教师主页移动版

综合介绍 General Introduction 陶焕杰，男，博士，西北工业大学计算机学院副教授，硕士生导师、中国算机学会会员、中国图象图形学学会会员、教育部学位与研究生教育评审专家。博士期间曾到新加坡南洋理工大学联合培养。目前主讲本科生课程《神经网络模型与算法》和研究生课程《深度学习中的数学理论》，主持和参加了10余项国家和省部级科研项目，兼职多个期刊的审稿人，以一作/通讯作者发表论文30余篇，申请专利20余项。 所在课题组为图像计算课题组，专注于开展与图像计算密切相关的应用基础研究。研究方向主要包括：图像分类、目标检测、语义分割，弱/半/自/无监督学习、元/迁移/对比/主动/持续/小样本/提示学习，深度学习的训练方法、表示理论和泛化理论等。 今年有2-3个硕士招生名额，欢迎认真上进自律且有科研追求的学生报考。在你的整个研究生期间，我会为你制定详实的学习和研究计划，实现“挖掘科学问题-->解决科学问题-->发表研究成果”的全程陪跑。对我的研究方向感兴趣的同学请邮件联系我（huanjie_tao@nwpu.edu.cn），并附上个人简历和本科成绩单。  部分学术论文[1]  Huanjie Tao”. Smoke recognition in satellite imagery via an attention pyramid network with bidirectional multi-level multi-granularity feature aggregation and gated fusion[J]. IEEE Internet of Things Journal, 2023.（SCI，中科院一区Top） [2]  Huanjie Tao*, Qianyue Duan, Hierarchical attention network with progressive feature fusion for facial expression recognition[J]. Neural Networks. 2024, 170:337-348.（SCI，中科院一区Top）[3]  Huanjie Tao”. A triple interference removal network based on temporal and spatial attention interaction for forest smoke recognition in videos[J]. Computers and Electronics in Agriculture, 2024.（SCI，中科院一区Top） [4]  Huanjie Tao*, A label-relevance multi-direction interaction network with enhanced deformable convolution for forest smoke recognition[J]. Expert Systems with Applications, 2024, 236:121383.（SCI，中科院一区Top） [5]  Huanjie Tao*, Qianyue Duan, A spatial-channel feature-enriched module based on multi-context statistics attention[J]. IEEE Internet of Things Journal, 2023.（SCI，中科院一区Top） [6]  Huanjie Tao*, Erasing-inpainting-based data augmentation using denoising diffusion probabilistic models with limited samples for generalized surface defect inspection[J]. Mechanical Systems and Signal Processing, 2024, 208:111082. （SCI，中科院一区Top）[7]  Huanjie Tao*, Qianyue Duan, Jianfeng An. An adaptive interference removal framework for video person re-identification[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(9):5148-5159.（SCI，中科院一区Top） [8]  Huanjie Tao*, Qianyue Duan, Minghao Lu, Zhenwu Hu. Learning discriminative feature representation with pixel-level supervision for forest smoke recognition[J]. Pattern Recognition. 2023, 143:109761.（SCI，中科院一区Top）[9]  Huanjie Tao*, Qianyue Duan. An adaptive frame selection network with enhanced dilated convolution for video smoke recognition [J]. Expert Systems with Applications, 2023, 215:119371.（SCI，中科院一区Top） [10] Huanjie Tao*, Qianyue Duan. Learning discriminative feature representation for estimating smoke density of smoky vehicle rear[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 12(23):23136-23147.（SCI，中科院一区Top） [11] Huanjie Tao*, Chao Xie, Jing Wang, Zhouxin Xin. CENet: a channel-enhanced spatiotemporal network with sufficient supervision information for recognizing industrial smoke emissions[J]. IEEE Internet of Things Journal, 2022, 9(19):18749-18759.（SCI，中科院一区Top）[12] Huanjie Tao*, Minghao Lu, Zhenwu Hu, Zhouxin Xin, Jing Wang. Attention-aggregated attribute-aware network with redundancy reduction convolution for video-based industrial smoke emission recognition[J]. IEEE Transactions on Industrial Informatics, 2022, 18(11):7653-7664.（SCI，中科院一区Top）[13] Huanjie Tao, Peng Zheng *, Chao Xie, Xiaobo Lu*. A three-stage framework for smoke vehicle detection in traffic surveillance videos [J]. Information Sciences. 2020, 522:17-34.（SCI，中科院一区Top）[14] Huanjie Tao, Xiaobo Lu*. Smoke vehicle detection based on spatiotemporal bag-of-features and professional convolutional neural network [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30(10): 3301-3316.（SCI，中科院一区Top） 个人相册

教育教学

荣誉获奖

科学研究

学术成果

综合介绍