About Me

I am a JSPS Fellowship Researcher (日本学術振興会外国人特別研究員) from the National Institute of Informatics, Japan, working with Prof. Shin’ichi Satoh. I received my doctoral degree from Xiamen University. My research interests are in machine learning and computer vision, especially in ML safety/reliability, deep learning theory, multimodal ML, AI Ethics, and large-scale image retrieval.

News

We are organizing an IJCV Special Issue: Open-World Visual Recognition. [Website]

We are organizing an Electronics Special Issue: Adversarial Machine Learning: Attacks, Defenses, and Security. [Website]

Publications

Journal:

• Huafeng Kuang, Hong Liu, Yongjian Wu, and Rongrong Ji. Semantically Consistent Visual Representation for Adversarial Robustness. IEEE Trans. on Information Forensics and Security, 2023.
• Zhengwei Yang, Xian Zhong, Zhun Zhong, Hong Liu, Zheng Wang, and Shin’ichi Satoh. Win-Win by Competition: Auxiliary-Free Cloth-Changing Person Re-Identification. IEEE Trans. on Image Processing, 2023. [CODES]
• Hong Liu, Zhun Zhong, Nicu Sebe, and Shin’ichi Satoh. Mitigating Robust Overfitting via Self-Residual-Calibration Regularization. Artificial Intelligence, 2023. [CODES]
• Yixu Wang, Jie Li, Hong Liu, Yan Wang, Mingliang Xu, Yongjian Wu, and Rongrong Ji. Model Stealing Attack based on Sampling and Weighting. SCIENCE CHINA Information Sciences, 2022. (In Chinese)
• Fengxiang Yang, Juanjuan Weng, Zhun Zhong, Hong Liu, Zheng Wang, Zhiming Luo, Donglin Cao, Shaozi Li, Shin’ichi Satoh, and Nicu Sebe. Towards Robust Person Re-identification by Defending Against Universal Attackers. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022. [CODES]
• Deng-Ping Fan, Ziling Huang, Peng Zheng, Hong Liu#, Xuebin Qin, and Luc Van Gool. Deep Facial Synthesis: A New Challenge. Machine Intelligence Research, 2022. [CODES][DATA][ToolBox][Awesome-List][Chinese Version][Video in Chinese][SLIDES(code:eoa3)]
• Liujuan Cao, Huafeng Kuang, Hong Liu, Yan Wang, Baochang Zhang, Feiyue Huang, Yongjian Wu, and Rongrong Ji. Towards Robust Adversarial Training via Geometry Constraint and Dual label Supervised. Journal of Software, 2021. [Chinese Version][English Version] [CODES]
• Mingbao Lin, Rongrong Ji, Hong Liu, Xiaoshuai Sun, Shen Chen, and Qi Tian. Hadamard Matrix Guided Online Hashing. International Journal of Computer Vision, 2020. [CODES]
• Hong Liu, Rongrong Ji, Jingdong Wang, and Chunhua Shen. Ordinal Constraint Binary Coding for Approximate Nearest Neighbor Search. IEEE Trans. on Pattern Analysis and Machine Intelligence. Volume: 41, Issue: 4, 2019.
• Rongrong Ji; Hong Liu#; Liujuan Cao; Di Liu; Yongjian Wu, and Feiyue Huang. Towards Optimal Manifold Hashing via Discrete Locally Linear Embedding, IEEE Trans. on Image Processing, Volume 26, Issue 11, 2017. [CODES]
• Hong Liu, Aiwen Jiang, Mingwen Wang, and Jianyi Wan.Local Similarity Preserved Hashing Learning via Markov Graph for Efficient Similarity Search. Neurocomputing, 159, 2015.

