Search Results for author: Ming Cai

Found 9 papers, 3 papers with code

Enhancing Language Representation with Constructional Information for Natural Language Understanding

1 code implementation5 Jun 2023 Lvxiaowei Xu, Jianwang Wu, Jiawei Peng, Zhilin Gong, Ming Cai, Tianxiang Wang

We adopt usage-based construction grammar as the basis of our work, which is highly compatible with statistical models such as PLMs.

Natural Language Understanding

FCGEC: Fine-Grained Corpus for Chinese Grammatical Error Correction

2 code implementations22 Oct 2022 Lvxiaowei Xu, Jianwang Wu, Jiawei Peng, Jiayu Fu, Ming Cai

Grammatical Error Correction (GEC) has been broadly applied in automatic correction and proofreading system recently.

Grammatical Error Detection

PA-ResSeg: A Phase Attention Residual Network for Liver Tumor Segmentation from Multi-phase CT Images

no code implementations27 Feb 2021 Yingying Xu, Ming Cai, Lanfen Lin, Yue Zhang, Hongjie Hu, Zhiyi Peng, Qiaowei Zhang, Qingqing Chen, Xiongwei Mao, Yutaro Iwamoto, Xian-Hua Han, Yen-Wei Chen, Ruofeng Tong

In this paper, we propose a phase attention residual network (PA-ResSeg) to model multi-phase features for accurate liver tumor segmentation, in which a phase attention (PA) is newly proposed to additionally exploit the images of arterial (ART) phase to facilitate the segmentation of portal venous (PV) phase.

Tumor Segmentation

Reconstruct Locally, Localize Globally: A Model Free Method for Object Pose Estimation

no code implementations CVPR 2020 Ming Cai, Ian Reid

If a CAD model is not available, it is possible to use multi-view visual reconstruction methods to create a geometric model, and use this in the same manner.

Object Pose Estimation

Deep-6DPose: Recovering 6D Object Pose from a Single RGB Image

no code implementations28 Feb 2018 Thanh-Toan Do, Ming Cai, Trung Pham, Ian Reid

Detecting objects and their 6D poses from only RGB images is an important task for many robotic applications.

Benchmarking Instance Segmentation +5

Cannot find the paper you are looking for? You can Submit a new open access paper.