no code implementations • 28 Feb 2020 • Jinyuan Zhao, Yanna Wang, Baihua Xiao, Cunzhao Shi, Fuxi Jia, Chunheng Wang
Scene text detection task has attracted considerable attention in computer vision because of its wide application.
1 code implementation • 19 Nov 2018 • Jian Xu, Chunheng Wang, Cunzhao Shi, Baihua Xiao
Our weakly supervised ASDA method achieves state-of-the-art performance on most datasets.
no code implementations • 15 Nov 2018 • Chen Du, Chunheng Wang, Yanna Wang, Cunzhao Shi, Baihua Xiao
Different layers of deep convolutional neural networks(CNNs) can encode different-level information.
no code implementations • 29 Jun 2018 • Jian Xu, Chunheng Wang, Cunzhao Shi, Baihua Xiao
Our method excavates the space of intrinsic structure and semantic information by proposed self-supervised encoder loss.
1 code implementation • 3 Apr 2018 • Jian Xu, Chunheng Wang, Chengzuo Qi, Cunzhao Shi, Baihua Xiao
In this paper, we propose a simple but effective semantic-based aggregation (SBA) method.
1 code implementation • 14 Jul 2017 • Jian Xu, Chunheng Wang, Chengzuo Qi, Cunzhao Shi, Baihua Xiao
Without post-processing, Our IME layer achieves a boost in performance of state-of-the-art image retrieval methods with post-processing on most datasets, and needs less computational cost.
Ranked #1 on Image Retrieval on Paris6k
1 code implementation • 3 May 2017 • Jian Xu, Cunzhao Shi, Chengzuo Qi, Chunheng Wang, Baihua Xiao
In this paper, we propose a simple but effective semantic part-based weighting aggregation (PWA) for image retrieval.
no code implementations • CVPR 2013 • Zhong Zhang, Chunheng Wang, Baihua Xiao, Wen Zhou, Shuang Liu, Cunzhao Shi
In this paper, we propose a novel method for cross-view action recognition via a continuous virtual path which connects the source view and the target view.
no code implementations • CVPR 2013 • Cunzhao Shi, Chunheng Wang, Baihua Xiao, Yang Zhang, Song Gao, Zhong Zhang
Scene text recognition has inspired great interests from the computer vision community in recent years.