Yang Liu (刘阳) @SYSU

Yang Liu (刘阳)

IEEE/ACM Member, CCF/CAAI/CSIG Member
Email: liuy856@mail.sysu.edu.cn
Office: School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China

I am currently a research associate professor at HCP Lab, School of Computer Science and Engineering, Sun Yat-sen University, working with Prof. Liang Lin. From 2019-2021, I worked as a posdoctoral fellow at School of Computer Science and Engineering, Sun Yat-sen University. I obtained my Ph.D degree of Telecommunications and Information Systems in June 2019 at Phoenix-eye (XD145) Lab, School of Telecommunications Engineering, Xidian University, advised by Prof. Zhaoyang Lu, Prof. Jing Li and Prof. Tao Yang. I serve as the reviewer of IEEE T-PAMI, T-IP, T-NNLS, T-MM, T-CSVT, CVPR, ICCV, AAAI, ACM MM, ECCV, etc. I am a member of the CSIG Visual Big Data Committee. [Chinese Version]

Computer Vision: Cross-modal Reasoning, Spatial-temporal Representation Learning

Machine Learning: Causality Inference, Self-supervised Learning, Transfer Learning

Embodied AI: Embodied Interaction, Embodied Manipulation, Robotic Control

CCF ChinaSoft 2023 Robotic Big Model and Embodied Intelligence Challenge, Third Prize, 2023.

The Third Guangdong Province Young Computer Science Academic Show, First Prize, 2023.

National Scholarship for PhD Students, 2018.

National English Competition, Third Prize, 2013.

National Mathematical Modeling Competition, Second Prize, 2012.

Related Link: AI Conference Calendar, CCF Rankings

News

2024-04: The book of multimodal large model 《多模态大模型：新一代人工智能技术范式》 is published!
2023-12: I won the third prize of CCF ChinaSoft 2023 Robotic Big Model and Embodied Intelligence Challenge!
2023-11: One first-author T-IP paper is selected as the ESI Hot Cited Paper!
2023-11: One first-author T-IP paper is selected as the ESI Highly Cited Paper!
2023-10: One accepted ACM MM 2023 paper is recommended as an oral!
2023-10: An invention patent has been granted.
2023-10: I have been selected as a member of the CSIG Visual Big Data Committee.
2023-07: One paper is accepted by ACM MM 2023!
2023-07: Two papers are accepted by ICCV 2023!
2023-06: One paper is accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence!
2023-06: I won the first prize in the Third Guangdong Province Young Computer Science Academic Show.
2023-06: One paper is accepted by ICIP 2023.
2023-04: One paper is accepted by IJCAI 2023!
2023-03: The open-source framework for causal discovery and visual-linguistic reasoning Causal-VLReasoning is online!
2023-03: I become a member of CAAI (Chinese Association for Artificial Intelligence).
2023-03: I become a member of CCF (China Computer Federation).
2023-03: I am invited as the Program Committee (PC) Member for the Computer Graphics International (CGI) 2023.
2023-03: One paper is accepted by Information Sciences.
2022-12: One review paper about causal reasoning is reported in social media by Machine Intelligence Research.
2022-11: I received the funding from Guangdong Basic and Applied Basic Research Foundation 2023.
2022-11: One review paper for causal reasoning is published online by Machine Intelligence Research.
2022-11: I am invited as the Program Committee (PC) Member for the Computational Visual Media Conference 2023.
2022-11: I am invited as the reviewer of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023.
2022-09: I become a member of IEEE Industrial Electronics Society.
2022-08: My TCGL paper published in IEEE T-IP is invited to be exhibited as the poster in Valse 2022.
2022-08: One review paper about causal reasoning is accepted by Machine Intelligence Research.
2022-08: I am invited as the Program Committee (PC) Member for the AAAI 2023.
2022-06: I become a member of CSIG.
2022-05: One paper is accepted by IEEE Transactions on Industrial Informatics.
2022-04: I received the funding from Science and Technology Projects in Guangzhou.
2022-03: One paper is accepted by CVPR 2022 as an oral presentation.
2022-01: One paper is accepted by IEEE Transactions on Image Processing. Code is available.
2022-01: One paper is accepted by ICASSP 2022.
2022-01: The code for TCGL is available.
2021-12: I am invited as the reviewer of Chinese Conference on Pattern Recognition and Computer Vision (PRCV) 2022.
2021-11: I am invited as the reviewer of IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022.
2021-10: I start working as a research associate professor at Sun-Yat-Sen University.
2021-05: One paper is accepted by IEEE Transactions on Image Processing. Code is available.
2021-04: The code for SAKDN is available.
2021-02: I become a Member of the IEEE.
2020-12: I am invitied as the reviewing expert for NSFC.
2020-11: I received the funding from National Natural Science Foundation of Guangdong Province of China 2021.
2020-09: I received the funding from National Natural Science Foundation of China 2021.
2020-06: I received the funding from China Postdoctoral Science Foundation 2020.
2020-03: I received the funding from Fundamental Research of the Central Universities 2020.
2020-01: My Ph.D Thesis (psw：ithd) is available now.
2019-10: Codes and datasets for IEEE TIP is available.
2019-10: One paper is accepted by IEEE Transactions on Image Processing.
2019-08: I start working as a postdoctoral fellow at Sun-Yat-Sen University.
2019-06: I obtain my Ph.D degree from Xidian University.

