From Gradient Analysis to Norm Control: Rethinking Triplet Loss for Gait Recognition.

Zhuguanyu Wu

Guozhen Peng Yunhong Wang 0001 Zhuguanyu Wu Shaoxiong Zhang 0001 Yuwei Zhao Ruiyi Zhan Annan Li From Gradient Analysis to Norm Control: Rethinking Triplet Loss for Gait Recognition. 2026 2076-2089 21 IEEE Trans. Inf. Forensics Secur. https://doi.org/10.1109/TIFS.2026.3658989 db/journals/tifs/tifs21.html#PengWWZZZL26 streams/journals/tifs

Zhuguanyu Wu Ruihao Gong Yang Yong Yushi Huang Xiangyu Fan Lei Yang 0059 Dahua Lin Xianglong Liu 0001 SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation. 2026 May abs/2605.30116 CoRR https://doi.org/10.48550/arXiv.2605.30116 db/journals/corr/corr2605.html#abs-2605-30116 streams/journals/corr

Zhuguanyu Wu Jiayi Zhang Jiaxin Chen 0002 Jinyang Guo Di Huang 0001 Yunhong Wang 0001 APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers. 9686-9695 2025 CVPR https://openaccess.thecvf.com/content/CVPR2025/html/Wu_APHQ-ViT_Post-Training_Quantization_with_Average_Perturbation_Hessian_Based_Reconstruction_for_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.00905 conf/cvpr/2025 db/conf/cvpr/cvpr2025.html#WuZ0G0025 Zhuguanyu Wu Shihe Wang Jiayi Zhang Jiaxin Chen 0002 Yunhong Wang 0001 FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation. 14891-14900 2025 CVPR https://openaccess.thecvf.com/content/CVPR2025/html/Wu_FIMA-Q_Post-Training_Quantization_for_Vision_Transformers_by_Fisher_Information_Matrix_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.01387 conf/cvpr/2025 db/conf/cvpr/cvpr2025.html#WuWZCW25

Zhuguanyu Wu Jiayi Zhang Jiaxin Chen 0002 Jinyang Guo Di Huang 0001 Yunhong Wang 0001 APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers. 2025 April abs/2504.02508 CoRR https://doi.org/10.48550/arXiv.2504.02508 db/journals/corr/corr2504.html#abs-2504-02508 streams/journals/corr

Zhuguanyu Wu Shihe Wang Jiayi Zhang Jiaxin Chen 0002 Yunhong Wang 0001 FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation. 2025 June abs/2506.11543 CoRR https://doi.org/10.48550/arXiv.2506.11543 db/journals/corr/corr2506.html#abs-2506-11543 streams/journals/corr

Xiangyu Fan Zesong Qiu Zhuguanyu Wu Fanzhou Wang Zhiqian Lin Tianxiang Ren Dahua Lin Ruihao Gong Lei Yang 0059 Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals. 2025 October abs/2510.27684 CoRR https://doi.org/10.48550/arXiv.2510.27684 db/journals/corr/corr2510.html#abs-2510-27684 streams/journals/corr

Zhuguanyu Wu Jiaxin Chen 0002 Hanwen Zhong Di Huang 0001 Yunhong Wang 0001 AdaLog: Post-training Quantization for Vision Transformers with Adaptive Logarithm Quantizer. 411-427 2024 ECCV (27) https://doi.org/10.1007/978-3-031-73383-3_24 conf/eccv/2024-27 db/conf/eccv/eccv2024-27.html#WuCZHW24 streams/conf/eccv

Zhuguanyu Wu Jiaxin Chen 0002 Hanwen Zhong Di Huang 0001 Yunhong Wang 0001 AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer. 2024 abs/2407.12951 CoRR https://doi.org/10.48550/arXiv.2407.12951 db/journals/corr/corr2407.html#abs-2407-12951 streams/journals/corr

Jiaxin Chen 0002 Xiangyu Fan Ruihao Gong Jinyang Guo Di Huang 0001 Yushi Huang Annan Li Dahua Lin Zhiqian Lin Xianglong Liu 0001 Guozhen Peng Zesong Qiu Tianxiang Ren Fanzhou Wang Shihe Wang Yunhong Wang 0001 Lei Yang 0059 Yang Yong Ruiyi Zhan Jiayi Zhang Shaoxiong Zhang 0001 Yuwei Zhao Hanwen Zhong