华中科技大学 HUST
人工智能与自动化学院 AIA
图像信息智能处理全国重点实验室
图像与视觉学习研究组 HAIV Lab
个人项目：人体动作
图治视万象，
探本从心学。
HAIV研究组期望的研究风格是深刻分析和清晰定义问题、深入细节且有效解决问题。问题可小可大，甚至偏好小一点的问题，但一定要化抽象为具体，能形式化成数学或符号语言为最好。虽然我们会打开脑洞、大胆尝试不同方法，但不为提方法而提方法，以能有力解决问题的适合的方法为准。我们比较偏好简洁的方法，追求的创新点希望是一个点，可以是复杂方法里一个点里的创新，也可以是完整的一个简洁的方法。
Recently, we have paper published at top-tier conferences such as CVPR, ICCV, ECCV, MICCAI, etc.
图像、视觉、学习相关论文
Vision & Learning
医疗、健康相关论文
Health informatics
2024年
Q Zhou, Z Zhang, Xiang Xiang*, K Wang, Y Wu, Y Li. Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning. In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024. 学院第一篇NAACL
Y Tan, Q Zhou, Xiang Xiang*, K Wang, Y Wu, Y Li. Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
J Ma, Xiang Xiang*, K Wang, Y Wu, Y Li. Aligning Logits Generatively for Principled Black-Box Knowledge Distillation. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
Y Deng, Xiang Xiang: Expanding Hyperspherical Space for Few-Shot Class-Incremental Learning. In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024.
Y Tan, Xiang Xiang: Cross-Domain Few-Shot Incremental Learning for Point-Cloud Recognition. In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024.
Xiang Xiang①, Z Zhang①, X Chen: Curriculum-Balanced Long-Tailed Learning. Neurocomputing, 2024. 新理论新方法
2023年
Z Zhang①, Xiang Xiang①: Decoupling MaxLogit for Out-of-Distribution Detection. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. 新视角新方法
S Wang, Q Wan, Xiang Xiang, Z Zeng: Saliency Regularization for Self-Training with Partial Annotations. In IEEE/CVF International Conference on Computer Vision (ICCV), 2023. 显著提升鲁棒性
Y. Deng, Xiang Xiang: Replaying Styles for Continual Semantic Segmentation across Domains. The 7th Asian Conference on Pattern Recognition (ACPR), 2023. 跨域增量学习
Q Zhou, Xiang Xiang, J Ma: Hierarchical Task-Incremental Learning with Feature-Space Initialization Inspired by Neural Collapse. Neural Processing Letters, 2023. 新问题新方法
Q Wan, S Wang, Xiang Xiang: A Simple Unknown-Instance-Aware Framework for Open-Set Object Detection. In International Conference on Information Science and Technology, 2023. 简单新方法
2022年
Xiang Xiang, Y. Tan, Q. Wan, J. Ma, A. L. Yuille, G. D. Hager: Coarse-To-Fine Incremental Few-Shot Learning. In European Conference on Computer Vision (ECCV), 2022. [PDF] 新问题与理论
Y Deng, Y Li, Y Zhang, Xiang Xiang, J Wang, J Chen, J Ma: Hierarchical Memory Learning for Fine-Grained Scene Graph Generation. Accepted to European Conference on Computer Vision (ECCV), 2022. [PDF] 新方法和分析
Xiang Xiang, F. Wang, Y. Tan, A. L. Yuille: Imbalanced Regression for Intensity Series of Pain Expression from Videos by Regularizing Spatio-Temporal Face Nets. Pattern Recognition Letters (PRL), Elsevier, 2022. 时空模型正则化
X. Wang, Xiang Xiang, B. Zhang, X. Liu, J. Zheng, Q. Hu: Weakly Supervised Object Detection Based on Active Learning. Neural Processing Letters (NPL), Springer Nature, 2022. 标签不足,主动来凑
J. Ma, Xiang Xiang, Z. Zhang, Y. Tan, Y. Wan, Z. Zeng, D. Tao: Mapping Emulation for Knowledge Distillation. Arxiv pre-print, 2205.10490, 2022. [PDF] 新理论新方法
S. Li, Xiang Xiang: Lightweight Human Pose Estimation Using Heatmap-Weighting Loss. In ICPR 2022 workshops, 2022. [PDF] 最佳论文提名奖！Best Paper Award (Honorable Mention)
Z. Zhang, Xiang Xiang: Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation. Arxiv pre-print, 2022.[PDF] 新loss
Xiang Xiang: Bootstrapping Autonomous Lane Changes with Self-Supervised Augmented Runs. In ECCV 2022 workshops. [PDF] 运动规划学习中的数据增强
J Ma: Source-blind Model Transfer Learning based on Domain Adaptation and Knowledge Distillation. Huazhong University of Science and Technology Bachelor's Graduation Project Thesis, advised by Xiang Xiang, Wuhan, China, May 2022.
