学术论文

Lianwei Yang, Zhikai Li, Junrui Xiao, Haisong Gong, Qingyi Gu (2024). MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction. In ICIP 2024.

Mengjuan Chen, Shaopeng Hu, Kohei Shimasaki, Qingyi Gu, Idaku Ishii (2024). A Visual-Feedback-Based Active Light-Section 3-D Reconstruction Method for Moving Objects. In TIM.

Mengjuan Chen, Shaopeng Hu, Kohei Shimasaki, Qingyi Gu, Idaku Ishii (2024). A Visual-Feedback-Based Active Light-Section 3-D Reconstruction Method for Moving Objects. In ARSO.

Zhihang Yuan, Yuzhang Shang, Yang Zhou, Zhen Dong, Chenhao Xue, Bingzhe Wu, Zhikai Li, Qingyi Gu, Yong Jae Lee, Yan Yan (2024). LLM Inference Unveiled: Survey and Roofline Model Insights. In arxiv preprint.

Zhikai Li, Xuewen Liu, Jing Zhang, Qingyi Gu (2024). RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization. In arxiv preprint.

Xuewen Liu, Zhikai Li, Junrui Xiao, Qingyi Gu (2024). Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models. In arxiv preprint.

Zhikai Li, Xiaoxuan Liu, Banghua Zhu, Zhen Dong, Qingyi Gu, Kurt Keutzer (2023). Qft: Quantized full-parameter tuning of llms with affordable resources. In arxiv preprint.

Zhikai Li, Mengjuan Chen, Junrui Xiao, Qingyi Gu (2023). PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers. In TNNLS 2023.

Junrui Xiao, Zhikai Li, Lianwei Yang, Qingyi Gu (2023). Patch-Wise Mixed-Precision Quantization of Vision Transformer. In IJCNN 2023.

Zhikai Li, Junrui Xiao, Lianwei Yang, Qingyi Gu (2023). RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers. In ICCV 2023.

Zhikai Li, Qingyi Gu (2023). I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference. In ICCV 2023.

Junrui Xiao, Zhikai Li, Lianwei Yang, Qingyi Gu (2023). BinaryViT: Towards Efficient and Accurate Binary Vision Transformers. In arxiv preprint.

Junrui Xiao, He Jiang, Zhikai Li, Qingyi Gu (2023). DCIFPN: Deformable cross-scale interaction feature pyramid network for object detection. In IET Image Processing.

Yunze Chen, He Jiang, Junrui Xiao, Ding Li, Qingyi Gu (2023). Temporal Action Detection with Dynamic Weights based on Curriculum Learning. In Neurocomputing.

Junrui Xiao, He Jiang, Zhikai Li, Qingyi Gu (2022). Rethinking Prediction Alignment in One-stage Object Detection. In NEUCOM.

Xianlei Long, Mengjuan Chen, Zhikai Li, Qingyi Gu (2022). Region Probability Map-Guided Fast Wide-Area Multiobject Detection. In TIM.

Mengjuan Chen, Simeng Tian, Fan He, Qingqin Fu, Qingyi Gu, Baolin Wu (2022). CellNet: A Lightweight Model towards Accurate LOC-Based High-Speed Cell Detection. In Electronics.

Xianlei Long, Idaku Ishii, Qingyi Gu (2022). CellNet: A Lightweight Model towards Accurate LOC-Based High-Speed Cell Detection. In Electronics.

Zhikai Li, Liping Ma, Xianlei Long, Junrui Xiao, Qingyi Gu (2022). Dual-Discriminator Adversarial Framework for Data-Free Quantization. In NEUCOM.

Yunze Chen, Junjie Huang, Zheng Zhu, Xianlei Long, Qingyi Gu (2022). Boosting Semi-Supervised Face Recognition with Raw Faces. In IET Image Processing.

Xianlei Long, Liping Ma, He Jiang, Zhikai Li, Yunze Chen, Qingyi Gu (2022). Mechanical Particle Filter Based Active Vision System for Fast Wide-Area Multi-Object Detection. In TIM.

He Jiang, Qingyi Gu (2022). G-Head: Gating Head for Multi-task Learning in One-stage Object Detection. In ICME 2022.

Yunze Chen, Mengjuan Chen, Qingyi Gu (2022). Class-wise boundary regression by uncertainty in temporal action detection. In IET Image Processing.

Qing Li, Mengjuan Chen, Qingyi Gu, Idaku Ishii (2022). A Flexible Calibration Algorithm for High-speed Bionic Vision System based on Galvanometer. In IROS 2022.

