2018-11--至今,  中科院自动化研究所,  副研究员
2016-07--2018-10   中科院自动化研究所， 助理研究员
2012-09--2016-07   中科院自动化研究所，博士
2009-09--2012-03   北京理工大学，硕士
2005-09--2009-07   北方工业大学，本科

多媒体内容分析、模式识别

(1) 国家自然科学基金委员会, 优秀青年科学基金项目, 62322212, 面向开放环境的多媒体内容理解,
2024-01-01 至 2026-12-31, 200万元, 在研, 主持
(2) 国家自然科学基金委员会, 面上项目, 62072455, 跨模态可解释性个体行为分析与健康管理, 2021-
01-01 至 2024-12-31, 58万元, 在研, 主持
(3) 科技委, XXX重点项目课题, XXX, 多模态小样本数据统一表示与跨域迁移, 2022-08 至
2025-08, 540万元, 在研, 主持
(4) 中国移动咪咕文化, AI能力定制, HT201801000260, 咪咕公司灵犀云视频精细化标签, 2018-01 至
2020-12, 122万元, 结题, 主持
(5) 腾讯, CCF-腾讯犀牛鸟科研基金, CCF-Tencent RAGR201801, 数据和知识联合驱动的视频精彩内容剪
辑, 2018-01 至 2019-12, 15万元, 结题, 主持

(1) Xiaoshan Yang; Baochen Xiong; Yi Huang; Changsheng Xu ; Cross-Modal Federated Human Activity Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
(2) Chaofan Chen; Xiaoshan Yang; Jinpeng Zhang; Bo Dong; Changsheng Xu ; Category Knowledgeguided Parameter Calibration for Few-shot Object Detection, IEEE Transactions on Image Processing, 2023, 32: 1092-1107
(3) Yuyang Wanyan; Xiaoshan Yang; Chaofan Chen; Changsheng Xu ; Active Exploration of Multimodal Complementarity for Few-Shot Action Recognition, IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), Vancouver, Canada, 2023
(4) Yiming Li; Xiaoshan Yang; Changsheng Xu ; Iterative Learning with Extra and Inner Knowledge for Long-tail Dynamic Scene Graph Generation, MM '23: The 31st ACM International Conference on Multimedia, Ottawa, Canada, 2023
(5) Baochen Xiong; Xiaoshan Yang; Yaguang Song; Yaowei Wang; Changsheng Xu ; Client-Adaptive Cross-Model Reconstruction Network for Modality-Incomplete Multimodal Federated Learning, MM '23: The 31st ACM International Conference on Multimedia, Ottawa, Canada, 2023
(6) Xiaoshan Yang; Baochen Xiong; Yi Huang; Changsheng Xu ; Cross-Modal Federated Human Activity Recognition via Modality-Agnostic and Modality-Specific Representation Learning, AAAI Conference on Artificial Intelligence (AAAI), Virtual Conference, 2022
(7) Yiming Li; Xiaoshan Yang; Changsheng Xu ; Dynamic Scene Graph Generation via Anticipatory Pre-training, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, Louisiana, 2022
(8) Yi Huang; Xiaoshan Yang; Ji Zhang; Changsheng Xu ; Relative Alignment Network for SourceFree Multimodal Video Domain Adaptation, The 30th ACM International Conference on Multimedia (MM), Lisbon, Portugal, 2022
(9) Fan Qi; Zixin Zhang; Xianshan Yang; Huaiwen Zhang; Changsheng Xu ; Feeling Without Sharing: A Federated Video Emotion Recognition Framework Via Privacy-Agnostic Hybrid Aggregation, The 30th ACM International Conference on Multimedia (MM), Lisbon, Portugal, 2022
(10) Chaofan Chen; Xiaoshan Yang; Ming Yan; Changsheng Xu ; Attribute-guided Dynamic Routing Graph Network for Transductive Few-shot Learning, The 30th ACM International Conference on Multimedia (MM), Lisbon, Portugal, 2022
(11) Chaofan Chen; Xiaoshan Yang; Changsheng Xu; Xuhui Huang; Zhe Ma ; ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual Conference, 2021
(12) Yi Huang; Xiaoshan Yang; Changsheng Xu ; Multimodal Global Relation Knowledge Distillation for Egocentric Action Anticipation, ACM International Conference on Multimedia (MM), Chengdu, China, 2021
(13) Fan Qi; Xiaoshan Yang; Changsheng Xu ; Zero-shot Video Emotion Recognition via Multimodal Protagonist-aware Transformer Network, ACM International Conference on Multimedia (MM), Chengdu, China, 2021
(14) Fang Peng; Xiaoshan Yang; Linhui Xiao; Yaowei Wang; Changsheng Xu ; SgVA-CLIP: Semanticguided visual adapting of vision-language models for few-shot image classification, IEEE Transactions on Multimedia(TMM), 2023
(15) Yaguang Song; Xiaoshan Yang; Changsheng Xu ; Recovering Generalization via Pre-traininglike Knowledge Distillation for Out-of-Distribution Visual Question Answering, IEEE Transactions on Multimedia (TMM), 2023

2023年国家优秀青年基金
2018年腾讯犀牛鸟卓创奖
2017年中国科学院优秀博士学位论文
2017年中国多媒体大会(ChinaMM)最佳论文奖
2016年中科院院长优秀奖

[1] 一种实时事件流识别方法及系统, 发明专利, 2022, 第 3 作者, 专利号: CN113901880A
[2] 视频行为预测方法、系统、电子设备及存储介质, 发明专利, 2021, 第 2 作者, 专利号: CN113705402A
[3] 视频精彩片段检测方法及系统, 发明专利, 2020, 第 3 作者, 专利号: CN111611950A
[4] 基于知识图谱预测视频精彩级别的方法、装置及存储介质, 发明专利, 2020, 第 1 作者, 专利号: CN110851621A
[5] 描述文本生成方法及装置, 发明专利, 2019, 第 1 作者, 专利号: CN110110145A
[6] 基于视觉属性的社会事件识别方法, 发明专利, 2014, 第 2 作者, 专利号: CN104142995A
[7] 学习跨平台多模态媒体数据共同特征表示的方法及装置, 发明专利, 2014, 第 2 作者, 专利号: CN104133807A
[8] 样本目标检测方法和装置，2021，第3作者，专利号：CN202111501858.2
[9] 视觉关系检测方法、电子设备、存储介质和程序产品，2021，第3作者，专利号：CN202111518629.1
[10] 视频行为预测方法、系统、电子设备及存储介质, 2021，第2作者，专利号：CN202110950812.2