
- object recognition
- human actions
- video representation
- domain knowledge
- space time
- feature extraction
- keypoints
- video streams
- information retrieval
- video data
- recognition rate
- knowledge base
- special case
- semantic information
- multimedia documents
- multimedia
- video content
- video clips
- recognition algorithm
- key concepts
- video shots
- moving objects
- video search
- shape recognition
- news video
- temporal segmentation
- text mining