Dr. Lianli Gao(高联丽) is a Professor in School of Computer Science and Engineering (CSE) at University of Electronic Science and Technology of China (UESTC). Dr. Gao received her Ph.D in School of Electronic Engineering and Computer Science (ITEE) at University of Queensland in 2014 (under the supervision of Prof. Jane Hunter, Prof. Michael Bruenig and A/Prof. Yuan-Fang Li and her B.CS. in School of Computer Science and Engineering (CSE) at University of Electronic Science and Technology of China (UESTC) in 2009, respectively.

Dr. Gao is the leader of the Multimedia Analysis and Visual Cognition research group. She has a strong ability to develop and author successful grant funding proposals in close collaboration with industry, government partners, and colleagues within and across universities. Her research has been supported by 12 nationally competitive research grants, including one Major Project from the Ministry of Science and Technology of China, two key projects from the National Natural Science Foundation of China, four projects from the industry, etc. In addition, she has served or will serve as ECCV Area Chair 2024, WACV Area Chair 2022-2024, program committee of the IJCAI 24 track on AI and Social Good, AAAI SPC 2022, ACM MM 2021 Session Chair, ACM MM 2021 Workshop Co-chair, IJCAI Session Chair 2019, Guest Editor of 2019 Journal of Visual Communication and Image Representation, etc.

Her research interests include multimedia understanding, computer vision, artificial intelligence (AI), machine learning, and AI for Robotics, and published over 160 publications at prestigious journals and proceedings in prominent conferences (including 70+ IEEE/ACM Transactions and 70+ CCF-A papers (Chinese Computing Federation A ranked (e.g., CVPR, ICCV, NeurIPS, ICML, and ICLR)). Her publications have been cited in Google Scholar more than 7,400 times, and her H-Index in Google Scholar is 44. She has received Best Student Paper Award from Australasian Database Conference 2017, Rising Star Award from IEEE Technical Community on Multimedia Computing 2020, Sichuan Provincial Academic/Technical Leader (Reserve Candidate) 2021, UESTC Research Excellence Award (2018, 2020,2023), Alibaba DAMO Academy Young Fellow Award 2019, Rising Star of Science Award 2023, and also has been selected as one of the 2023 Chinese Young Female Scholars in Artificial Intelligence for her outstanding academic performance in AI. In terms of international challenges she received ICCV Deeper Action 3rd Place Award in Kinetics-TPS Challenge on Part-level Action Parsing 2021, CVPR Security AI Challenger Phrase VI Track 1st Place award in White-box Adversarial Attacks on ML Defense Models 2021, ICCV COCO DensePose Challenge 2nd place award 2019, OPPO Security Challenge 2nd Place 2021, and ECCV DeeperAction Track4 3nd Place 2022, etc.

🔥 Hire

We consistently have open positions available for Professors, Associate Professors, Lecturers, Postdocs, and PhD students. If you are interested Feel free to reach out to me via email.

🔥 News

• 2024.10:   Two papers accepted by NeurIPS 2024!
• 2024.09:   appointed as an Associate Editor for IEEE Transactions on Multimedia 2024!
• 2024.08:   Best Paper Candidate of ICME 2024!
• 2024.02:   Two papers were accepted by IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024)!
• 2024.01:   Four papers were accepted by IEEE Transactions on Multimedia (TMM 2024)!
• 2023.10:   One paper was accepted by IEEE Transactions on Image Processing (TIP 2023)!
• 2023.09:   One paper was accepted by Annual Conference on Neural Information Processing Systems (NeurIPS 2023)!
• 2023.07:   Four papers were accepted by ACM Multimedia (MM 2023)!
• 2023.07:   One paper was accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2023)!
• 2023.05:   Two papers were accepted by IEEE/CVF International Conference on Computer Vision (ICCV 2023)!
• 2023.03:   One paper was accepted by IEEE Transactions on Image Processing (TIP 2023)!
• 2023.02:   One paper was accepted by IEEE Transactions on Image Processing (TIP 2023)!

📝 Publications

Here are some selective publications. For full publications, please visit my Google Scholar and DBLP.

