孙立博士后、帅兵博士海外归来为我室师生做学术报告


        2017年4月14日上午,孙立博士后与帅兵博士回校看望恩师李绍滋教授与苏松志副教授,同时面向全体实验室师生就自身当前研究方向进行了一场学术报告。汇报主要围绕两人近期主要工作展开,帅兵博士就自己的论文《scene segmentation with deep neural networks》进行了专业阐述,并与李绍滋教授深入讨论了场景分割的技术细节,同时细致回答了张佳博士与钟准博士的问题。孙立博士后展示了自己关于机器人视觉工作的一些科研成果,该工作主要利用弱监督学习方法使机器人具有自动分类衣物的功能,据孙立博士后阐述,该工作已在英国BBC电视台播出报道。同时孙立博士后围绕机器人视觉的发展与瓶颈与老师和同学进行了深入浅出的讨论。
        以下为帅兵和孙立的相关信息。
         帅兵,2012年毕业于厦门大学,取得硕士学位,现于新加坡南洋理工大学攻读博士学位,主要研究方向为基于深度学习的场景语义分割,现已在顶级会议与期刊上发表多篇优质论文。主要研究成果如下:
1. Shuai B, Liu T, Wang G. Improving fully convolution network for semantic segmentation. ArXiv Pre-print, Nov, 2016.
2. Shuai B, Zuo Z, Wang B, Wang G. Scene Segmentation with DAG-Recurrent Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2017. (under minor revision)
3. Abul Nabi Abrar, Shuai B, Wang G. Episodic CAMN: Contextual Attention-based Memory Net- works for Scene Labeling. IEEE Proceedings on Computer Vision and Pattern Recognition (CVPR), 2017.
4. Hu Ping, Shuai B, Wang G. Deep Level Sets for Salient Object Detection. IEEE Proceedings on Computer Vision and Pattern Recognition (CVPR), 2017.
5. Rahul R.Varior, Shuai B, Lu J, Xu D, Wang G. A siamese long short-term memory architecture for human re-identication. European Conference on Computer Vision (ECCV), Oct, 2016.
6. Shuai B, Zuo Z, Wang G, Wang B. Dag-recurrent neural networks for scene labeling. IEEE Pro- ceedings on Computer Vision and Pattern Recognition (CVPR), Jun, 2016. (equal contribution)
7. Shuai B, Zuo Z,Wang G,Wang B. Scene Parsing with Integration of Parametric and Non-parametric Models. IEEE Transactions on Image Processing (TIP), vol.25, no. 5, pp. 2379 - 2391, May. 2016.
8. Zuo Z, Shuai B, Wang G, Liu X, Wang X, Wang B. Learning Contextual Dependencies with Convo- lutional Hierarchical Recurrent Neural Networks. IEEE Transactions on Image Processing (TIP), 2016.
9. Shuai B, Wang G, Zuo Z, Wang B, Zhao L. Integrating parametric and non-parametric models for scene labeling. IEEE Proceedings on Computer Vision and Pattern Recognition (CVPR), pp. 4249-4258, June, 2015.
10. Shuai B, Zuo Z, Wang G. Quaddirectional 2d-recurrent neural networks for image labeling. IEEE Signal Processing Letters (SPL), vol. 22, no. 11, pp. 1990-1994, Nov. 2015.
11. Zuo Z, Shuai B,Wang G, Liu X,Wang X,Wang B, Chen Y. Convolutional recurrent neural networks: Learning spatial dependencies for image representation. IEEE Proceedings on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 18-26, June, 2015.
12. Zuo Z, Wang G, Shuai B, Zhao L, Yang Q, Jiang X. Learning discriminative and shareable features for scene classification. European Conference on Computer Vision (ECCV), pp. 552-568 Sep, 2014.
13. Zuo Z,Wang G, Shuai B, Zhao L, Yang Q. Exemplar based deep discriminative and shareable feature learning for scene image classification. Pattern Recognition (PR), vol. 48, no. 10, pp. 3004 - 3015, Oct, 2015.
