Junwei Liang 's Website
Junwei Liang (Ph.D. Candidate)       梁俊卫
Language Technologies Institute
School of Computer Science
Carnegie Mellon University

Office: Gates and Hillman Centers 5513
Email: junweil at cs dot cmu dot edu (junweil@cs.cmu.edu)
Publications
Research
Honors
CV
Introduction
Greeting! I'm Junwei Liang, a Ph.D. candidate under the supervision of Prof. Alexander Hauptmann at Carnegie Mellon University.
My research focus is large-scale video analysis and retrieval.
I am also doing research in event reconstruction from unorganized social media videos.
My CV can be found here.
News
Research Experience
Honors and Awards
Selected Publications [Google Scholar]
  1. Focal Visual-Text Attention for Memex Question Answering [PDF, BibTex, Code/Model/Dataset]
    Junwei Liang, Lu Jiang, Liangliang Cao, Yannis Kalantidis, Li-Jia Li, and Alexander Hauptmann
    In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). (Journal Regular Paper)
  2. Focal Visual-Text Attention for Visual Question Answering [PDF, BibTex, Code/Model]
    Junwei Liang, Lu Jiang, Liangliang Cao, Li-Jia Li, and Alexander Hauptmann
    In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (Spotlight Paper)
  3. Leveraging Multi-modal Prior Knowledge for Large-scale Concept Learning in Noisy Web Data [PDF, BibTex]
    Junwei Liang, Lu Jiang, Deyu Meng, and Alexander Hauptmann
    In ACM International Conference on Multimedia Retrieval (ICMR), 2017.
  4. Webly-Supervised Learning of Multimodal Video Detectors [demo, PDF, BibTex, Poster ]
    Junwei Liang, Lu Jiang, and Alexander Hauptmann
    In AAAI Conference on Artificial Intelligence (AAAI), 2017.
  5. An Event Reconstruction Tool for Conflict Monitoring Using Social Media [demo, PDF, BibTex, Poster ]
    Junwei Liang, Desai Fan, Han Lu, Poyao Huang, Jia Chen, Lu Jiang, and Alexander Hauptmann
    In AAAI Conference on Artificial Intelligence (AAAI), 2017.
  6. Learning to detect concepts from webly-labeled video data [PDF, BibTex]
    Junwei Liang, Lu Jiang, Deyu Meng, and Alexander Hauptmann
    In International Joint Conference on Artificial Intelligence (IJCAI), 2016.
  7. Informedia@TRECVID 2016 [PDF, slides, BibTex]
    Junwei Liang, Jia Chen, Poyao Huang, Xuanchong Li, Lu Jiang, Zhenzhong Lan, Pingbo Pan, Hehe Fan,Qin Jin, Jiande Sun, Yang Chen, Yi Yang, Alexandar Hauptmann
    In NIST TRECVID Video Retrieval Evaluation Workshop, 2016.
  8. Temporal Localization of Audio Events for Conflict Monitoring in Social Media [PDF, BibTex, poster]
    Junwei Liang, Lu Jiang and Alexander Hauptmann
    In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2017.
  9. Synchronization for Multi-Perspective Videos in the Wild [PDF, BibTex, poster]
    Junwei Liang, Poyao Huang, Jia Chen and Alexander Hauptmann
    In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2017.
  10. Videos from the 2013 Boston Marathon: An Event Reconstruction Dataset for Synchronization and Localization [PDF, BibTex, dataset]
    Jia Chen, Junwei Liang, Han Lu, Shoou-I Yu and Alexander Hauptmann
    In CMU Center for Human Rights Technical Report, 2016.
  11. Video Description Generation using Audio and Visual Cues [PDF, BibTex]
    Qin Jin, and Junwei Liang
    In ACM International Conference on Multimedia Retrieval (ICMR), 2016.
  12. Detecting Semantic Concepts in Consumer Videos Using Audio [PDF, BibTex, poster]
    Junwei Liang, Qin Jin, Xixi He, Gang Yang, Jieping Xu, Xirong Li
    In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2015.
  13. RUC-Tencent at ImageCLEF 2015: Concept Detection, Localization and Sentence Generation [PDF, BibTex]
    Xirong Li, Qin Jin, Shuai Liao, Junwei Liang, Xixi He, Yu-Jia Huo, Weiyu Lan, Bin Xiao, Yanxiong Lu, Jieping Xu
    In CLEF Cross Language Image Retrieval Track (imageCLEF), 2015.
Educations
Selected Professional Activities
Informedia Lab, Carnegie Mellon University
School of Computer Science
Language Technologies Institute
Created by Junwei Liang. Last update 05/21/2017.