Sequential Transformer for End-to-End Video Text Detection.
Jun-Bo ZhangMengbiao ZhaoFei YinCheng-Lin LiuPublished in: WACV (2024)
Keyphrases
- end to end
- text detection
- natural scene images
- video analysis
- scalable video
- urban scenes
- scene text
- text information
- video database
- congestion control
- connected components
- object recognition
- complex background
- video data
- aerial images
- multimedia
- outdoor scenes
- multi band
- video streams
- binary images
- high resolution
- multiscale