Xinxiao WU
Professor of computer science at BIT
Adjunct Professor of AI at SMBU
吳心筱
北京理工大學(xué)計(jì)算機(jī)學(xué)院教授，博士生導(dǎo)師
深圳北理莫斯科大學(xué)兼職教授。
Professor Xinxiao WU received her PhD degree from the School of Computer Science at Beijing Institute of Technology in 2010. From 2010 to 2011, she was a Postdoctoral Research Fellow at Nanyang Technological University, Singapore. She won the Outstanding Doctoral Thesis Award of the Chinese Artificial Intelligence Society in 2012. She has authored over 50 papers on top-tier journals such as IJCV, IEEE TIP, IEEE TNNLS, IEEE TMM and IEEE TCSVT, and top conferences such as ICCV, CVPR, ECCV, NeurIPS, AAAI, IJCAI, and ACM MM. Her research interests include computer vision, machine learning, and multi-modal reasoning. She has served on the editorial board of IEEE Transactions on Multimedia and served as Area Chair for ACM Multimedia 2021-2024.
吳心筱教授,《IEEE Transactions on Multimedia》期刊編委, 于2005年獲北京理工大學(xué)工學(xué)博士學(xué)位，2010-2011年赴新加坡南洋理工大學(xué)計(jì)算機(jī)系博士后研究。曾獲得中國(guó)人工智能學(xué)會(huì)優(yōu)秀博士學(xué)位論文獎(jiǎng)。在IJCV、IEEE TIP、IEEE TNNLS、IEEE TMM、IEEE TCSVT等重要國(guó)際刊物和ICCV、CVPR、ECCV、NeurIPS、AAAI、IJCAI、ACM MM等重要國(guó)際會(huì)議上發(fā)表學(xué)術(shù)論文50篇、出版專(zhuān)著1部。負(fù)責(zé)國(guó)家自然科學(xué)基金、教育部博士點(diǎn)基金等多項(xiàng)國(guó)家和省部級(jí)科研項(xiàng)目。主要研究興趣包括計(jì)算機(jī)視覺(jué)、機(jī)器學(xué)習(xí)、多模態(tài)推理等。
Selected papers：
1. Xinxiao Wu, Tong Li. Sentimental Visual Captioning using Multimodal Transformer[J]. International Journal of Computer Vision (IJCV), vol. 131, 2023: 1073-1090.
2. Xinxiao Wu, Wentian Zhao, Jiebo Luo. Learning Cooperative Neural Modules for Stylized Image Captioning[J]. International Journal of Computer Vision (IJCV), vol. 130, 2022:2305-2320.
3. Xinxiao Wu, Ruiqi Wang, Jingyi Hou, Hanxi Lin, Jiebo Luo. Spatial–Temporal Relation Reasoning for Action Prediction in Videos. International Journal of Computer Vision (IJCV), vol. 129, 2021: 1848-1505.
4. Mengxiao Tian, Xinxiao Wu, Yunde Jia. Adaptive Latent Graph Representation Learning for Image-Text Matching[J]. IEEE Transactions on Image Processing (T-IP), vol.32, 2023: 471-482.
5. Wentian Zhao, Xinxiao Wu, Jiebo Luo. Cross-Domain Image Captioning via Cross-Modal Retrieval and Model Adaptation[J]. IEEE Transactions on Image Processing (T-IP), vol.30, 2021: 1180-1192.
6. Yayun Qi, Wentian Zhao, Xinxiao Wu. Relational Distant Supervision for Image Captioning without Image-text Pairs[C]//AAAI Conference on Artificial Intelligence (AAAI), 2024, 4524-4532.
7. Jin Chen, Zhi Gao, Xinxiao Wu, Jiebo Luo. Meta-causal Learning for Single Domain Generalization[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023, 7683-7692.
8. Wentian Zhao, Xinxiao Wu, Jiebo Luo. Multi-modal Dependency Tree for Video Captioning[C]//35th Conference on Neural Information Processing Systems (NeurIPS), 2021.
9. Xinxiao Wu, Jianwei Zhao, Ruiqi Wang. Anticipating Future Relations via Graph Growing for Action Prediction[C]//AAAI Conference on Artificial Intelligence (AAAI), 2021, 2852-2960.
10. Jingyi Hou, Xinxiao Wu, Wentian Zhao, Jiebo Luo, Yunde Jia. Joint Syntax Representation Learning and Visual Cue Translation for Video Captioning[C]//International Conference on Computer Vision (ICCV), 2019, 8917-8926.
