涂志刚-个人主页 (original) (raw)
新闻资讯&最新成果
2026-05，本课题组联合发起 ECCV 2026 Workshop——首届 Human-Centered Multimodal Intelligence in the Wild (HCMIW@ECCV2026) 征稿启事，诚邀投稿（截稿 2026-07-01）主页 投稿
2026-02，祝贺涂志刚教授入选中科院1区Top期刊Pattern Recognition(IF=7.6)编委
2025-12，祝贺涂志刚教授主持获批国家自然科学基金重点项目
2024-12，祝贺张嘉旭博士获国家自然科学基金“青年学生基础研究项目”
2024-10，涂志刚老师指导的“道行星迹”项目获中国国际大学生创新大赛高教主赛道-“全国金奖”
**2024-09，祝贺涂志刚老师入选2024年度全球前2%顶尖科学家“年度科学影响力排行榜”Link1 Link2
祝贺涂志刚教授团队荣获中科院1区Top期刊IEEE TCSVT 2022年度全球3位最佳审稿人之一！ (One of the three Best Reviewers of 2022)
**2026-01，祝贺章湘粤喜获“王之卓创新人才奖”（遥感全重推荐第一）
2025-5-22~2025-9-1，蹇浩航、向天琪前往小米实习
2025-5-7~2025-9-1，周誉喜、刘跃前往美团实习
2025-5-7~2025-9-1，朱俊宏前往百度实习
2023/2024-06，刘远忠、李松廉获“陈永龄院士优秀学生科技创新奖学金”
2024-03，黄志胜全额奖学金攻读美国得克萨斯A&M大学(TAMU)博士！
2024-02，祝贺黄志胜喜获国家奖学金（排名遥感国重硕士生第一名）
2024-02，祝贺黄志胜喜获“王之卓创新人才奖”（遥感国重仅5人）
2024-03，李松廉成功就职腾讯，郐洋成功就职阿里巴巴
2023-11，祝贺课题组博士生张嘉旭荣获首届“雷军卓越奖学金”（全校仅10人，个人奖金10万）Link
Professor Zhigang Tu serves as a Website & Social Media Chair for ICME2024, Canada (CCF B类会议)
2023-10-18，课题组喜获腾讯犀牛鸟基金技术创新奖
Professor Zhigang Tu serves as an Area Chair for AAAI 2023 (CCF A类会议)
Professor Zhigang Tu serves as an Area Chair for VICP 2022 (CCF C类会议)
祝贺小组在2021国际计算机视觉大会(ICCV2021)的MMVRAC挑战赛中 喜获“骨架人体动作识别”、“鱼眼视频人体动作识别”两个赛道的亚军Link
课题组一年级硕士研究生张嘉旭在中国人工智能学会CAAI主办的ACAIT2020大会上荣获“最佳学生论文奖”
涂志刚教授研发的“第七届世界军人运动会开闭幕式指挥调度系统”获国家测绘科技进步“一等奖”
Professor Zhigang Tu serves as an Associate Editor of the SCI-indexed journal: The Visual Computer (CCF C类期刊)
Professor Zhigang Tu serves as an Executive Guest Editor for the SCI-indexed journal: Combinatorial Chemistry & High Throughput Screening
涂志刚教授牵头，A股上市公司英飞拓与武汉大学测绘遥感信息工程国家重点实验室共同组建智慧城市时空信息技术研究中心.
---
CVPR 2026 DarkAct: A RGB-Thermal Dataset and Fusion Framework for Multimodal Low-Light Action Recognition. (CCF-A类会议，人工智能&计算机视觉三大顶会之一)
ACM MM2025 EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation. (CCF-A类会议，首次提出以speech query为基础的mask建模策略，用于精确识别语义关键帧，引导全身co-speech motion生成)
ICCV 2025 Oral Presenttaion MikuDance: Animating Character Art with Mixed Motion Dynamics. (CCF-A类会议，人工智能&计算机视觉三大顶会之一，首次提出了2D角色立绘的动作驱动视频生成大模型)
ICCV 2025 SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis. (CCF-A类会议，人工智能&计算机视觉三大顶会之一，提出语音驱动虚拟人运动生成)
CVPR 2025 Visual Prompting for One-shot Controllable Video Editing without Inversion. (CCF-A类会议，人工智能&计算机视觉三大顶会之一，首次从visual prompting的角度来看待one-shot可控视频编辑，消除了对不准确的ddim inversion的依赖)
**ACM MM 2024 Generative Motion Stylization of Cross-structure Characters within Canonical Motion Space. (CCF-A类会议，首次提出一种跨骨骼结构且支持多模态控制条件的动作风格化模型）
**ICLR 2024 TapMo: Shape-aware Motion Generation of Skeleton-free Characters. (机器学习排名第一顶会，提出了一种针对无骨骼动画角色的文本驱动运动生成方法，实现了无骨骼角色的统一动作驱动和感知形状的运动合成）
**ICCV 2023 PHRIT: Parametric Hand Representation with Implicit Template. (CCF-A类会议，人工智能&计算机视觉三大顶会之一，提出了一种新颖的人手参数化模型建模方法，在多个下游任务达到sota精度）
**CVPR 2023 Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry . (CCF-A类会议，人工智能&计算机视觉三大顶会之一，提出的运动重定向方法解决了角色自穿模问题，达到sota精度）
**CVPR 2022 MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video. (CCF-A类会议，人工智能&计算机视觉三大顶会之一，在多个3D人体姿态估计Benchmark上取得SOTA)
