Currently I am a lead research scientist at Salesforce. Before that I was a senior researcher at MetaMind. And I worked as a Postdoctoral Researcher Scholar at the University of California, Los Angeles (UCLA) from Jun 2014 to Sep 2015. I got my Ph.D. in the department of Computer Science and Engineering, University at Buffalo, SUNY in 2014 under the supervision of Prof. Jason J. Corso. And I got my B.S. and M.S. of Computer Science degree from Huazhong University of Science and Technology(HUST) in the year 2005 and 2007 in China..

Research Interests

Deep Learning, Video Parsing, Image Classification, Interactive Robot Learning, Natural Language Processing, Dialogue Learning, Metric Learning, Large Scale Retrieval.

Institutions

         

Links

Curriculum Vitae
Google Scholar

Contact

cxiong [at] buffalo.edu

Publications

arXiv:

A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks, K. Hashimoto, C. Xiong, Y. Tsuruoka and R. Socher. [ pdf, blog post]

A Way out of the Odyssey: Analyzing and Combining Recent Insights for LSTMs, S. Longpre, S. Pradhan, C. Xiong and R. Socher. [ pdf]

Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning, J. Lu*, C. Xiong*, D. Parikh and R. Socher.
[ pdf] (* equal contribution).

2017

Dynamic Coattention Networks For Question Answering, C. Xiong, V. Zhong and R. Socher.
International Conference on Learning Representations (ICLR 2017), (Accepted).[ pdf, blog post]

Quasi-Recurrent Neural Networks, J. Bradbury, S. Merity, C. Xiong and R. Socher.
International Conference on Learning Representations (ICLR 2017), (Accepted).[ pdf, blog post]

Pointer Sentinel Mixture Models, S. Merity, C. Xiong, James Bradbury and R. Socher.
International Conference on Learning Representations (ICLR 2017), (Accepted).[ pdf, new dataset]

2016

Dynamic Memory Networks for Visual and Textual Question Answering, C. Xiong, S. Merity and R. Socher.
The 33rd International Conference on Machine Learning (ICML 2016). [ pdf, New York Times]

Active Clustering with Model-Based Uncertainty Reduction, C. Xiong, D. M. Johnson and J. J. Corso.
IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI). [ pdf]

Recognizing Car Fluents from Videos, B. Li, T.F. Wu, C. Xiong , S.C. Zhu.
IEEE Computer Vision and Pattern Recognition (CVPR 2016) . [ pdf ] (Oral Presentation)

Grounded Semantic Role Labeling, S. Yang, Q. Gao, C. Liu, C. Xiong, J. Chai.
The 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2016). [ pdf ] (Long Paper)

Robot Learning with a Spatial, Temporal, and Causal And-Or Graph, C. Xiong , N. Shukla, W. Xiong, and S.C. Zhu.
IEEE International Conference on Robotics and Automation (ICRA 2016).
[ pdf ]

Maximum Margin Dirichlet Process Mixtures for Clustering, G. Chen, H. Zhang and C. Xiong.
AAAI Conference on Artificial Intelligence (AAAI 2016).
[ pdf ]

Semi-Supervised Nonlinear Distance Metric Learning via Forests of Max-Margin Cluster Hierarchies, D. M. Johnson, C. Xiong and J. J. Corso.
IEEE Transactions on Knowledge and Data Engineering (TKDE). [ pdf ]

2015

A Unified Framework for Human-Robot Knowledge Transfer, N. Shukla, C. Xiong and S.C. Zhu.
AAAI Fall Symposium on AI for Human-Robot Interaction (AI-HRI 2015).
[ pdf ]

Joint Action Recognition and Pose Estimation From Video, B. X. Nie, C. Xiong and S.C. Zhu.
IEEE Computer Vision and Pattern Recognition (CVPR 2015).
[ pdf ]

Can humans fly? Action understanding with multiple classes of actors, C. Xu, S.-H. Hsieh, C. Xiong, and J. J. Corso.
IEEE Computer Vision and Pattern Recognition (CVPR 2015).
[ pdf ]

Jointly modeling deep video and compositional text to bridge vision and language in a unified framework, R. Xu, C. Xiong, W. Chen, and J. J. Corso.
AAAI Conference on Artificial Intelligence (AAAI 2015).
[ pdf ]

2014

Seeing is worse than believing: Reading people's minds better than computer vision methods recognize actions, A. Barbu, D. Barrett, W. Chen, N. Siddharth, C. Xiong , J. J. Corso, C. D. Fellbaum, C. Hanson, S. J. Hanson, S. Helie, E. Malaia, B. A. Pearlmutter, J. M. Siskind, T. M. Talavage, and R. B. Wilbur.
European Conference on Computer Vision (ECCV 2014).
[ pdf ]