         孙立,自硕士起(2010年)从事数据挖掘、机器人视觉、机器学习研究。硕士期间,获厦门大学全额奖学金, 并申请到苏格兰国家奖学金赴英国格 拉斯哥大学开始博士研究。博士期 间,为欧盟FP7项目CloPeMa(http://www.clopema.eu/)主要参与人, 贡献多个机器人演示。博士期间的成果吸引到BBC采访 (http://www.bbc.co.uk/news/uk-scotland-32612928), 并被其他国 家的多家媒体转载。2016年获得格拉斯哥大学计 算机博士学位, 现于伯明翰大学从 事博士后研究。现在进行的项目为欧盟H2020 RoMaNs,主要负责机器视觉部分的研究与开发。 主要研究成果如下:
1.Li Sun, Gerarado Aragon-Camarasa, Simon Rogers, J. Paul Siebert. “Robot Vision Architecture for Autonomous ClothesManipulation”, submitted to IEEE Transaction on Robotics. (顶级期刊、在审)
2.Li Sun, Gerarado Aragon-Camarasa, J. Paul Siebert, Aamir Khan, Simon Rogers. “Improving the Cloth Manipulation through Advanced Visual Perception”, International Journal of Advanced Robotic Systems.
3.Li Sun, Yanping Lv et al. “ECG Analysis Using Multiple Instance Learning for Myocardial Infarction Detection”, IEEE Transactionsion Biomedical Engineering, 2012. (顶级期刊、JCR 2)
4.Li Sun, Cheng Zhao, Rustam Stolkin. "Weakly-supervised DCNN for RGB-D Object Recognition in Real-World Applications Which Lack Large-scale Annotated Training Data", International Conference on Intelligent Robots and Systems (IROS) 2017. (在审,顶级会议)
5.Cheng Zhao, Li Sun, Rustam Stolkin. " A Fully End-To-End Deep Learning Approach For Real-Time Simultaneous 3D Reconstruction And Material Recognition", International Conference on Advanced Robotics (ICAR) 2017.
6.Li Sun, Simon Rogers, Gerarado Aragon-Camarasa, J. Paul Siebert. "Recognising the Clothing Categories from Free-Configuration using Gaussian-Process-Based Interactive Perception", International Conference of Robotics and Automation (ICRA) 2016. (顶级会议)
7.Li Sun, Gerardo Aragon-Camarasa, J. Paul Siebert, Simon Rogers. “Accurate Garment Manipulation using Binocular Stereo Head with the Application to Dual-Arm Flattening”,International Conference of Robotics and Automation ( ICRA) 2015. (顶级会议)
8.Aamir Khan, Li Sun, Gerardo Aragon-Camarasa, Paul Siebert, “Interactive Perception Based on Gaussian Process Classification for House-Hold Objects Recognition and Sorting”, IEEE International Conference on Robotics and Biomimetics, 2016
9.Aamir Khan, Gerardo Aragon-Camarasa, Li Sun, Paul Siebert, “On the Calibration of Active Binocular and RGBD Vision Systems for Dual-Arm Robots”, IEEE International Conference on Robotics and Biomimetics, 2016.
10.Adam Schmidt, Li Sun, Gerardo Aragon-Camarasa, J. Paul Siebert. “The Calibration of the Pan-Tilt Units for the Active Stereo Head”. Image Processing and Communications Challenges 7 389, 213-221, 2015.
11.Li Sun, Gerardo Aragon-Camarasa, Paul Siebert, Simon Rogers. “Advances in robot manipulation of Clothes and Flexible Objects”, International Conference of Robotics and Automation (ICRA) Workshop on Clothes Manipulation. 2014.
12.Li Sun, Gerarado Aragon-Camarasa, J. Paul Siebert, Simon Rogers. “ A Heuristic-Based Approach for Flattening Wrinkled Clothes”,14th Towards Autonomous Robotic Systems, 2013.
13.Li Sun, Yanping Lv, Kaitao Yang, et al. “Heartbeat Classification Model with Supervised Dimensionality Reduction Framework based on MCA”, China Conference on Machine Learning(CCML), 2011.

帅兵博士进行学术报告

孙立博士后进行学术报告

孙立博士后与帅兵博士同实验室师生合影