**ACM MM 2022 Uncertainty-Aware 3D Human Pose Estimation from Monocular Video. (CCF-A类会议，提出一种基于不确定性估计和先验概率的方法优化3D Pose的精度,在多个3D人体姿态估计Benchmark上取得SOTA)
**IJCAI-ECAI 2022 Oral Presentation Distilling Inter-Class Distance for Semantic Segmentation. (CCF-A类会议，提出一种类间距离蒸馏的方法, 在针对语义分割的知识蒸馏方法中取得SOTA)
**CVPR 2021 Model-based 3D Hand Reconstruction via Self-Supervised Learning. (CCF-A类会议，人工智能&计算机视觉三大顶会之一，首次实现了在噪声数据中以自监督的方式估计精确的手势)
**ECCV 2020 Clustering-driven Deep Autoencoder for Video Anomaly Detection. (CCF-A类会议，人工智能&计算机视觉三大顶会之一. 在多个公开数据库(UCSD, Avenue, ShanghaiTech)实现当时精度与速度第一)
**ICCV 2019 SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation with Semi-supervised Learning. (CCF-A类会议，人工智能&计算机视觉三大顶会之一. 多个3D手势识别公开数据库(NYU, MSRA, ICVL)实现当时精度第一)
2026-04-21, 1 paper has been accepted by IEEE TMM (IF=9.7)
2025-11-27, 1 paper has been accepted by IEEE TMM (IF=9.7)
2025-11-11, 1 paper has been accepted by IEEE Trans. CSVT (IF=11.1)
2025-11-08, 1 paper has been accepted by IEEE TIP (IF=13.7)
2025-10-20, 1 paper has been accepted by IEEE TIP (IF=13.7)
2025-10-05, 1 paper has been accepted by IEEE TMM (IF=9.7)
2025-09-05, 1 paper has been accepted by IEEE TIFS (IF=8.0)
2025-07-05, 1 paper has been accepted by ACM MM2025 (CCF A类)
2025-06-26, two paper has been accepted by ICCV2025 (CCF A类)
2025-04-16, 1 paper has been accepted by IEEE Trans. CSVT (IF=11.1)
2025-03-20, 1 paper has been accepted by CVPR2025 (CCF A类)
2024-08-07, 1 paper has been accepted by Neural Networks (IF=6.0)
2024-04-07, 1 paper has been accepted by IEEE TPAMI (IF=23.6)
2023-11-25, 1 paper has been accepted by IEEE Trans. CSVT (IF=8.4)
2023-06-10, 1 paper has been accepted by IEEE Trans. on Image Processing (IF=11.041)
2023-02-17, 1 paper has been accepted by IEEE TPAMI (IF=24.314)
2022-09-29, 1 paper has been accepted by IEEE Trans. on Image Processing (IF=11.041)
2022-07-21, 1 paper has been accepted by IEEE Trans. CSVT (IF=5.859).
2022-05-20, 1 paper has been accepted by IEEE Trans. on Image Processing (IF=10.856).
2022-04-20, 1 paper has been accepted by IJCAI2022 (CCF A类，Oral Presentation).
2022-04-13, 1 paper has been accepted by IEEE Trans. on Multimedia (IF=6.513).
2022-02-17, 1 survey paper has been accepted by Artificial Intelligence Review (IF=8.139).
2021-08-20, 1 paper has been accepted by Pattern Recognition (IF=7.74).
2021-03-20, 1 paper has been accepted by IEEE Trans. on Image Processing (IF=9.34).
2020-07-27, 1 paper has been accepted by IEEE Trans. on Image Processing (IF=9.34).
2020-02-24, 1 paper has been accepted by Pattern Recognition (IF=7.196).
---
2023-6-1~2023-10-1，黄志胜腾讯AI Lab实习
2022-6-15~2022-11-30， 张嘉旭腾讯AI-Lab实习.
2022-7-1~2022-9-30， 刘远忠滴滴实习.
2021-7-1~2021-10-15， 李可美团实习并成功签约美团.
2020-6-1~2020-9-1，刘祥健前往旷视科技实习.
2019-12-1~2020-2-28，陈雨劲前往腾讯AI Lab实习.
2019-7-1~2019-11-30，陈雨劲前往美国CSE department, State University of New York at Buffalo，Professor Junsong Yuan课题组交流.
三名研究生顺利毕业并找到合适工作： 陈雨劲全奖攻读德国慕尼黑工大博士！ 刘祥健华为中央研究院！ 汤佳欣成都市选调生！