S. Li: 3D Human Pose Estimation Using Loss Weighted by Heapmap. Huazhong University of Science and Technology Bachelor's Graduation Project Thesis, advised by Xiang Xiang, Wuhan, China, May 2022.
Z. Peng: Learning-based Dental Keypoint Detection. Huazhong University of Science and Technology Bachelor's Graduation Project Thesis, advised by Xiang Xiang, Wuhan, China, May 2022.
S. Zhou: Hierarchical Class-Incremental Learning based on Tree-like Deep Networks. Huazhong University of Science and Technology Bachelor's Graduation Project Thesis, advised by Xiang Xiang, Wuhan, China, May 2022.
2021年
X. Wei, R. Qiu, H. Yu, Y. Yang, H. Tian, Xiang Xiang: Entropy-based Optimization via A* Algorithm for Parking Space Recommendation. SPIE International Conference on Traffic Engineering and Transportation System, 2021. [PDF][SPIE] 路径优化
Y. Tan: Estimating Pain Intensity based on Dynamics in Face Videos. Huazhong University of Science and Technology Bachelor's Graduation Project Thesis, advised by Xiang Xiang, Wuhan, China, May 2021. [PDF][PPT] 视频vs图片
J. Li: A Survey on Interpretability of Deep Learning Networks. Huazhong University of Science and Technology Bachelor's Graduation Project Thesis, advised by Xiang Xiang, Wuhan, China, May 2021. [PDF] 可解释性
Xiang Xiang: Large-Scale Piecewise Affine Warping for Training Document Rectifier. pre-print, 2021. [PDF] 如今扫描仪较之CamScanner的优势也仅剩扫描褶皱弯曲纸张了
2020年
Xiang Xiang*, Z. Wang, S. Lao, B. Zhang*: Pruning Multi-view Stereo Net for Efficient 3D Reconstruction. ISPRS Journal of Photogrammetry and Remote Sensing, vol. 168, pp. 17-27, Elsevier, Oct. 2020 (*correspondence). [official][arxiv] 快速三维重建
J. Huang, Z. Huang, Xiang Xiang, X. Gong, B. Zhang: Long-Short Graph Memory Network for Skeleton-based Action Recognition. In IEEE Winter Conference on Applications of Computer Vision 2020 (WACV 2020), Aspen, USA. [pdf][github][slides] GCN与LSTM结合
2018年
Xiang Xiang: Image-set, Temporal and Spatiotemporal Representations of Videos for Recognizing, Localizing and Quantifying Actions. Johns Hopkins University Ph.D. Dissertation, advised by Gregory D. Hager and Trac D. Tran, June 2018, Baltimore, USA. [pdf][talk-a][talk-b][official page at JHU Sheridan libraries][official announcement at JHU CS Dept][semanticscholar] 表征视频
Xiang Xiang and Trac D. Tran: Linear Disentangled Representation Learning for Facial Actions. IEEE Transactions on Circuits and System for Video Technology (IEEE T-CSVT), Volume: 28, Issue: 12, 2018. [ieee][arxiv][github][Modeling Work (new perspective): video-based sparsity + PCP] 人脸的近似线性解耦
Xiang Xiang*, Ye Tian*, Austin Reiter, Gregory D. Hager, Trac D. Tran: S3D: Stacking Segmental P3D for Action Quality Assessment. Full paper IEEE International Conference on Image Processing (ICIP) 2018, Athens, Greece. (* Equal contribution.) [ieee][sigport][researchgate][github][linkedin][grant proposal][followup works at cvpr19] 语义分段的三维CNN
2017年
Feng Wang, Xiang Xiang, Jian Cheng, Alan L. Yuille. NormFace: L2 Hypersphere Embedding for Face Verification. Full long paper at ACM MultiMedia (MM) Conference 2017, Mountain View, USA. [arxiv][github][researchgate][comment][linkedin][csdn in Chinese] 深度特征和权重归一化的作用