NeurIPS 2024

CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model.
C. Chen, J. Zhu, X. Luo, H. T. Shen, Lianli Gao, J. Song.
In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
Paper | Code

Proposing a benchmark of Continual Instruction tuNing for MLLMs .

NeurIPS 2024

Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization.
B. Chen, X. Lyu, Lianli Gao, J. Song and H. T. Shen.
In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
Paper | Code

Alleviating Hallucinations in LVLMs.

IJCV 2024

Informative scene graph generation via debiasing.
Lianli Gao, X. Lyu, Y. Guo, Y. Hu, Y.-F. Li, L. Xu, H. T. Shen, and J. Song. ArXiv (**), 2024
Paper | Code

Making balanced and informative predicate prediction for SGG.

CVPR 2024

Dept: Decoupled prompt tuning.
J. Zhang, S. Wu, Lianli Gao, H. T. Shen, and J. Song.
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Paper | Code

Overcoming base-new trade-off problem for existing prompt tuning methods.

CVPR 2024

Prog: Prompting-to simulate generalized knowledge for universal cross-domain retrieval.
K. Fang, J. Song, Lianli Gao, P. Zeng, Z.-Q. Cheng, X. Li, and H. T. Shen.
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Paper | Code

Applying prompt tuning to produce generalized features for UCDR.

TPAMI 2023

Label-guided generative adversarial network for realistic image synthesis.
J. Zhu, Lianli Gao, J. Song, Y. Li, F. Zheng, X. Li, and H. T. Shen.
IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 45(3):3311–3328, 2023
Paper | Code

Bridging semantic gap between labels and images for Label-Image Generation.

TPAMI 2023

Adaptive fine-grained predicates learning for scene graph generation.
X. Lyu, Lianli Gao, P. Zeng, H. T. Shen, and J. Song.
IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 45(11):13921–13940, 2023
Paper | Code

Ensuring balanced and efficient learning process for fine-grained SGG.

ICML 2023

A closer look at few-shot classification again.
X. Luo, H. Wu, J. Zhang, Lianli Gao, J. Xu, and J. Song.
In International Conference on Machine Learning (ICML), pages 23103–23123, 2023
Paper | Code

Empirically proving disentanglement of training and test-time adaptation algorithms in FSL.

TIP 2023

Toward a unified transformer-based framework for scene graph generation and human-obfect interaction detection.
T. He, Lianli Gao, J. Song, and Y. Li.
IEEE Trans. Image Process. (TIP), 32:6274–6288, 2023
Paper | Code

Build a Unified Transformer-based Framework for SGG and HOI.

CVPR 2023

Prototype-based Embedding Network for Scene Graph Generation.
C. Zheng, X. Lyu, Lianli Gao, B. Dai, and J. Song.
In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 22783–22792, 2023
Paper | Code

Acquiring robust features for reliable relation prediction in SGG.

ICCV 2023

Part-aware transformer for generalizable person re-identification.
H. Ni, Y. Li, Lianli Gao, H. T. Shen, and J. Song.
In IEEE/CVF International Conference on Computer Vision (ICCV), pages 11246–11255, 2023
Paper | Code

Mitagating domain-specific biases in Domain generalization person ReID.

MM 2023

Moviefactory: Automatic movie creation from text using large generative models for language and images.
J. Zhu, H. Yang, H. He, W.Wang, Z. Tuo, W. Cheng, Lianli Gao, J. Song, and J. Fu.
In Proceedings of the 31st ACM International Conference on Multimedia (ACM MM), pages 9313–9319, 2023
Paper | Demo

Empowering users to create captivating movies using simple text inputs.

