Papers

• Xingjian Zhang, Siwei Wen, Wenjun Wu, Lei Huang*. TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning. preprint arXiv:2504.09641. [Paper]

• Xingjian Zhang, Xi Weng, Yihao Yue, Zhaoxin Fan, Wenjun Wu, Lei Huang*. TinyLLaVA-Video: A Simple Framework of Small-scale Large Multimodal Models for Video Understanding. preprint arXiv:2501.15513. [Paper]

• Junlong Jia, Ying Hu, Xi Weng, Yiming Shi, Miao Li, Xingjian Zhang, Baichuan Zhou, Ziyu Liu, Jie Luo, Lei Huang*, Ji Wu. TinyLLaVA Factory: A Modularized Codebase for Small-scale Large Multimodal Models. preprint arXiv:2405.11788. [Paper]

• Baichuan Zhou, Ying Hu, Xi Weng, Junlong Jia, Jie Luo, Xien Liu, Ji Wu, Lei Huang*. TinyLLaVA: A Framework of Small-scale Large Multimodal Models. preprint arXiv:2402.14289. [Paper]

• Bin Wen, Jie Luo, Xianglong Liu, Lei Huang. Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction. preprint arXiv:2002.00176. [Paper]

• Wei Li, Zehuan Yuan, Dashan Guo, Lei Huang, Xianghong Fang, Changhu Wang. Deformable Tube Network for Action Detection in Videos. preprint arXiv:1907.01847. [Paper]

• Lei Huang, Xianglong Liu, Bo Lang, Bo Li. Projection Based Weight Normalization for Deep Neural Networks. preprint arXiv:1710.02338. [Paper] [Code] [bibtex]

• Adams Wei Yu, Lei Huang, Qihang Lin, Ruslan Salakhutdinov, Jaime Carbonell. Block-normalized Gradient Method: an Empirical Study for Training Deep Nerual Network. preprint arXiv:1707.04822. [Paper]

• Xi Weng, Jianing An, Xudong Ma, Binhang Qi, Jie Luo, Xi Yang, Jin Song Dong, Lei Huang*. Clustering Properties of Self-Supervised Learning. ICML. 2025 [Paper] [Code]

• Tong Bai, Haoran Zhao, Lei Huang, Zhipeng Wang, Dong In Kim, Arumugam Nallanathan. A Decade of Video Analytics at Edge: Training, Deployment, Orchestration, and Platforms. IEEE Communications Surveys & Tutorials. 2025 [Paper]

• Jiejie Zhao, Tongyu Zhu, Leilei Sun, Bowen Du, Haiquan Wang, Lei Huang. Dual-mask: Progressively sparse multi-task architecture learning. Pattern Recognition. 2025 [Paper]

• Lei Huang, Yunhao Ni, Xi Weng, Rao Muhammad Anwer, Salman Khan, Ming-Hsuan Yang, Fahad Shahbaz Khan. Understanding Whitening Loss in Self-supervised Learning. IEEE TPAMI. 2024 [Paper]

• Jiawei Zhang, Jiahe Li, Xiaohan Yu, Lei Huang, Lin Gu, Jin Zheng, Xiao Bai. CoR-GS: sparse-view 3D Gaussian splatting via co-regularization. ECCV. 2024 [Paper]

• Jiawei Zhang, Lei Huang, Xiao Bai, Jin Zheng, Lin Gu, Edwin Hancock. Exploring the Usage of Pre-trained Features for Stereo Matching. IJCV. 2024 [Paper]

• Yunhao Ni, Yuxin Guo, Junlong Jia, Lei Huang*. On the Nonlinearity of Layer Normalization. ICML 2024 [Paper]

• Jiawei Zhang, Jiahe Li, Lei Huang, Xiaohan Yu, Lin Gu, Jin Zheng, Xiao Bai. Robust Synthetic-to-Real Transfer for Stereo Matching. CVPR 2024. [Paper] [code]

• Huan Xiong, Lei Huang, Wenston J.T. Zang, Xiantong Zhen, Guo-Sen Xie, Bin Gu, and Le Song. On the Number of Linear Regions of Convolutional Neural Networks with Piecewise Linear Activations. IEEE TPAMI. 2024

• Xi Weng#, Yunhao Ni#, Tengwei Song, Jie Luo, Rao Muhammad Anwer, Salman Khan, Fahad Shahbaz Khan, Lei Huang*. Modulate Your Spectrum in Self-Supervised Learning. ICLR. 2024 [Paper] [code]

• Lei Huang, Jie Qin, Yi Zhou, Fan Zhu, Li Liu, Ling Shao. Normalization Techniques in Training DNNs: Methodology, Analysis and Application. IEEE TPAMI (ESI Highly Cited Paper). 2023 [Paper]

• Aishan Liu, Shiyu Tang, Xinyun Chen, Lei Huang, Haotong Qin, Xianglong Liu, Dacheng Tao. Towards Defending Multiple Lp-norm Bounded Adversarial Perturbations via Gated Batch Normalization. IJCV 2023. [Paper]