Hao Zhu, Feng Wang, Xiang Xiang and Trac D. Tran. Supervised Hashing with Jointly Learning Embedding and Quantization. Full paper at IEEE International Conference on Image Processing (ICIP) 2017, Beijing, China. [ieee][researchgate][linkedin][Modeling work (new objective): relaxed optimization for image retrieval] 哈希编码与量化一起学
Xiang Xiang, Dung N. Tran, Trac D. Tran. Sparse Unsupervised Clustering with Mixture Observations for Video Summarization. Abstract paper at IEEE Applied Imagery Pattern Recognition Workshop (AIPR) 2017, Washington DC, USA. 无监督视频摘要
2016年
Xiang Xiang and Trac D. Tran: Recursively Measured Action Units. Workshop paper at IAPR International Conference on Pattern Recognition (ICPR) 2016 workshops, Cancun, Mexico. LNAI, vol. 10183 (Pattern Recognition of Social Signals), 978-3-319-59258-9. [researchgate][books.google][springer][Algorithmic work (new algorithm): video-based LSTM + SMP] 人脸表情LSTM
2015年
Xiang Xiang, Minh Dao, Gregory D. Hager, Trac D. Tran: Hierarchical Sparse and Collaborative Low-Rank Representation for Emotion Recognition. Full paper at IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2015, Brisbane, Australia. ISBN: 978-1-4673-6997-8. [ieee][arxiv][github] [mathworks] [youtube] [elsevier][Modeling work (2 new objectives): video-based sparsity + PCP] 压缩感知人脸表情
2012年
Xiang Xiang, Hong Chang, Jiebo Luo: Online Web-Data-Driven Segmentation of Selected Moving Objects in Videos. Full paper at Asian Conference on Computer Vision (ACCV) 2012: 134-146, Daejeon, Korean. LNCS, vol. 7725 (ACCV), 2013, ISBN: 978-3-642-37443-2. [demo: over 10 seconds!!!][springer][acm][pdf][researchgate][github][youtube] [dataset][google][cvpapers][visionbib][slides][Modeling work (new objective for segmentation + new algorithm for tracking): video-based MIL tracking + Graph cuts] 视频抠物
2011年
Xiang Xiang: An Attempt to Segment Foreground in Dynamic Scenes. Full paper at International Symposium on Visual Computing (ISVC) 2011: 124-134, Lake Tahoe, USA. LNCS, vol. 6938 (Advances in Visual Computing), 2011, ISBN: 978-3-642-24027-0. [springer][acm][researchgate][google][Empirical work: video-based graph cuts] 前景分割
2008年
Xiang Xiang, Wenhui Chen, Du Zeng: Intelligent Target Tracking and Shooting System with Mean Shift. Full paper at IEEE International Symposium on Parallel and Distributed Processing and Applications (ISPA) 2008: 417-421, Sydney, Australia. Parallel and Distributed Processing, IEEE, 2008, ISBN: 978-0-7695-3471-8. [ieee][pdf][github][youtube][whu][sjtu] 跟踪摄像
2023年
Y Tan, Xiang Xiang, Y Chen, H Jing, S Ye, C Xue, H Xu: Coupling Bracket Segmentation and Tooth Surface Reconstruction on 3D Dental Models. In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2023. 新问题新方法 获奖论文 MICCAI STAR Award
Y. Tan, Xiang Xiang: Boundary-Constrained Graph Network for Tooth Segmentation on 3D Dental Surfaces. In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Workshop on Machine Learning for Medical Imaging (MLMI), 2023.
B. Li, Xiang Xiang, G. Huang, P. Wang, X. Han, D. Bai, H. Xu: A Coupled-Lines System to Determine the Anteroposterior Position of Maxillary Central Incisor for Smiling Profile Esthetics. The Angle Orthodontist, 2023. 几何建模
周郁葱， 谭煜雯， 项翔， 薛超然， 徐晖．深度学习算法辅助数字化牙模三维牙齿分割的研究进展．口腔疾病防治 31 (9), 673-678, 2023.
