profile photo

Daqing LIU  

Ph.D. Candidate

School of Information Science and Technology
University of Science and Technology of China
Hefei, Anhui, 230026, P.R. China

Email  /  CV  /  Google Scholar  /  GitHub

Bio

I'm a fourth-year Ph.D. candidate at University of Science and Technology of China, supervised by Prof. Zheng-Jun Zha. From May 2018 to May 2019, I was a visiting student at Nanyang Technological University, working with Asst. Prof. Hanwang Zhang. I received my B.Eng. degree in Automation from Chang'an University in 2016.

My primary research interests are Computer Vision and Machine Reasoning. Specifically, my current research focuses on vision and language, e.g., image/video captioning, visual grounding, visual/video question answering, and vision-and-language navigation.

I am seeking an (industry) research job on computer vision. Feel free to drop me an email!

News

  • [07/2020]   Our RMN paper for video captioning is accessable at IJCAI. Code is released.
  • [04/2020]   1 paper accepted to IJCAI 2020.
  • [03/2020]   1 collaborative paper accepted to CVPR 2020.
  • [07/2019]   1 paper accepted to ICCV 2019 (Oral).
  • [04/2019]   2 papers accepted to T-PAMI 2019.
  • Publications
    Learning to Discretely Compose Reasoning Module Networks for Video Captioning

    Ganchao Tan*, Daqing Liu*, Meng Wang, Zheng-Jun Zha
    *Equal Contribution
    International Joint Conference on Artificial Intelligence (IJCAI), 2020
    ijcai / arXiv / code / bibtex

    We propose a discrete reasoning module selection strategy with three spatio-temporal reasoning modules for video captioning.

    More Grounded Image Captioning by Distilling Image-Text Matching Model

    Yuanen Zhou, Meng Wang, Daqing Liu, Zhenzhen Hu, Hanwang Zhang
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2020
    cvf / arxiv / code / bibtex

    Distilling the image-text matching model could enhance both the performance and transparency of existing captioning models.

    Joint Visual Grounding with Language Scene Graphs

    Daqing Liu, Hanwang Zhang, Zheng-Jun Zha, Meng Wang, Qianru Sun
    arXiv preprint, arXiv:1906.03561, 2019
    arxiv / bibtex

    We enable the joint visual grounding by performing marginalization over the language scene graph.

    Learning to Assemble Neural Module Tree Networks for Visual Grounding

    Daqing Liu, Hanwang Zhang, Zheng-Jun Zha, Feng Wu
    IEEE International Conference on Computer Vision (ICCV), 2019   (Oral Presentation)
    cvf / arxiv / code / talk / bibtex

    By reasoning along the dependency parsing tree, we perform a fine-grained and explainable visual grounding with superior performance.

    Context-Aware Visual Policy Network for Fine-Grained Image Captioning

    Zheng-Jun Zha, Daqing Liu, Hanwang Zhang, Yongdong Zhang, Feng Wu
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2019
    ieee / arxiv / code / bibtex

    The extended version of this paper, with additional experiments on image paragraph captioning.

    Learning to Compose and Reason with Language Tree Structures for Visual Grounding

    Richang Hong, Daqing Liu, Xiaoyu Mo, Xiangnan He, Hanwang Zhang,
    IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2019
    ieee / arxiv / bibtex

    We propose to recursively accumulate grounding confidence along the dynamically composed tree for visual grounding.

    Context-Aware Visual Policy Network for Sequence-Level Image Captioning

    Daqing Liu, Zheng-Jun Zha, Hanwang Zhang, Yongdong Zhang, Feng Wu
    ACM Conference on Multimedia (MM), 2018   (Oral Presentation)
    acm / arxiv / code / bibtex

    We perform compositional visual reasoning for image captioning by explicitly considering the previous visual attentions as visual context.

    Selected Honors

  • Scholarship Award from Huawei Technologies Co., Ltd., 2019
  • Scholarship Award from the China Aerospace and Technology Corporation, 2018
  • National Second Prize of the 14th "Challenge Cup", 2015
  • Pivot of Merit Student of Chang'an University, 2014
  • Winning Prize of the 9th "Freescale Cup" National University Intelligent Car Competition, 2014
  • Services

  • Invited Reviewer for IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • Invited Reviewer for Neurocomputing
  • Invited Reviewer for IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • Invited Reviewer for IEEE Transactions on Multimedia (TMM)

  • Last update: July 18, 2020. Website template from here.