Zhikai Li, Liping Ma, Mengjuan Chen, Junrui Xiao, Qingyi Gu (2022). Patch Similarity Aware Data-Free Quantization for Vision Transformers. In ECCV 2022.

He Jiang, Junrui Xiao, Qingyi Gu (2022). DLA: Dynamic Label Assignment for Accurate One-stage Object Detection. In ICSCA 2022:.

Yiming Hu, Xingang Wang, Qingyi Gu (2022). PWSNAS: Powering Weight Sharing NAS With General Search Space Shrinking Framework. In TNNLS.

Yiming Hu, Xinggang Wang, Lujun Li, Qingyi Gu (2021). Improving One-Shot NAS with Shrinking-and-Expanding Supernet. In patcog.

Xuejun Xing, Jianwei Guo, Liangliang Nan, Qingyi Gu, Xiaopeng Zhang, Dong-Ming Yan (2021). Efficient MSPSO Sampling for Object Detection and 6-D Pose Estimation in 3-D Scenes. In TIE.

Tianwei Wu, Xilong Liu, Mengjuan Chen, Qingyi Gu, Wenxiang Qin, Tingyu Yan, Jiawei Lu (2021). Calibration and Measurement of Large Distortion Binocular Camera Based on Fully Connected Neural Network. In RCAR 2021:.

Jianwei Guo, Xuejun Xing, Weize Quan, Dong-Ming Yan, Qingyi Gu, Yang Liu, Xiaopeng Zhang (2021). Efficient Center Voting for Object Detection and 6D Pose Estimation in 3D Point Cloud. In TIP.

Zhikai Li, Liping Ma, Xianlei Long, Yunze Chen, Haitao Deng, Fengxia Yan, Qingyi Gu (2021). Hardware-Oriented Algorithm for High-Speed Laser Centerline Extraction Based on Hessian Matrix. In TIM.

Yiming Hu, Yuding Liang, Zichao Guo, Ruosi Wan, Xiangyu Zhang, Qingyi Gu, Jian Sun (2020). Angle-based Search Space Shrinking for Neural Architecture Search. In ECCV 2021:.

Yunze Chen, Mengjuan Chen, Rui Wu, Jiagang Zhu, Zheng Zhu, Qingyi Gu (2020). Refinement of Boundary Regression Using Uncertainty in Temporal Action Localization. In BMVC 2020.

Shenhua Hu, Yiming Hu, Jianquan Li, Xianlei Long, Mengjuan Chen, Qingyi Gu (2020). Natural Scene Facial Expression Recognition with Dimension Reduction Network. In ICRA 2020.

Tingyu Yan, Jun Wang, Xilong Liu, Qingyi Gu, Mengjuan Chen (2019). Segmentation of Complex Object based on A Standardization Coding Method. In SSCI 2019.

Jianquan Li, Xianlei Long, Shenhua Hu, Yiming Hu, Qingyi Gu (2019). An Ultra-High-Speed Object Detection Method with Projection-based Position Compensation. In Journal of Real-Time Image Processing.

Jianquan Li, Xianlei Long, De Xu, Qingyi Gu (2019). An Ultra-High-Speed Object Detection Method with Projection-based Position Compensation. In TIM.

Shenhua Hu, Yiming Hu, Jianquan Li, Yunze Chen, Mengjuan Chen, Qingyi Gu (2019). Natural Scene Facial Expression Recognition based on Differential Features. In CAC 2019.

Yiming Hu, Siyang Sun, Jianquan Li, Jiagang Zhu, Xingang Wang, Qingyi Gu (2019). Multi-loss-aware Channel Pruning of Deep Networks. In ICIP 2019.

Yiming Hu, Jianquan Li, Xianlei Long, Shenhua Hu, Jiagang Zhu, Xingang Wang, Qingyi Gu (2019). Cluster Regularized Quantization for Deep Networks Compression. In ICIP 2019.

Xianlei Long, Shenhua Hu, Yiming Hu, Qingyi Gu, Idaku Ishii (2019). An Ultra-High-Speed Object Detection Method with Projection-based Position Compensation. In Sensors.

Jianquan Li, Xilong Liu, Fangfang Liu, De Xu, Qingyi Gu, Idaku Ishii (2019). A Hardware-Oriented Algorithm for Ultra-High-Speed Object Detection. In JSEN.

