吴心筱 博士

教授 博士生导师

北京理工大学计算机学院教师。2010年7月在北京理工大学获得计算机应用技术工学博士学位,并获得北京理工大学优秀博士学位论文奖。2010年至2011年赴新加坡南洋理工大学计算机学院从事博士后研究。2011年12月加入北京理工大学计算机学院。2012年获得全国人工智能学会优秀博士学位论文奖。2013年入选校级优秀青年教师资助计划。在计算机视觉与人工智能顶级国际会议ICCV, CVPR, ECCV, AAAI, IJCAI, ACM MM以及SCI收录国际重要学术期刊IJCV, IEEE TIP, IEEE TMM, IEEE TNNLS, IEEE TCSVT, IEEE TCYB上发表多篇论文。负责国家自然科学青年基金、面上项目、教育部博士点基金、国防预研项目等多项科研项目以及多项校企合作项目。担任国际多媒体领域顶级期刊IEEE TMM编委。主要从事机器学习、视觉和语言、图像视频内容理解方向的研究。

欢迎有志于视觉与语言、机器学习、人工智能研究的的同学们加入我们!

  • wuxinxiao.github.io

新闻

  • 2024-01-23

    石语珩和林瀚熙论文“Commonsense Knowledge Prompting for Few-shot Action Recognition in Videos”被IEEE Transactions on Multimedia (TMM) 录用,祝贺语珩和瀚熙!
  • 2023-12-09

    杨硕和王泳琪论文“Multi-modal Prompting for Open-vocabulary Video Visual Relationship Detection”被The 38th AAAI Conference on Artificial Intelligence (AAAI2024) 录用,祝贺杨硕和泳琪!
  • 2023-12-09

    齐雅昀论文“Relational Distant Supervision for Image Captioning without Image-text Pairs”被The 38th AAAI Conference on Artificial Intelligence (AAAI2024) 录用,祝贺雅昀!
  • 2023-07-26

    杨硕和尚子睿论文“Probability Distribution Based Frame-supervised Language-driven Action Localization”被The 31st ACM International Conference on Multimedia (ACM MM2023) 录用,祝贺杨硕和子睿!
  • 2023-07-17

    赵文天论文“Boosting Entity-aware Image Captioning with Multi-modal Knowledge Graph”被IEEE Transactions on Multimedia (TMM) 录用,祝贺文天!
  • 2023-04-20

    邵世通和陈焕然论文“Teaching What You Should Teach: A Data-Based Distillation Method”被International Joint Conference on Artificial Intelligence (IJCAI2023) 录用,祝贺世通和焕然!
  • 2023-03-29

    朱宇博论文“Topic-aware Video Summarization using Multimodal Transformer”被Pattern Recognition (PR) 录用,祝贺宇博!
  • 2023-03-17

    纪校锋论文“Counterfactual Inference for Visual Relationship Detection in Videos”被IEEE International Conference on Multimedia and Expo (ICME2023) 录用,祝贺校锋!
  • 2023-02-28

    陈谨论文“Meta-causal Learning for Single Domain Generalization”被The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR2023) 录用,祝贺陈谨!
  • 2023-01-19

    赵文天和齐雅昀获得首届“兴智杯”全国人工智能创新应用大赛多模态技术创新赛二等奖!祝贺文天和雅昀!
  • 2023-01-06

    李彤论文“Sentimental Visual Captioning using Multimodal Transformer”被International Journal of Computer Vision (IJCV) 录用,祝贺李彤!
  • 2022-12-05

    田孟潇论文“Adaptive Latent Graph Representation Learning for Image-Text Matching”被IEEE Transactions on Image Processing (TIP) 录用,祝贺孟潇!
  • 2022-05-29

    赵文天论文“Learning Cooperative Neural Modules for Stylized Image Captioning”被International Journal of Computer Vision (IJCV) 录用,祝贺文天!
  • 2022-04-21

    杨硕论文“Entity-Aware and Motion-Aware Transformers for Language-driven Action Localization”被International Joint Conference on Artificial Intelligence (IJCAI2022) 录用,祝贺杨硕!
  • 2022-03-07