• TIP 2023 From global to local: Multi-scale out-of-distribution detection. J. Zhang, Lianli Gao, B. Hao, H. Huang, J. Song, and H. Shen. IEEE Trans. Image Process., 32:6115–6128, 2023. Code
• ICCV 2023 DETA: denoised task adaptation for few-shot learning. J. Zhang, Lianli Gao, X. Luo, H. Shen, and J. Song. In IEEE/CVF International Conference on Computer Vision, ICCV, pages 11507–11517, 2023. Code
• TIP 2022 Hierarchical representation network with auxiliary tasks for video captioning and video question answering. Lianli Gao, Y. Lei, P. Zeng, J. Song, M. Wang, and H. T. Shen. IEEE Trans. Image Process., 31:202–215, 2022. Code
• TIP 2022 Video question answering with prior knowledge and object-sensitive learning. P. Zeng, H. Zhang, Lianli Gao, J. Song, and H. T. Shen. IEEE Trans. Image Process., 31:5936–5948, 2022. Code
• ECCV 2022 State-aware compositional learning toward unbiased training for scene graph generation. T. He, Lianli Gao, J. Song, and Y. Li. IEEE Trans. Image Process., 32:43–56, 2023. Code
• CVPR 2022 Practical evaluation of adversarial robustness via adaptive auto attack. Y. Liu, Y. Cheng, Lianli Gao, X. Liu, Q. Zhang, and J. Song. In IEEE/CVF Conference on Computer Vision and PatternRecognition, CVPR, pages 15084–15093, 2022. Code
• CVPR 2022 Unified multivariate gaussian mixture for efficient neural image compression. X. Zhu, J. Song, Lianli Gao, F. Zheng, and H. T. Shen. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pages 17591–17600, 2022. Code
• CVPR 2022 Fine-grained predicates learning for scene graph generation. X. Lyu, Lianli Gao, Y. Guo, Z. Zhao, H. Huang, H. T. Shen, and J. Song. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pages 19445–19453, 2022. Code
• ECCV 2022 Towards open-vocabulary scene graph generation with prompt-based finetuning. T. He, Lianli Gao, J. Song, and Y. Li. In IEEE/CVF International Conference on Computer Vision, ICCV, pages 56–73, 2022. Code
• ECCV 2022 Frequency domain model augmentation for adversarial attack. Long, Q. Zhang, B. Zeng, Lianli Gao, X. Liu, J. Zhang, and J. Song. In IEEE/CVF International Conference on Computer Vision, ICCV, pages 549–566, 2022. Code
• ICLR 2022 Beyond imagenet attack: Towards crafting adversarial examples for black-box domains. Q. Zhang, X. Li, Y. Chen, J. Song, Lianli Gao, Y. He, and H. Xue. In The Tenth International Conference on Learning Representations, ICLR, 2022. Code
• NeurIPS 2022 A differentiable semantic metric approximation in probabilistic embedding for cross-modal retrieval. H. Li, J. Song, Lianli Gao, P. Zeng, H. Zhang, and G. Li. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems, NeurIPS, 2022. Code
• NeurIPS 2022 Natural color fool: Towards boosting black-box unrestricted attacks. S. Yuan, Q. Zhang, Lianli Gao, Y. Cheng, and J. Song. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems, NeurIPS, 2022. Code
• NeurIPS 2022 A lower bound of hash codes’ performance. X. Zhu, J. Song, Y. Lei, Lianli Gao, and H. Shen. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems, NeurIPS, 2022. Code
• TPAMI 2020 Hierarchical lstms with adaptive attention for visual captioning. Lianli Gao, X. Li, J. Song, and H. T. Shen. IEEE Trans. Pattern Anal. Mach. Intell., 42(5):1112–1131, 2020. Code