• Yi Zhou, Lei Huang, Tao Zhou, Hanshi Sun. Combating medical noisy labels by disentangled distribution learning and consistency regularization. Future Generation Computer Systems. 2023

• Xi Weng#, Lei Huang*#, Lei Zhao#, Rao Muhammad Anwer, Salman Khan, Fahad Shahbaz Khan. An Investigation into Whitening Loss for Self-supervised Learning. Neurips 2022 (Spotlight). [Paper] [code]

• Jiaxi Wang, Ji Wu, Lei Huang. Understanding the Failure of Batch Normalization for Transformers in NLP. Neurips 2022 (Spotlight). [Paper] [code]

• Tian Wang, Boyao Hou, Zexian Li, Zhe Li, Lei Huang, Baochang Zhang, Hichem Snoussi. A Malleable Boundary Network for temporal action detection. Computers and Electrical Engineering. 2022

• Lei Huang, Yi Zhou, Tian Wang, Jie Luo, Xianglong Liu. Delving into the Estimation Shift of Batch Normalization in a Network. CVPR 2022. [Paper] [code]

• Jiawei Zhang, Xiang Wang, Xiao Bai, Chen Wang, Lei Huang, Yimin Chen, Lin Gu, Jun Zhou, Tatsuya Harada, Hancock Edwin. Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective. CVPR 2022. [Paper] [code]

• Ge Kan, Jinhu Lu, Tian Wang, Baochang Zhang, AichunZhu, Lei Huang, Guodong Guo, Hichem Snoussi. Bi-level Doubly Variational Learning for Energy-based Latent Variable Models. CVPR 2022. [Paper]

• Tengwei Song, Jie Luo, Lei Huang. Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding. NeurIPS 2021. [Paper] [code]

• Yi Zhou, Lei Huang, Tao Zhou, Ling Shao. CCT-Net: Category-Invariant Cross-Domain Transfer for Medical Single-to-Multiple Disease Diagnosis. ICCV 2021.

• Yi Zhou, Lei Huang, Tao Zhou, Huazhu Fu, Ling Shao. Visual-Textual Attentive Semantic Consistency for Medical Report Generation. ICCV 2021.

• Lei Huang, Yi Zhou, Li Liu, Fan Zhu, Ling Shao. Group Whitening: Balancing Learning Efficiency and Representational Capacity. CVPR 2021. [Paper] [code]

• Zhiqiang Shen, Zechun Liu, Jie Qin, Lei Huang, Kwang-Ting Cheng, Marios Savvides. S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration. CVPR 2021. [Paper] [code]

• Liang Hou, Zehuan Yuan, Lei Huang, Huawei Shen, Xueqi Cheng, Changhu Wang. Slimmable Generative Adversarial Networks. AAAI 2021. [Paper] [code]

• Yi Zhou, Lei Huang, Tianfei Zhou, Ling Shao. Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification. AAAI 2021.

• Yi Zhou, Boyang Wang, Lei Huang, Shanshan Cui, Ling Shao. A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability. IEEE Transactions on Medical Imaging 2020.

• Jiaxin Chen, Jie Qin, Yichao Yan, Lei Huang, Li Liu, Fan Zhu, Ling Shao. Deep Local Binary Coding for Person Re-Identification by Delving into the Details. ACM Multimedia 2020.

• Lei Huang, Jie Qin, Li Liu, Fan Zhu, Ling Shao. Layer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs. ECCV 2020 (Oral). arXiv:2002.10801 [Paper] [Code]

• Yuming Shen, Jie Qin, Lei Huang, Li Liu, Fan Zhu, Ling Shao. Invertible Zero-Shot Recognition Flows. ECCV 2020

• Huan Xiong, Lei Huang, Mengyang Yu, Li Liu, Fan Zhu, Ling Shao. On the Number of Linear Regions of Convolutional Neural Networks. ICML 2020. [Paper] [Code]

• Lei Huang, Li Liu, Fan Zhu, Diwen Wan, Zehuan Yuan, Bo Li, Ling Shao. Controllable Orthogonalization in Training DNNs. CVPR 2020 (Oral, Best Paper Nomination ). [Paper] [Code]

• Lei Huang, Lei Zhao, Yi Zhou, Fan Zhu, Li Liu, Ling Shao. An Investigation into the Stochasticity of Batch Whitening. CVPR 2020 (Oral). [Paper] [Code]

• Lei Zhao, Xiaohui Wang, Lei Huang. An Efficient Agreement Mechanism in CapsNets By Pairwise Product. ECAI 2020. [Paper] [Code]

• Lei Huang, Xianglong Liu, Jie Qin, Fan Zhu, Li Liu, Ling Shao. Projection Based Weight Normalization: Efficient Method for Optimization on Oblique Manifold in DNNs. Pattern Recognition, 2020.