Michiaki Inoue, Qingyi Gu, Mingjun Jiang, Takeshi Takaki, Idaku Ishii, Kenji Tajima (2018). Motion-blur-free High-speed Video Shooting with Frame-timing Control. In ICST 2018.

Xianwu Jiang, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2018). A High-speed Vision System with Multithread Automatic Exposure Control for High-dynamic-range Imaging. In JRM.

Michiaki Inoue, Qingyi Gu, Mingjun Jiang, Takeshi Takaki, Idaku Ishii, Kenji Tajima (2017). 12,000-fps Multi-object Detection using HOG Descriptor and SVM Classifier. In IROS 2017.

Mingjun Jiang, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2017). Real-Time Vibration Source Tracking using High-Speed Vision. In JSEN.

Michiaki Inoue, Qingyi Gu, Mingjun Jiang, Takeshi Takaki, Idaku Ishii, Kenji Tajima (2017). Motion-Blur-Free High-Speed Video Shooting Using a Resonant Mirror. In Sensors.

Tadayoshi Aoyama, Qingyi Gu, Takeshi Takaki, Idaku Ishii (2017). Position and Inclination Control of a Passive Disk Based on Cyclic Motion Generation. In ROBOMECH Journal.

Atul Sharma, Kohei Shimasaki, Qingyi Gu, Jun Chen, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii, Koichi Tamura, Kenji Tajima (2016). Super High-Speed Vision Platform that can Process 1024x1024 Images in Real Time at 12500 Fps. In SII 2016.

Xianwu Jiang, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2016). A High-Frame-Rate High Dynamic Range Imaging from Virtual Multi-Thread Automatic Exposures. In ROBIO 2016.

Tadayoshi Aoyama, Amalka De Zoysa, Qingyi Gu, Takeshi Takaki, Idaku Ishii (2016). Motion-blur-free Video Recording under Microscope Using High-speed Intermittent Tracking. In Journal of Robotics and Mechatronics.

Takahiro Ueno, Tadayoshi Aoyama, Qingyi Gu, Takeshi Takaki, Idaku Ishii, Tomohiro Kawahara (2016). Motion-blur-free Video Recording under Microscope Using High-speed Intermittent Tracking. In Journal of the Robotics Society of Japan.

Qingyi Gu, Jun Chen, Tadayoshi Aoyama, Idaku Ishii (2016). An Efficient Watershed Algorithm for Preprocessed Binary Image. In 2016 IEEE International Conference on Information and Automation.

Qingyi Gu, Idaku Ishii (2016). Review of some advances and applications in real-time high-speed vision: Our views and experiences. In IJAC.

Tadayoshi Aoyama, Takeshi Takaki, Qingyi Gu, Idaku Ishii (2016). Control Scheme of Nongrasping Manipulation Based on Virtual Connecting Constraint. In ICRA 2016.

Jun Chen, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2015). Blink-spot Projection Method for Fast Three-dimensional Shape Measurement. In JRM.

Tadayoshi Aoyama, Takeshi Takaki, Qingyi Gu, Idaku Ishii (2015). An Intermittent Frame-by-frame Tracking Camera for Motion-blur-free Video Shooting. In SII 2015.

Tadayoshi Aoyama, Takeshi Takaki, Takumi Miura, Qingyi Gu, Idaku Ishii (2015). Realization of Flower Stick Rotation using Robotic Arm. In IROS 2015.

Qingyi Gu, Sushil Raut, Ken-Ichi Okumura, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2015). Real-time Image Mosaicing System Using a High-frame-rate Video Sequence. In JRM.

Takahiro Ueno, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Tomohiro Kawahara (2015). Motion-blur-free Microscopic Video Shooting based on Frame-by-frame Intermittent Tracking. In CoASE 2015.

Qingyi Gu, Tomohiro Kawahara, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii, Ayumi Takemoto, Naoaki Sakamoto (2015). LOC-Based High-throughput Cell Morphology Analysis System. In TASE.

Qingyi Gu, Naoki Nakamura, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2015). A Full-pixel Optical Flow System using a GPU-based High-frame-rate Vision. In AIR 2015.

Sushil Raut, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2015). Real-time Optical Image Stabilization using High Frame Rate Video Sequence at 500 Fps. In AIR 2015.

Tadayoshi Aoyama, Amalka De Zoysa, Qingyi Gu, Takeshi Takaki, Idaku Ishii (2015). Real-time Flow-rate Control System for Cell Analysis. In AIR 2015.