Open-source Framework

CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal Reasoning
Yang Liu, Weixing Chen, Guanbin Li, Liang Lin

[CausalVLR] [Paper] [BibTex]

                            @article{CausalVLR,
                              title={CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal Reasoning},
                              author={Liu, Yang and Chen, Weixing and Li, Guanbin and Lin, Liang},
                              journal={arXiv preprint arXiv:2306.17462},
                              year={2023}
                            }
                            }

CausalVLR is a python open-source framework for causal relation discovery, causal inference that implements state-of-the-art causality learning algorithms for various visual-linguistic reasoning tasks, such as VQA, embodied interaction, model robustness, medical report generation, etc.

Demos of Embodied AI

Embodied Interactive Robot

We implemtent and integrate active visual sensing, visual navigation, embodied dialog, robotic manipulation and robotic arm controling algorithms into the robotic dog. The robotic dog can provide vairous services for humans in complex and dynamic environments.

Embodied Interactive Agent for the Coffee Scene

The multimodal embodied interactive agent (MEIA) can translate high-level tasks expressed in natural language into a sequence of executable actions. The MEIA can generate executable action plans based on diverse requirements and the robot's capabilities. Furthermore, we construct an embodied question answering dataset based on a dynamic virtual cafe environment with the large language model. The MEIA obtained the third prize of CCF ChinaSoft 2023 Robotic Big Model and Embodied Intelligence Challenge.

Book

Multimodal Large Models: A New Generation of Artificial Intelligence Technology Paradigm
《多模态大模型：新一代人工智能技术范式》
Publishing House of Electronics Industry (PHE), ISBN 978-7-121-47547-4, 2024.
电子工业出版社，ISBN 978-7-121-47547-4, 2024.
Yang Liu, Liang Lin
刘阳, 林倞

[Resource Page (在线资源)] [JD Page (京东商城链接)][媒体报道]

Selected Papers

Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering
Yang Liu, Guanbin Li, Liang Lin
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023.

[Paper] [中文解读] [Code & Dataset] [BibTex]

                                  @article{liu2022cross,
                                         author={Liu, Yang and Li, Guanbin and Lin, Liang},
                                          journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
                                          title={Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering}, 
                                          year={2023},
                                          volume={},
                                          number={},
                                          pages={1-17},
                                          doi={10.1109/TPAMI.2023.3284038}
                                            }

MEIA: Towards Realistic Multimodal Interaction and Manipulation for Embodied Robots
Yang Liu, Xinshuai Song, Kaixuan Jiang, Weixing Chen, Jingzhou Luo, Guanbin Li, Liang Lin
arXiv:2402.00290