Latent Domains Modeling for Visual Domain Adaptation, C. Xiong , Scott McCloskey, Shao-Hang Hsieh and J. J. Corso.
AAAI Conference on Artificial Intelligence (AAAI 2014).
[ pdf ](Oral Presentation)

Actionness Ranking with Lattice Conditional Ordinal Random Fields, Wei Chen, C. Xiong and J. J. Corso
IEEE Computer Vision and Pattern Recognition (CVPR 2014).
[ pdf , code. ]

Adaptive Quantization for Hashing: An Information-Based Approach to Learning Binary Codes, C. Xiong , W. Chen, G. Chen, D. M. Johnson and J. J. Corso
SIAM International Conference on Data Mining (SDM 2014).
[ pdf, code. ](Oral Presentation)

Spectral Active Clustering of Remote Sensing Images, Z. Wang, G.-S. Xia,C. Xiong and L. Zhang.
IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2014).
[pdf]

2013

Uncertainty reduction for active image clustering via a hybrid global-local uncertainty model, C. Xiong, D. M. Johnson, and J. J. Corso.
AAAI Conference on Artificial Intelligence (Late-Breaking Papers Track) (AAAI 2013).
[ pdf, code. ]

Comprehensive cross-hierarchy cluster agreement evaluation, D. M. Johnson, C. Xiong, and J. J. Corso.
AAAI Conference on Artificial Intelligence (Late-Breaking Papers Track) (AAAI 2013).
[ pdf, code. ]

2012

Streaming hierarchical video segmentation, C. Xu*, C. Xiong* and J. J. Corso.
European Conference on Computer Vision (ECCV 2012). [ pdf, code ] (Oral Presentation)(* equal contribution).

Random forests for metric learning with implicit pairwise position dependence, C. Xiong , D. M. Johnson, R. Xu and J. J. Corso.
ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2012). [ pdf, code ](Oral Presentation)

Coaction discovery: Segmentation of common actions across multiple videos, C. Xiong , D. M. Johnson, R. Xu and J. J. Corso.
Multimedia Data Mining Workshop in Conjunction with the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (MDMKDD 2012). [ pdf, code ]

Dictionary transfer for image denoising via domain adaptation, G. Chen, C. Xiong and J. J. Corso.
IEEE International Conference on Image Processing (ICIP 2012). [ pdf ](Oral Presentation)

Efficient max-margin metric learning, C. Xiong, D. M. Johnson and J. J. Corso.
European Conference on Data Mining (ECDM 2012). [ pdf, code ](Best Paper Award)

Spectral active clustering via purification of the k-nearest neighbor graph, C. Xiong, D. M. Johnson and J. J. Corso.
European Conference on Data Mining (ECDM 2012). [ pdf, code ](Oral Presentations)

Online Active Constraint Selection For Semi-Supervised Clustering, C. Xiong, D. M. Johnson and J. J. Corso.
ECAI Active and Incremental Workshop, 2012. [ pdf, code ]

2011

AirTouch: Interacting With Computer Systems At A Distance., D. Schlegel, A. Y. C. Chen, C. Xiong, J. Delmerico and J. J. Corso.
IEEE Winter Vision Meetings: Workshop on Applications of Computer Vision (WACV 2011). [ pdf](Oral Presentations)

Towards a parts-based approach to sub-cortical brain structure parsing, D. Gagneja, C. Xiong and J. J. Corso.
SPIE Conference on Medical Imaging, 2011. [ pdf ]

2009

From image parsing to painterly rendering, K. Zeng, M. Zhao, C. Xiong and S. C. Zhu.
ACM Transaction on Graphics, 2009 (TOG). [ pdf ]

Marker-less registration based on template tracking for augmented reality, L. Lin, Y. Wang, Y. Liu, C. Xiong and K. Zeng.
Multimedia Tools Applications, 2009 (MTA). [ pdf ]

Manuscript Under Review

Awards

  • CVPR 2014 Young Researcher Travel Award
  • SDM 2014 Doctoral Forum
  • SIGKDD 2012 Student Travel Award
  • ECDM 2012 Best Paper Award

Professional Services

Conference and Workshop Organization

  • Organizing Committee, Workshop on language and vision (at CVPR 2015).
Journal and Conference Reviewer
  • TPAMI, IJCV, TIP, PR, Neurocomputing, ICCV 2015, ICRA 2015, CVPR 2016, ICRA 2016, AAAI 2016, NIPS 2016, AAAI 2017, CVPR 2017, ICLR 2017