Conference:

• Huafeng Kuang, Hong Liu, Yongjian Wu, Shin’ichi Satoh, Rongrong Ji. Improving Adversarial Robustness via Information Bottleneck Distillation. NeurIPS, 2023.
• Zhenglin Zhou#, Huaxia Li#, Hong Liu#, Nanyang Wang, Gang Yu, and Rongrong Ji. STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection. CVPR, 2023. [CODES] (# contribute equally)
• Ke Sun, Hong Liu, Taiping Yao, Xiaoshuai Sun, Shen Chen, Shouhong Ding, and Rongrong Ji. An Information Theoretic Approach for Attention-Driven Face Forgery Detection. ECCV, 2022. [CODES]
• Yixu Wang, Jie Li, Hong Liu, Yan Wang, Yongjian Wu, Feiyue Huang, and Rongrong Ji. Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack. ECCV, 2022. [CODES]
• Zhengwei Yang, Xian Zhong, Hong Liu, Zhun Zhong, and Zheng Wang. Attentive Decoupling Network for Cloth-Changing Re-identification. ICME, 2022.
• Nobukatsu Kajiura, Hong Liu, and Shin’ichi Satoh. Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels. ACM MM Asia, 2021. [CODES]
• Xinshuai dong, Anh Tuan Luu, Rongrong Ji, and Hong Liu. Towards Robustness Against Natural Language Word Substitutions. ICLR 2021. (Spotlight) [CODES]
• Ke Sun, Hong Liu, Qixiang Ye, Yue Gao, Jianzhuang Liu, Ling Shao, and Rongrong Ji. Domain General Face Forgery Detection by Learning to Weight. AAAI 2021. [CODES]
• Fengxiang Yang, Zhun Zhong Hong Liu, Zheng Wang, Zhiming Luo, Shaozi Li, Nicu Sebe, and Shin’ichi Satoh, Learning to Attack Real-World Models for Person Re-identification via Virtual-Guided Meta-Learning. AAAI 2021.[CODES]
• Xinshuai Dong, Hong Liu, Liujuan Cao, Rongrong Ji, Qixiang Ye, Jianzhuang Liu, and Qi Tian. API-Net: Robust Generative Classifier via a Single Discriminator. ECCV 2020.[CODES]
• Hanlin Chen, Baochang Zhang, Song Xue, Xuan Gong, Hong Liu, Rongrong Ji, and David Doermann. Anti-Bandit Neural Architecture Search for Model Defense. ECCV 2020.[CODES]
• Jie Li, Rongrong Ji, Hong Liu, Jianzhuang Liu, Bineng Zhong, Cheng Deng, and Qi Tian. Projection & Probability-Driven Black-Box Attack. CVPR, 2020.[CODES]
• Hong Liu, Rongrong Ji, Jie Li, Baochang Zhang, Yue Gao, Yongjian Wu, and Feiyue Huang. Universal Adversarial Perturbation via Prior Driven Uncertainty Approximation. ICCV, 2019. (Oral). [CODES]
• Jie Li, Rongrong Ji, Hong Liu, Xiaopeng Hong, Yue Gao, and Qi Tian. Universal Perturbation Attack Against Image Retrieval. V1 and V2. ICCV, 2019. [CODES]
• Huafeng Kuang, Rongrong Ji, Hong Liu, Shengchuan Zhang, Xiaoshuai Sun, Feiyue Huang, and Baochang Zhang. Multi-modal Multi-layer Fusion Network with Average Binary Center Loss for Face Anti-spoofing. ACM MM, 2019. [CODES]
• Jie Hu, Rongrong Ji, Hong Liu, Shengchuan Zhang, Cheng Deng, and Qi Tian. Towards Visual Feature Translation. CVPR, 2019. [CODES]
• Hong Liu, Jie Li, Rongrong Ji, and Yongjian Wu. Learning Neural Bag-of-Matrix-Summarization with Riemannian Network. AAAI, 2019. [CODES]
• Mingbao Lin, Rongrong Ji, Hong Liu, Xiaoshuai Sun, Yongjian Wu, and Yunsheng Wu. Towards Optimal Discrete Online Hashing with Balanced Similarity. AAAI, 2019. [CODES]
• Hong Liu, Mingbao Lin, Shengchuan Zhang, Yongjian Wu, Feiyue Huang, and Rongrong Ji. Dense Auto-Encoder Hashing for Robust Cross-Modality Retrieval. ACM MM, 2018. [CODES]
• Mingbao Lin, Rongrong Ji, Hong Liu, and Yongjian Wu. Supervised Online Hashing via Hadamard Codebook Learning. ACM MM, 2018. (Oral). [CODES]
• Jianqiang Qian, Xianmin Lin, Hong Liu, Youming Deng, and Rongrong Ji. Towards Compact Visual Descriptor via Deep Fisher Network with Binary Embedding. ICME, 2018. (Oral)
• Hong Liu, Rongrong Ji, Yongjian Wu, Feiyue Huang, and Baochang Zhang. Cross-Modality Binary Code Learning via Fusion Similarity Hashing. CVPR, 2017. [CODES]
• Hong Liu, Rongrong Ji, Yongjian Wu, and Feiyue Huang. Ordinal Constrained Binary Code Learning for Nearest Neighbor Search. AAAI, 2017. (Oral) [CODES]
• Hong Liu, Rongrong Ji, Yongjian Wu, and Gang Hua. Supervised Matrix Factorization for Cross-Modality Hashing. IJCAI, 2016. [CODES] [STATEMENT]
• Hong Liu, Rongrong Ji, Yongjian Wu, and Wei Liu. Towards Optimal Binary Code Learning via Ordinal Embedding. AAAI, 2016. [CODES]

