Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks

Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu, Shi-Min Hu.

arXiv:2105.02358, 2021.

PAPER   Code  

LinkNet: 2D-3D linked multi-modal network for online semantic segmentation of RGB-D videos

Jun-Xiong Cai, Tai-Jiang Mu, Yu-Kun Lai, and Shi-Min Hu.

Computers & Graphics 98: 37-47 (2021).

PAPER   Code  

Supervoxel Convolution for Online 3D Semantic Segmentation

Shi-Sheng Huang, Ze-Yu Ma, Tai-Jiang Mu, Hongbo Fu, Shi-Min Hu.

ACM Transactions on Graphics (TOG), 2021, to appear.

PROJECT   PAPER   Video   Supp  

PCT: Point Cloud Transformer

Meng-Hao Guo, Jun-Xiong Cai, Zheng-Ning Liu, Tai-Jiang Mu, Ralph R. Martin, Shi-Min Hu.

Computational Visual Media 7(2): 187-199 (2021)

PAPER   Code  

Accurate Dynamic SLAM Using CRF-Based Long-Term Consistency

Zheng-Jun Du, Shi-Sheng Huang, Tai-Jiang Mu*, Qunhe Zhao, Ralph R. Martin and Kun Xu.

IEEE Transactions on Visualization and Computer Graphics (TVCG), 2020, Preprint [doi: 10.1109/TVCG.2020.3028218].

PAPER[CVM2020 Version]   Video   Supp   Code

Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates

Congyue Deng, Tai-Jiang Mu and Shi-Min Hu.

arXiv:2006.07818, 2020.

PAPER  

Detecting Human-object Interactions with Multi-level Pairwise Feature Network

Hanchao Liu, Tai-Jiang Mu* and Xiaolei Huang.

Computational Visual Media 7(2): 229-239 (2021).

PAPER  

A new dataset of dog breed images and a benchmark for finegrained classification

Ding-Nan Zou, Song-Hai Zhang, Tai-Jiang Mu and Ming Zhang.

Computational Visual Media 6(4): 477-487, 2020.

PAPER    Dataset  

ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings

Jia-Hui Huang, Sheng Yang, Tai-Jiang Mu and Shi-Min Hu.

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2168-2177, 2020.

PAPER  

WallNet: Reconstructing General Room Layouts from RGB Images

Jiahui Huang, Zheng-Fei Kuang, Fang-Lue Zhang and Tai-Jiang Mu^*.

Graphical Models 111: 101076 (2020).

PAPER  

S4Net: Single Stage Salient-Instance Segmentation

Ruochen Fan, Ming-Ming Cheng, Qibin Hou, Tai-Jiang Mu, Jingdong Wang and Shi-Min Hu.

Computational Visual Media 6(2): 191-204 (2020).

PAPER  [Earlier CVPR 2019 version]   PROJECT   Code

Lidar-Monocular Visual Odometry using Point and Line Features

Shi-Sheng Huang, Ze-Yu Ma, Tai-Jiang Mu, Hongbo Fu and Shi-Min Hu.

Proceedings of the International Conference on Robotics and Automation (ICRA), 1091-1097, 2020.

PAPER   Video  

Lane Detection: A Survey with New Results

Dun Liang, Yuan-Chen Guo, Shao-Kui Zhang, Tai-Jiang Mu^* and Xiaolei Huang.

Journal of Computer Science and Technology 35(3): 493-505 (2020).

PAPER   PROJECT

SpinNet: Spinning convolutional network for lane boundary detection

Ruochen Fan, Xuanrun Wang, Qibin Hou, Hanchao Liu and Tai-Jiang Mu^*.

Computational Visual Media 5(4): 417-428 (2019).

PAPER  

S4Net: Single Stage Salient-Instance Segmentation

Ruochen Fan, Ming-Ming Cheng, Qibin Hou, Tai-Jiang Mu, Jingdong Wang and Shi-Min Hu.

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6103-6112, 2019.

PAPER   PROJECT   Code

Deep Point-based Scene Labeling with Depth Mapping and Geometric Patch Feature Encoding

Jun-Xiong Cai, Tai-Jiang Mu^*, Yu-Kun Lai and Shi-Min Hu.

Graphical Models 104: 101033 (2019).

PAPER  

A Large Chinese Text Dataset in the Wild

Tai-Ling Yuan, Zhe Zhu, Kun Xu, Cheng-Jun Li, Tai-Jiang Mu^* and Shi-Min Hu.

Journal of Computer Science and Technology 34(3): 509-521 (2019).

PAPER   PROJECT

Synthesizing Robot Programs with Interactive Tutor Mode

Hao Li, Yu-Ping Wang and Tai-Jiang Mu.

International Journal of Automation and Computing 16(4):462-474 (2019).

PAPER  

Deep video stabilization using adversarial networks

Sen-Zhe Xu, Jun Hu, Miao Wang, Tai-Jiang Mu and Shi-Min Hu.

Computer Graphics Forum 37(7):267-276 (2018).

PAPER  

VGPN: Voice-Guided Pointing Robot Navigation for Humans

Jun Hu, Zhongyu Jiang, Xionghao Ding, Taijiang Mu^* and Peter Hall.

IEEE International Conference on Robotics and Biomimetics (ROBIO), 1107-1112, 2018.

PAPER  

Knowledge graph construction with structure and parameter learning for indoor scene design

Yuan Liang, Fei Xu, Song-Hai Zhang, Yu-Kun Lai and Taijiang Mu^*.

Computational Visual Media 4(2): 123-137 (2018).

PAPER  

Nerva: Automated application synthesis for humanoid robot from user natural language description

Hao Li, Yu-Ping Wang and Tai-Jiang Mu^*.

Communications in Information and Systems 17(1): 45-64 (2017).

PAPER  

Image-based clothes changing system

Zhao-Heng Zheng, Hao-Tian Zhang, Fang-Lue Zhang and Tai-Jiang Mu.

Computational Visual Media 3(4): 337-347 (2017).

PAPER  

A survey on multiview video synthesis and editing

Shaoping Lu, Taijiang Mu^*, and Songhai Zhang.

Tsinghua Science and Technology 21(6): 678-695 (2016).

PAPER  

A Response Time Model for Abrupt Changes in Binocular Disparity

Tai-Jiang Mu, Jia-Jia Sun, Ralph R. Martin, and Shi-Min Hu.

The Visual Computer 31(5): 675-687 (2015).

PAPER   BIBTEX

Stereoscopic Image Completion and Depth Recovery

Tai-Jiang Mu, Ju-Hong Wang, Song-Pei Du, and Shi-Min Hu.

The Visual Computer 30(6-8): 833-843 (2014).

PAPER   BIBTEX