    林瀚熙论文“Adaptive Recursive Circle Framework for Fing-grained Action Recognition”被IEEE International Conference on Multimedia and Expo (ICME2022) 录用,祝贺瀚熙!
  • 2021-12-01

    陈谨和纪校锋论文“Adaptive Image-to-video Scene Graph Generation via Knowledge Reasoning and Adversarial Learning”被36th AAAI Conference on Artificial Intelligence (AAAI2022) 录用,祝贺陈谨和校锋!
  • 2021-09-29

    赵文天论文“Multi-modal Dependency Tree for Video Captioning”被Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS2021) 录用,祝贺文天!
  • 2021-03-13

    陈谨论文“Sequential Instance Refinement for Cross-domain Object Detection in Images”被IEEE Transactions on Image Processing (TIP) 录用,祝贺陈谨!
  • 2021-03-12

    侯静怡和齐雅昀论文“跨语言知识蒸馏的视频中文字幕生成”被《计算机学报》录用,祝贺静怡和雅昀!
  • 2021-03-07

    李彤论文“Image Captioning with Inherent Sentiment”被IEEE International Conference on Multimedia and Expo (ICME2021 Oral) 录用,祝贺李彤!
  • 2020-12-02

    赵建伟和王瑞琦论文“Anticipating Future Relations via Graph Growing for Action Prediction”被The 35th AAAI Conference on Artificial Intelligence (AAAI2021) 录用,祝贺建伟和瑞琦!
  • 2020-12-02

    陈谨论文“Spatial-temporal Causal Inference for Partial Image-to-video Adaptation”被35th AAAI Conference on Artificial Intelligence (AAAI2021) 录用,祝贺陈谨!
  • 2020-11-24

    赵文天论文“Cross-domain Image Captioning via Cross-modal Retrieval and Model Adaptation”被IEEE Transactions on Image Processing (TIP) 录用,祝贺文天!
  • 2020-11-20

    王瑞琦论文“Spatial-Temporal Relation Reasoning for Action Prediction in Videos”被International Journal of Computer Vision (IJCV) 录用,祝贺瑞琦!
  • 2020-09-25

    陈谨论文“Domain Adversarial Reinforcement Learning for Partial Domain Adaptation”被IEEE Transactions on Neural Networks and Learning Systems (TNNLS) 录用,祝贺陈谨!
  • 2020-07-26

    陈佳露论文“Preserving Global and Local Temporal Consistency for Arbitrary Video Style Transfer”被ACM Multimedia 2020录用,祝贺佳露!

研究方向

人工智能   视频定位  计算机视觉  
视觉描述生成   视觉和语言  视频风格迁移  
动物交互分析 人体动作识别   迁移学习 
领域自适应   跨域目标检测 领域泛化 
视频摘要生成  多模态视频分析理解   视觉故事生成
 

代表性论文

Commonsense Knowledge Prompting for Few-shot Action Recognition in Videos.

Yuheng Shi, Xinxiao Wu, Hanxi Lin.
IEEE Transactions on Multimedia (TMM), 2024

Multi-Modal Prompting for Open-Vocabulary Video Visual Relationship Detection.

Shuo Yang, Yongqi Wang, Xinxiao Wu.
AAAI Conference on Artificial Intelligence (AAAI), 2024

Probability Distribution Based Frame-supervised Language-driven Action Localization.

Shuo Yang, Zirui Shang, Xinxiao Wu.
The 31st ACM International Conference on Multimedia (ACM MM), 2023

Boosting Entity-aware Image Captioning with Multi-modal Knowledge Graph.

Wentian Zhao, Xinxiao Wu.
IEEE Transactions on Multimedia (TMM), 2023

Topic-aware Video Summarization using Multimodal Transformer.

Yubo Zhu, Wentian Zhao, Rui Hua, Xinxiao Wu.
Pattern Recognition (PR), 2023

Meta-causal Learning for Single Domain Generalization.

Jin Chen, Zhi Gao, Xinxiao Wu, Jiebo Luo.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Sentimental Visual Captioning using Multimodal Transformer.

Xinxiao Wu, Tong Li
International Journal of Computer Vision (IJCV), 2023

Adaptive Latent Graph Representation Learning for Image-Text Matching.