• Diwen Wan, Fumin Shen, Li Liu, Fan Zhu, Lei Huang, Mengyang Yu, Heng Tao Shen, Ling Shao. Deep Quantization Generative Networks. Pattern Recognition, 2020.

• Lei Zhao, Lei Huang. Exploring Dynamic Routing As A Pooling Layer. IEEE International Conference on Computer Vision Workshops, 2019. [Paper]

• Lei Huang, Yi Zhou, Fan Zhu, Li Liu, Ling Shao. Iterative Normalization: Beyond Standardization towards Efficient Whitening. CVPR 2019. [Paper] [Code] [bibtex]

• Yi Zhou, Xiaodong He, Lei Huang, Li Liu, Fan Zhu, Shanshan cui, Ling Shao. Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images. CVPR 2019. [Paper]

• Lei Huang, Yuqing Ma, Xianglong Liu. A general non-parametric active learning framework for classification on multiple manifolds. Pattern Recognition Letters, 2019.

• Lei Huang, Dawei Yang, Bo Lang, Jia Deng . Decorrelated Batch Normalization. CVPR 2018. [Paper] [SupplementaryMaterial] [Code] [bibtex]

• Lei Huang, Xianglong Liu, Bo Lang, Admas Wei Yu, Bo Li. Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks. AAAI 2018 (Oral). [Paper] [Code] [bibtex]

• Lei Huang, Xianglong Liu, Yang Liu, Bo Lang, Dacheng Tao. Centered Weight Normalization in Accelerating Training of Deep Neural Networks. ICCV 2017. [Paper] [SupplementaryMaterial] [Code] [bibtex]

• Bo Wu, Yang Liu, Bo Lang, Lei Huang. DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model. Neurocomputing, 2018 (arXiv:1712.03563).

• Zepeng Gu, Bo Lang, Tongyu Yue, Lei Huang. Learning Joint Multimodal Representation Based on Multi-fusion Deep Neural Networks. The 24th International Conference on Neural Information Processing (ICONIP 2017), Oral.

• Xianglong Liu, Lei Huang, Cheng Deng, Bo Lang, Dacheng Tao. Query-adaptive hash code ranking for large-scale multi-view visual search. IEEE Transactions on Image Processing (TIP), 2016.

• Yang Liu, Lei Huang, Xianglong Liu, Bo Lang. A Novel Rotation Adaptive Object Detection Method Based on Pair Hough Model. Neurocomputing, 2016.

• Yang Liu, Lei Huang, Siqi Wang, Xianglong Liu, Bo Lang. Efficient Segmentation for Region-based Image Retrieval Using Edge Integrated Minimum Spanning Tree. ICPR 2016.

• Xianglong Liu, Lei Huang, Cheng Deng, Jiwen Lu, Bo Lang. Multi-View Complementary Hash Tables for Nearest Neighbor Search. ICCV 2015. [Paper] [Poster] [Spotlight] [bibtex]

• Lei Huang, Yang Liu, Xianglong Liu, Xindong Wang, Bo Lang. Graph-based Active Semi-supervised Learning: a New Perspective for Relieving Multi-class Annotation Labor. ICME 2014. [Paper] [Poster] [Code] [bibtex]

• Lei Huang, Xianglong Liu, Binqiang Ma, Bo Lang. Online Semi-Supervised Annotation via Proxy-based Local Consistency Propagation. Neurocomputing, 2014. [Paper] [bibtex]

• Tianxu Ji, Xianglong Liu, Cheng Deng, Lei Huang, Bo Lang. Query-Adaptive Hash Code Ranking for Fast Nearest Neighbor Search. ACM Multimedia (short paper), 2014. [Paper] [Code] [bibtex]

• Hualei Shen, Dianfu Ma, Yongwang Zhao, Hailong Sun, Sujun Sun, Rongwei Ye, Lei Huang, Bo Lang, Yan Sun. MIAPS: a web-based system for remotely accessing and presenting medical images. Computer Methods and Programs in Biomedicine, 2014.

• Mengyun Wang, Xianglong Liu, Lei Huang, Bo Lang, Hailiang Yu. Ontology-based Concept Similarity Integrating Image Semantic and Visual Information. The 4th International Workshop on Advances in Semantic Information Retrieval, 2014.

• Lei Huang, Yang Wang, Xianglong Liu, Bo Lang. Efficient Semi-supervised Annotation with Proxy-based Local Consistency Propagation. ICME 2013. [Paper] [Poster] [bibtex]

• Lei Huang, Yang Liu. BUAA AUDR at ImageCLEF 2012 Photo Annotation Task. CLEF Online Working Notes, 2012.

• Xianglong Liu, Bo Lang, Wei Yu, Junwu Luo, Lei Huang. AUDR: An Advanced Unstructured Data Repository. The 6th International Conference on Pervasive Computing and Applications (ICPCA6) South Africa, 2011.