44 citations
- Chinese Academy of SciencesCN6 papers
- Institute of Computing TechnologyCN6 papers
- Tsinghua UniversityCN5 papers
- University of Chinese Academy of SciencesCN4 papers
- City University of Hong KongHK2 papers
- Emory UniversityUS2 papers
- South China University of TechnologyCN2 papers
- University of California, Los AngelesUS2 papers
- Beijing University of TechnologyCN1 paper
- Duke Kunshan UniversityCN1 paper
- Duke UniversityUS1 paper
- Group Sense (China)CN1 paper
6 papers · 1 filter
Delving Globally into Texture and Structure for Image Inpainting
Haipeng Liu, Yang Wang, Meng Wang +1
Image inpainting has achieved remarkable progress and inspired abundant methods, where the critical bottleneck is identified as how to fulfill the high-frequency structure and low-…
TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation
Jiawei Yang, Yao Zhang, Yuan Liang +3
Deep learning models are notoriously data-hungry. Thus, there is an urging need for data-efficient techniques in medical image analysis, where well-annotated data are costly and ti…
MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction
Guozhi Tang, Lele Xie, Lianwen Jin +6
Visual Information Extraction (VIE) task aims to extract key information from multifarious document images (e.g., invoices and purchase receipts). Most previous methods treat the V…
Decoupled Attention Network for Text Recognition
Tianwei Wang, Yuanzhi Zhu, Lianwen Jin +5
Text recognition has attracted considerable research interests because of its various applications. The cutting-edge text recognition methods are based on attention mechanisms. How…
Deep Multimodal Speaker Naming
Yongtao Hu, Jimmy Ren, Jingwen Dai +3
Automatic speaker naming is the problem of localizing as well as identifying each speaking character in a TV/movie/live show video. This is a challenging problem mainly attributes…
On Vectorization of Deep Convolutional Neural Networks for Vision Tasks
Jimmy SJ. Ren, Li Xu
We recently have witnessed many ground-breaking results in machine learning and computer vision, generated by using deep convolutional neural networks (CNN). While the success main…