Pre-print:

• Hong Liu, Shin’ichi Satoh. Rethinking Adversarial Training with A Simple Baseline. In Arxiv, 2023.

• Hong Liu, Yongqing Sun, Shin’ichi Satoh. Rethinking Robust 3D Recognition via Multi-view Test-Time Adaptation. MIRU, 2023.

• Hong Liu. Sparse-Inductive Generative Adversarial Hashing for Nearest Neighbor Search. In Arxiv 2023.

• Zelong Zeng, Fan Yang, Hong Liu, Shin’ichi Satoh. Self-distillation with Online Diffusion on Batch Manifolds Improves Deep Metric Learning. In Arxiv, 2022. [CODES]

• Xiao Liu, Shengchuan Zhang, Hong Liu, Xin Liu, Cheng Deng, and Rongrong Ji. CerfGAN: A Compact, Effective, Robust, and Fast Model for Unsupervised Multi-Domain Image-to-Image Translation. In Arxiv, 2018.

Honors and Awards

• Notable Reviewer, ICLR 2023

• Top-100 Chinese New Stars in Artificial Intelligence by Baidu Scholar, China, 2021

• Japan Society for the Promotion of Science (JSPS) Fellowship, Japan, 2020

• CSIG Outstanding Doctoral Dissertation Award, China Society of Image and Graphics (CSIG), China, 2020

• Fujian Outstanding Doctoral Dissertation Award, Fujian, China, 2020

• Outstanding Ph.D. Graduate Student, Xiamen University, China, 2020

Activities

• Guest Editor of IJCV Special Issue on Open-World Visual Recognition.

• Guest Editor of Electronics Special Issue on Adversarial Machine Learning: Attacks, Defenses and Security

• Guest Editor of Electronics Special Issue on Multimedia Content Analysis, Management and Retrieval: Trends and Challenges.

• Journal Reviewer: IEEE TPAMI, IJCV, IEEE TIP, ACM TOPS, IEEE TMM, IEEE TKDE, IEEE TBD, IEEE TNNLS, IEEE TC, ACM TIST, IEEE TAI, PR, PRL, AIRE, KBS, NEUCOM, TVCJ, PLOS ONE, SIGNAL PROCESS-IMAGE.

• Conference reviewer or PC member: ICLR, ICML, NeurIPS, CVPR, ICCV, ECCV, WACV, IJCAI, AAAI, ICASSP, ACM MM, ACCV, ICMR.

Talks

• “Understanding Adversarial Training via Model Calibration”, Xiamen University, 2023.

• “Evaluation of Person Re-identification Robustness: Attack and Defense”, MLCSA workshop, ACCV 2022.

• “Deep Facial Synthesis: A New Challenge”, Institute of Automation, the Chinese Academy of Science, 2022.

• “Adversarial Robustness in Computer Vision: Attack, Defense, and Beyond”, Symposium: Excellent Doctoral Forum, ICIG 2021.

Contact

E-mail: lynnliu.xmu[AT]gmail.com or hliu[AT]nii.ac.jp

---