This paper introduces a trainable framework that combines ConvLSTM-based video text detection with GRU-based online tracking, achieving state-of-the-art F-scores on ICDAR2013 Video, Minetto, and YVT.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An End-to-end Video Text Detector with Online Tracking
This paper introduces a trainable framework that combines ConvLSTM-based video text detection with GRU-based online tracking, achieving state-of-the-art F-scores on ICDAR2013 Video, Minetto, and YVT.