🎖 Honors and Services

• Research Honors:
  • 2023, 2024 Rising Star of Science Award.
  • 2023, 2020, 2018 UESTC Research Excellence Award.
  • 2023, 2018 UESTC Excellent Faculty Award for Teaching Excellence.
  • 2023 Chinese Young Female Scholars in Artificial Intelligence.
  • 2021 Sichuan Provincial Academic/Technical Leader (Reserve Candidate).
  • 2020 IEEE Technical Community on Multimedia Computing Rising Star Award.
  • 2019 Alibaba DAMO Academy Young Fellow Award.
  • 2017 Australasian Database Conference Best Student Paper Award.
• Grand Challenges:
  • ECCV 2022: DeeperAction Challenge 3rd place award on Track 4 Kinetics-TPS Challenge on Part-level Action Parsing.
  • CVPR 2021: Security AI Challenger Phrase VI Track 1st Place award in White-box Adversarial Attacks on ML Defense Models.
  • ICCV 2021: DeeperAction Challenge 3rd Place award on Track 3 Kinetics-TPS Challenge on Part-level Action Parsing.
  • OPPO 2021: Security Challenge 2nd Place award.
  • ICCV 2019: COCO DensePose Task Challenge 2nd place award.
• Academic Services:
  • 2025: Senior program committee of AAAI 2025.
  • 2024: Associate Editor for IEEE Transactions on Multimedia 2024!
  • 2024: ECCV Area Chair, WACV Area Chair, program committee of the IJCAI 24 track on AI and Social Good.
  • 2023: WACV Area Chair
  • 2022: AAAI SPC, WACV Area Chair
  • 2021: ACM MM Session Chair, ACM MM Workshop Co-chair
  • 2019: IJCAI Session Chair, Guest Editor of Journal of Visual Communication and Image Representation, etc.
  • 2018-Now: Reviewers of IEEE TPAMI, TIP, TMM, TNNLS, TOC; IJCV; CVPR, ECCV, ICCV, AAAI, IJCAI, NeurIPS, ICML, MM, IJCAI and etc.

🙋 Supervisions

• Current Ph.D students:
  • Kaipeng Fang, Xiao Cai (Enrolled in Jun. 2023)
  • Xu Luo, Haonan Zhang (Enrolled in Jun. 2022)
  • Hao Ni, Sitong su (Enrolled in Jun. 2021)
  • Ji Zhang, Xinyu Lyu, and Juncheng Zhu (Enrolled in Jun. 2020)
• Former Ph.D students:

  • Tao He (Co-supervisor Monash University Jun.2018 - Nov. 2022)

    Thesis: Towards Unbiased Scene Graph Generation: Techniques and Applications.

  • Xuanhang Wang (Jun. 2019 - Jul. 2023)

    Thesis: Visual semantic understanding based visual dialogue.

  • Pengpeng Zeng (Jun. 2019 - Jul. 2023)

    Thesis: Research on Synergizing Vision and Text for Semantic Consistency Method.

  • Xiangpeng Li (Jun.2018 - Jul. 2022)

    Thesis: Research on Visual Reasoning algorithm that integrates natural language analysis.

  • Yuyu Guo (Jun. 2018 - Jul. 2022)

    Thesis: Visual Relationship Generation Based on Scene Understanding.

• Current and former M.Sc. students:
  • Hilali Sara Rita,Ke Liu, Mengqi Li, Shihan Wu, Fuwei Liu, and Lu Zhu (Enrolled in Sep. 2022)
  • Jiaqi Guo, Qisheng Chen, Youheng Sun, Yixin Qin, and Han Wang (Enrolled in Sep. 2022)
  • Durasic Aleksandra, Fuchun Wang, and Hao Wu (Enrolled in Sep. 2021)
  • Xiaoya Chen, Kai Xing, Jiahui Li, and Wenxue Shen (Graduated Jun. 2023)
  • Qike Zhao, Yaya Cheng, and Haoyu Wang (Graduated Jun. 2022)
  • Zhilong Zhou, Qian Ye, Hao He, and Ruiming Lang (Graduated Jun. 2021)
  • Qingsong Zhang, Liyang Zhang, and Ziming Fang (Graduated Jun. 2020)
  • Yuyu Guo (Graduated Jun. 2019)
  • Liangfu Cao (Graduated Jun. 2018)
  • Chuanshu Long (Graduated Jun. 2017)

💻 Research Grants

Some selective Research Grants:

• 2024.01 - 2027.12, Key Program of National Natural Science Foundation of China: “Trusted Big Cross-Meida Data Analysis and Key Technologies”, Lead PI
• 2022.01 - 2024.12, Distinguished Young Scholars of the National Natural Science Foundation of China: “Visual Cognition by Integrating Natural Language”, Lead PI.
• 2019.01 - 2022.12, General Program of National Natural Science Foundation of China: “Deep Visual Understanding by Fusing Natural Language Processing”, Lead PI.
• 2016.01 - 2018.12, Young Scientists Fund of the National Natural Science Foundation of China: “Deep Learning and Event Driven based Video Mashup”, Lead PI.