GloTSFormer: Global Video Text Spotting Transformer.
Han WangYanjie WangYang LiCan HuangPublished in: CoRR (2024)
Keyphrases
- video data
- natural language descriptions
- video sequences
- video streams
- document analysis
- text retrieval
- information retrieval
- video segments
- fuzzy logic
- news video
- video retrieval
- video search
- text documents
- keywords
- multimedia
- text detection
- multimedia search
- real time
- video content
- video clips
- video analysis
- video frames
- closed captions
- database
- keyword spotting
- video images
- video surveillance
- key frames
- multimedia documents
- video database
- free text
- multimedia data
- textual descriptions
- text mining
- natural language
- semantic labels
- image sequences
- digital video
- global image statistics