Mengxiao Tian, Xinxiao Wu, Yunde Jia.
IEEE Transactions on Image Processing (TIP), 2022

Learning Cooperative Neural Modules for Stylized Image Captioning.

Xinxiao Wu, Wentian Zhao, Jiebo Luo
International Journal of Computer Vision (IJCV), 2022

Entity-aware and Motion-aware Transformers for Language-driven Action Localization in Videos.

Shuo Yang, Xinxiao Wu.
International Joint Conference on Artificial Intelligence (IJCAI), 2022

Adaptive Recursive Circle Framework for Fing-grained Action Recognition.

Hanxi Lin, Wentian Zhao, Xinxiao Wu.
IEEE International Conference on Multimedia and Expo (ICME), 2022

Adaptive Image-to-video Scene Graph Generation via Knowledge Reasoning and Adversarial Learning.

Jin Chen, Xiaofeng Ji, Xinxiao Wu.
AAAI Conference on Artificial Intelligence (AAAI), 2022

Multi-modal Dependency Tree for Video Captioning.

Wentian Zhao, Xinxiao Wu, Jiebo Luo.
Neural Information Processing Systems (NeurIPS), 2021

Spatial–Temporal Relation Reasoning for Action Prediction in Videos.

Xinxiao Wu, Ruiqi Wang, Jingyi Hou, Hanxi Lin, Jiebo Luo.
International Journal of Computer Vision (IJCV), 2021

Sequential Instance Refinement for Cross-Domain Object Detection in Images.

Jin Chen, Xinxiao Wu, Lixin Duan, Lin Chen.
IEEE Transactions on Image Processing (TIP), 2021

Image Captioning with Inherent Sentiment.

Tong Li, Yunhui Hu, Xinxiao Wu.
IEEE International Conference on Multimedia and Expo (ICME) oral, 2021

Cross-Domain Image Captioning via Cross-Modal Retrieval and Model Adaptation.

Wentian Zhao, Xinxiao Wu, Jiebo Luo.
IEEE Transactions on Image Processing (TIP), 2021

Spatial-temporal Causal Inference for Partial Image-to-video Adaptation.

Jin Chen, Xinxiao Wu, Yao Hu, Jiebo Luo.
AAAI Conference on Artificial Intelligence (AAAI), 2021

Anticipating Future Relations via Graph Growing for Action Prediction.

Xinxiao Wu, Jianwei Zhao, Ruiqi Wang.
AAAI Conference on Artificial Intelligence (AAAI), 2021

Exploiting Informative Video Segments for Temporal Action Localization.

Che Sun, Hao Song, Xinxiao Wu, Yunde Jia, Jiebo Luo.
IEEE Transactions on Multimedia (TMM), 2020

Domain Adversarial Reinforcement Learning for Partial Domain Adaptation.

Jin Chen, Xinxiao Wu, Lixin Duan, Shenghua Gao.
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2020

Preserving Global and Local Temporal Consistency for Arbitrary Video Style Transfer.

Xinxiao Wu, Jialu Chen.
ACM International Conference on Multimedia (ACM MM), 2020

Confidence-guided self refinement for action prediction in untrimmed videos.

Jingyi Hou, Xinxiao Wu, Ruiqi Wang, Jiebo Luo, Yunde Jia.
IEEE Transactions on Image Processing (TIP), 2020

Joint Learning of Multiple Latent Domains and Deep Representations for Domain Adaptation.

Xinxiao Wu, Jin Chen, Feiwu Yu, Mingyu Yao, Jiebo Luo.
IEEE Transactions on Cybernetics (T-CYB), 2020

Learning Normal Patterns via Adversarial Attention-Based Autoencoder for Abnormal Event Detection in Videos.

Hao Song, Che Sun, Xinxiao Wu, Mei Chen, Yunde Jia.
IEEE Transactions on Multimedia (TMM), 2020

Joint Commonsense and Relation Reasoning for Image and Video Captioning.

Jingyi Hou, Xinxiao Wu, Xiaoxun Zhang, Yayun Qi, Yunde Jia, Jiebo Luo.
AAAI Conference on Artificial Intelligence (AAAI), 2020

MemCap: Memorizing Style Knowledge for Image Captioning.