2022年
Xiang Xiang, Z. Zhang, X. Peng, J. Shao: Learning-based Detection of MYCN Amplification in Clinical Neuroblastoma Patients: A Pilot Study. In International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI) workshop on Multiscale Multimodal Medical Imaging, 2022. [PDF]新问题
Y. Tian, G. Huang, Xiang Xiang, N. Wang, W. Dai, J. Chen, D. Bai, H. Xu: The Lower Bow-Shaped Curve as a Novel Reference Frame to Determine the Lateral Limit of the Maxillary Anterior Arch for Smile Esthetics. American Journal of Orthodontics & Dentofacial Orthopedics, 2022. 几何建模
Y. Wang, P. Wang, Xiang Xiang, H. Xu, Y. Tang, Y. Zhou, D. Bai, C. Xue: Effect of Occlusal Coverage Depths on the Precision of 3D-Printed Orthognathic Surgical Splints. BMC Oral Health, 2022. 几何建模
2021年
项翔, 胡琦, 张子函:通过基于行为观测的辅助诊疗实现数字化健康干预与管理. “智能传播与健康治理”国际学术研讨会，2021.
Z. Zhang: Recognition Algorithm Design for Medical Images based on Deep Learning Models. Huazhong University of Science and Technology Bachelor's Graduation Project Thesis, advised by Xiang Xiang, Wuhan, China, May 2021. [PDF][PPT] 检验不够，影像来凑
2019年
Xiang Xiang: Beyond Deep Feature Averaging: Sampling Videos Towards Practical Facial Pain Recognition. Full paper at IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019 workshop on Face and Gesture Analysis for Health Informatics, Long Beach, USA. [PDF][thecvf][upmc.fr] 基于特征度量学习的视频采样
2018年
Xiang Xiang: Effect of Spatial Alignment in Cataract Surgical Phase Recognition. Abstract paper at IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 workshop on Fine-Grained Instructional Video Understanding, Salt Lake City, USA. [pdf][umich][poster] 视频打分
Wentao Zhu, Xiang Xiang, Trac D. Tran, Gregory D. Hager and Xiaohui Xie: Adversarial Deep Structural Networks for Mammographic Mass Segmentation. Full paper at IEEE International Symposium on Biomedical Imaging (ISBI) 2018, Washington DC, USA. [arxiv] [github][linkedin] 基于对抗训练的数据增强
Xiang Xiang, Wentao Zhu, Trac D. Tran, Gregory D. Hager: Survey on Multi-Scale CNNs for Lung Nodule Detection. Abstract paper at IEEE International Symposium on Biomedical Imaging (ISBI) 2018, Washington DC, USA. 多尺度CNN
Xiang Xiang*, Ye Tian*, Gregory D. Hager, Trac D. Tran: Assessing Pain Levels from Videos Using Temporal Convolutional Networks. Abstract paper at IEEE Winter Conf. on Applications of Computer Vision (WACV) 2018 workshop on Computer Vision for Active and Assisted Living , Lake Tahoe, USA. (* Equal contribution.) [youtube] 时序卷积
2017年
Feng Wang, Xiang Xiang*, Chang Liu, Trac D. Tran, Austin Reiter, Gregory D. Hager, Jian Cheng and Alan L. Yuille. Regularizing Face Verification Nets for Pain Intensity Regression. Full paper at IEEE International Conference on Image Processing (ICIP) 2017, Beijing, China. (*corresponding author. Oral presentation.) [ieee][researchgate][arxiv] [github][slides][linkedin][Modeling work (new objective): fine-tuning a face net with a regression loss regularized by a classification loss to induce discrete values] 正则化预训练模型
2016年
Xiang Xiang and Trac D. Tran: Pose-Selective Max Pooling for Measuring Similarity. Workshop paper at IAPR International Conference on Pattern Recognition (ICPR) 2016 workshops, Cancun, Mexico. LNCS, vol. 10165 (Video Analytics), ISBN: 978-3-319-56686-3. [springer][github][researchgate][arxiv][aau][linkedin][google][Algorithmic work (2 new algorithms): video-based keyframe + deepface] 针对人脸的池化
2014年
Xiang Xiang, Daniel Mirota, Austin Reiter, Gregory D. Hager: Is Multi-Model Feature Matching Better for Endoscopic Motion Estimation? Workshop paper at International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2014 workshops, Boston, USA. LNCS, vol. 8899 (Comp.-Ass. & Rob. End.), 2014, ISBN: 978-3-319-13409-3. [springer][nih][researchgate][code][google][Empirical work: video-based 3D vision] 不确定性分析
2011年
Xiang Xiang: A Localization Framework under Non-rigid Deformation for Rob. Surg.. Full paper at International Symposium on Visual Computing (ISVC) 2011: 11-22, Lake Tahoe, USA. LNCS, vol. 6938 (Advances in Visual Computing), 2011, ISBN: 978-3-642-24027-0. [springer][acm][linkedin][researchgate][google][visionbib][Modeling work (new formulation): geometry based registration] 形变估计