Jun Chen, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2015). A Fast 3D Shape Scanner using Two HFR Camera-projector Systems. In AIR 2015.

Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii, Ayumi Takemoto, Naoaki Sakamoto (2015). Real-time LOC-based Morphological Cell Analysis System using High-speed Vision. In IROS 2014.

Tadayoshi Aoyama, Yuji Harada, Qingyi Gu, Takeshi Takaki, Idaku Ishii (2015). A Scheme for Manipulating a Passive Object using an Active Plate. In ICRA 2015.

Jun Chen, Yongjiu Liu, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2014). Robot-mounted 500-fps 3-D Shape Measurement using Motion-compensated Coded Structured Light Method. In ROBIO 2014.

Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2014). Rapid Vision-based Shape and Motion Analysis System for Fast-flowing Cells in a Microchannel. In ICRA 2014.

Yongjiu Liu, Hao Gao, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2014). A Fast 3-D Shape Measurement Method for Moving Object. In PIC 2014.

Yongjiu Liu, Hao Gao, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2014). High-frame-rate Structured Light 3-D Vision for Fast Moving Objects. In JRM.

Tadayoshi Aoyama, Yuji Harada, Qingyi Gu, Takeshi Takaki, Idaku Ishii (2014). Cyclic Motion Design and Analysis for a Passive Object Manipulation using an Active Plate. In Advanced Robotics.

Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2013). Simultaneous Vision-based Shape and Motion Analysis of Cells Fast-flowing in a Microchannel. In TASE.

Jun Chen, Qingyi Gu, Hao Gao, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2013). Real-time Feature-based Video Mosaicing at 500 Fps. In IROS 2013.

Jun Chen, Qingyi Gu, Hao Gao, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2013). Fast 3-D Shape Measurement using Blink-dot Projection. In IROS 2013.

Xiaorong Zhao, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2013). A Fast Multi-camera Tracking System with Heterogeneous Lenses. In IROS 2013.

Qingyi Gu, Takeshi Takaki, Idaku Ishii (2013). Fast Tracking System for Multi-colored Pie-shaped Markers. In International Journal of Optomechatronics.

Qingyi Gu, Abdullah Al Noman, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2013). A Fast Color Tracking System with Automatic Exposure Control. In ICInfA 2013.

Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2013). Fast Tracking System for Multi-colored Pie-shaped Markers. In International Journal of Optomechatronics.

Hua Yang, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2013). Dynamics-based Stereo Visual Inspection using Multidimensional Modal Analysis. In JSEN.

Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2013). High-frame-rate Tracking of Multiple Color-patterned Objects. In JRTIP.

Hua Yang, Qingyi Gu, Tadayoshi Aoyama, Takeshi Takaki, Idaku Ishii (2013). Real-time Modal Analysis of Shell-shaped Objects using High-frame-rate Structured-light-based Vision. In IMAC-XXXI Conference & Exposition on Structural Dynamics.

Qingyi Gu, Takeshi Takaki, Idaku Ishii (2012). Fast FPGA-based Multiobject Feature Extraction. In TCSVT.

Qingyi Gu, Takeshi Takaki, Idaku Ishii (2012). 2000-fps Multi-object Tracking based on Color Histogram. In Real-Time Image and Video Processing 2012.

Idaku Ishii, Tomoki Ichida, Qingyi Gu, Takeshi Takaki (2012). 500-fps Face Tracking System. In Journal of Real-Time Image Processing.

Idaku Ishii, Tetsuro Tatebe, Qingyi Gu, Takeshi Takaki (2012). Color-histogram-based Tracking at 2000 Fps. In Journal of Electronic Imaging.

Qingyi Gu, Takeshi Takaki, Idaku Ishii (2012). A Fast Multiobject Extraction Algorithm based on Cell-based Connected Components Labeling. In IEICE TRANSACTIONS on Information and Systems.

Idaku Ishii, Tetsuro Tatebe, Qingyi Gu, Takeshi Takaki (2011). 2000 FPS Real-time Target Tracking Vision System Based on Color Histogram. In Real-Time Image and Video Processing 2011.

Qingyi Gu, Takeshi Takaki, Idaku Ishii (2010). 2000-FPS Multi-object Extraction based on Cell-based Labeling. In ICIP 2010.

Idaku Ishii, Tetsuro Tatebe, Qingyi Gu, Yuta Moriue, Takeshi Takaki, Kenji Tajima (2010). 2000 FPS Real-time Vision System with High-frame-rate Video Recording. In ROBOT 2010.