Wentian Zhao, Xinxiao Wu, Xiaoxun Zhang.
AAAI Conference on Artificial Intelligence (AAAI), 2020

Exploiting Images for Video Recognition: Heterogeneous Feature Augmentation via Symmetric Adversarial Learning.

Feiwu Yu, Xinxiao Wu, Jialu Chen, Lixin Duan.
IEEE Transactions on Image Processing (TIP),2019

Temporal Action Localization in Untrimmed Videos using Action Pattern Trees.

Hao Song, Xinxiao Wu, Bing Zhu, Yuwei Wu, Mei Chen, Yunde Jia.
IEEE Transactions on Multimedia (TMM), 2019

Unsupervised Deep Learning of Mid-Level Video Representation for Action Recognition.

Jingyi Hou, Xinxiao Wu, Jin Chen, Jiebo Luo, Yunde Jia
AAAI Conference on Artificial Intelligence (AAAI), 2018

Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks.

Feiwu Yu, Xinxiao Wu, Yuchao Sun, Lixin Duan.
International Joint Conference on Artificial Intelligence (IJCAI), 2018

Extracting Key Segments of Videos for Event Detection by Learning From Web Sources.

Hao Song, Xinxiao Wu, Wennan Yu, Yunde Jia.
IEEE Transactions on Multimedia (TMM), 2018

Content-Attention Representation by Factorized Action-Scene Network for Action Recognition.

Jingyi Hou, Xinxiao Wu, Yuchao Sun, Yunde Jia.
IEEE Transactions on Multimedia (TMM), 2017

A Hierarchical Video Description for Complex Activity Understanding.

Cuiwei Liu, Xinxiao Wu, Yunde Jia.
International Journal of Computer Vision (IJCV), 2016

Cross-View Action Recognition Over Heterogeneous Feature Spaces.

Xinxiao Wu, Han Wang, Cuiwei Liu, Yunde Jia.
IEEE Transactions on Image Processing (TIP), 2015

Video Annotation via Image Groups from the Web.

Han Wang, Xinxiao Wu, and Yunde Jia.
IEEE Transactions on Multimedia (TMM), 2014

Cross-View Action Recognition over Heterogeneous Feature Spaces.

Xinxiao Wu, Han Wang, Cuiwei Liu, Yunde Jia.
IEEE International Conference on Computer Vision (ICCV), 2013

View-Invariant Action Recognition Using Latent Kernelized Structural SVM.

Xinxiao Wu, Yunde Jia.
European Conference on Computer Vision (ECCV), 2012

Action recognition using context and appearance distribution features.

Xinxiao Wu, Dong Xu, Lixin Duan, Jiebo Luo.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011

Incremental discriminative-analysis of canonical correlations for action recognition.

Xinxiao Wu, Wei Liang, Yunde Jia.
IEEE International Conference on Computer Vision (ICCV), 2009

研究生小伙伴

杨硕

博士生
video grounding

田孟潇

博士生
video understanding

齐雅昀

博士生
video caption

朱宇博

硕士生
style transfer

李鸿熙

硕士生
video summarization

石语珩

硕士生
action recognition

黄希晴

硕士生
action segmentation

王泳琪

硕士生
video relation detection

尚子睿

硕士生
video grounding

王子奕

硕士生
domain generalization

毕业生

王晗

北京林业大学 副教授

宋浩

腾讯 研究员

侯静怡

北京科技大学 师资博士后

刘超

阿里巴巴 高级算法工程师

余非梧

阿里达摩院 开发工程师

朱冰

阿里云 数据工程师

孙宇超

旷视科技 算法研究员

王瑞琦

小米 产品经理

滑蕊

航空工业制造院 信息化管理

陈佳露

小米 算法工程师

李天宇

京投 管培生

林瀚熙

字节跳动 算法工程师

李彤

阿里巴巴 算法工程师

陈谨

航天智能院 研发工程师

赵文天

北京理工大学 博士后

闻子涵

中国空间技术研究院 算法工程师

纪校锋

字节跳动 算法工程师

伊嘉诚

中国人民解放军战略支援部队 助理工程师

教学内容

人工智能基础

本科生课程
秋季开学

图像与视频处理

硕士课程
秋季开学

计算感知

博士课程
秋季开学