设为首页|English Version
当前位置: 首页 >> 师资队伍
教师内容页
刘龙军  
研究领域(方向)

计算机视觉相关的智能感知算法模型优化与加速,软硬件协同模型压缩与计算架构研究, VLSI/SoC数字集成电路与智能芯片、智能系统设计等。

个人及工作简历

2015年毕业于西安交通大学电信学院人工智能与机器人研究所,获模式识别与智能系统专业工学博士学位,博士期间赴美国佛罗里达大学(University of Florida,UF)国家公派联合培养留学两年。毕业后留校在人工智能与机器人研究所工作,2019年晋升副教授,在人工智能、集成电路设计、智能系统体系架构等研究领域发表五十余篇论文,包括如ISCA,CVPR,AAAI,ACM MM,TPDS,TCS-I,TCSVT,TMM,等著名学术会议与期刊。获得中国自动化学会“CAA自然科学奖”一等奖(“从芯片到系统的高效智能计算架构关键技术研究”,第二完成人);高等教育(研究生)国家级教学成果一等奖(“价值塑造、前沿引领、产教融合、团队协同的人工智能高层次人才培养新体系”);获得IEEE Computer Architecture Letter(IEEE计算机体系结构期刊快报,第一作者)期刊年度最佳论文奖“Best of CAL”;以第一作者投稿的学术论文获得计算机体系结构领域国际顶级学术会议IEEE/ACM International Symposium on Computer Architecture(ISCA,IEEE/ACM国际计算机体系结构学术年会,第一作者)收录并在大会上做论文口述报告。获得IEEE International Conference on ASIC(IEEE国际专用集成电路设计学术会议)“优秀学生论文奖”(第一作者)。获中国自动化学会科普奖“CAA科普奖”(“AI科普行动”)等等。

科研项目

国家自然科学基金、国家重点研发计划、国家重大科技专项、国家博士后基金、陕西省基金、中国工程院咨询项目、研究生横向项目等。

学术及科研成果、专利、论文

近年指导研究生发表的部分学术论文:

“CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection”[C], IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024 (CCF A类).

“Compensation Architecture to Alleviate Noise Effects in RRAM-based Computing-in-memory Chips with Residual Resource”[C], The 57th IEEE International Symposium on Circuits and Systems (ISCAS), 2024.

“IS-DARTS: Stablizing DARTS through Presice Measurement on Candidate Importance”[C], The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024 (CCF A类).

“RepCo: Replenish Sample Views with Better Consistency for Contrastive Learning”[J], Neural Networks , 2023.

“Design Hybrid Computing Architecture for Accelerating Point Cloud Registration”[C], IEEE Intelligent Vehicles Symposium (IV) , 2023.

“Hierarchical Model Compression via Shape-Edge Representation of Feature Maps -- an Enlightenment from the Primate Visual System”[J], IEEE Transactions on Multimedia (TMM) , 2022.

“Rethinking the Mechanism of the Pattern Pruning and the Circle Importance Hypothesis”[C], 30th ACM International Conference on Multimedia (ACM MM), 2022. (CCF A类)

“Robust and Efficient Star Identification Algorithm based on 1D Convolutional Neural Network” [J], IEEE Transactions on Aerospace and Electronic Systems (T-AES), 2022.

“Exploring the Discriminative Feature and Feature Correlation of Feature Maps for Hierarchical DNN Pruning and Compression”[J], IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2022.

“AKECP: Adaptive Knowledge Extraction from Feature Maps for Fast and Efficient Channel Pruning”[C], 29th ACM International Conference on Multimedia (ACM MM), 2021. (CCF A类)

“CMD: Controllable Matrix Decomposition with Global Optimization for Deep Neural Network Compression”[J], Springer Journal Machine Learning (JML), 2021.

“DFSNet: Dividing-Fuse Deep Neural Networks with Searching Strategy for Distributed DNN Architecture”[J], ELSEVIER Journal Neurocomputing, 2021.

“HSC: Leveraging Horizontal Shortcut Connections for Improving Accuracy and Computational Efficiency of Lightweight CNN”[J], ELSEVIER Journal Neurocomputing, 2021

“Adaptive Weight Mapping Strategy to Address the Parasitic Effects for ReRAM-based Neural Networks”[C], The IEEE International Conference on ASIC (ASICON), 2021.

"Dynamic Dataflow Scheduling and Computation Mapping Techniques for Efficient Depthwise Separable Convolution Acceleration," [J] IEEE Transactions on Circuits and Systems I: Regular Papers (TCAS-I), vol. 68, no. 8, Aug. 2021. (CCF A类)

"Lane Shared Bit-Pragmatic Deep Neural Network Computing Architecture and Circuit," [J] in IEEE Transactions on Circuits and Systems II: Express Briefs (TCAS-II), vol. 68, no. 1, Jan. 2021.

 "Designing Efficient Shortcut Architecture for Improving the Accuracy of Fully Quantized Neural Networks Accelerator,"[C] 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC), 2020

联系方式
电子邮箱:liulongjun@xjtu.edu.cn
联系电话:13002978196
联系地址:西安交通大学兴庆校区科学馆2楼202办公室,创新港校区四号楼4-2173办公室
更新日期:2024-03-26