34 citations · 115 across the 15 of their papers we have counts for
5 papers · 1 filter
Progressive Self-Guided Loss for Salient Object Detection
Sheng Yang, Weisi Lin, Guosheng Lin +2
We present a simple yet effective progressive self-guided loss function to facilitate deep learning-based salient object detection (SOD) in images. The saliency maps produced by th…
Towards Robust Curve Text Detection with Conditional Spatial Expansion
Zichuan Liu, Guosheng Lin, Sheng Yang +3
It is challenging to detect curve texts due to their irregular shapes and varying sizes. In this paper, we first investigate the deficiency of the existing curve detection methods…
Correlation Propagation Networks for Scene Text Detection
Zichuan Liu, Guosheng Lin, Wang Ling Goh +3
In this work, we propose a novel hybrid method for scene text detection namely Correlation Propagation Network (CPN). It is an end-to-end trainable framework engined by advanced Co…
Learning Markov Clustering Networks for Scene Text Detection
Zichuan Liu, Guosheng Lin, Sheng Yang +3
A novel framework named Markov Clustering Network (MCN) is proposed for fast and robust scene text detection. MCN predicts instance-level bounding boxes by firstly converting an im…
A Binary Convolutional Encoder-decoder Network for Real-time Natural Scene Text Processing
Zichuan Liu, Yixing Li, Fengbo Ren +1
In this paper, we develop a binary convolutional encoder-decoder network (B-CEDNet) for natural scene text processing (NSTP). It converts a text image to a class-distinguished sali…