profile picture

Fengmao Lv

Associate Professor

Education

Ph.D. in Computer Science

University of Electronic Science and Technology of China
2013 - 2018

B.E. in Computer Science

University of Electronic Science and Technology of China
2009 - 2013

About me

I am currently an Associate Professor at the School of Computing and Artificial Intelligence, Southwest Jiaotong University, China. My research interests are in multimodal deep learning, transfer learning and their applications in computer vision, natural language processing and social network analysis.

I have openings for self-motivated undergraduate students, master students and PhD students (co-supervised). Feel free to contact me if you are interested in my research area.

Research Interests

  • Multimodal Deep Learning: multimodal fusion, multimodal recognition
  • Transfer Learning: domain adaptation, zero-shot leaning, few-shot learning
  • Computer Vision: semantic segmentation, video understanding, medical imaging analysis
  • Natural Language Processing: sentiment analysis, aspect term extraction
  • Social Network Analysis: multimodal Twitter analysis, social network sentiment analysis

    • Selected Publications

  • Unified view imputation and feature selection learning for incomplete multi-view data
    • Yanyong Huang, Zongxin Shen, Tianrui Li, Fengmao Lv*
    International Joint Conference on Artificial Intelligence (IJCAI), 2024, accepted.
  • Transferring multi-modal domain knowledge to uni-modal domain for urban scene segmentation
    • Peng Liu, Yanqi Ge, Lixin Duan, Wen Li, Haonan Luo, Fengmao Lv*
    IEEE Transactions on Intelligent Transportation Systems, 2024, accepted.
  • Source-free domain adaptation with unrestricted source hypothesis
    • Jiujun He, Liang Wu, Chaofan Tao, Fengmao Lv*
    Pattern Recognition, 2024, accepted.
  • Semantic consistent embedding for domain adaptive zero-shot learning
    • Jianyang Zhang, Guowu Yang, Ping Hu, Guosheng Lin, Fengmao Lv*
    IEEE Transactions on Image Processing, 2023, accepted.
  • C2IMUFS: Complementary and consensus learning-based incomplete multi-view unsupervised feature selection
    • Yanyong Huang, Zongxin Shen, Yuxin Cai, Xiuwen Yi, Dongjie Wang, Fengmao Lv, Tianrui Li
    IEEE Transactions on Knowledge and Data Engineering, 2023, accepted.
  • Learning cross-domain semantic-visual relationships for transductive zero-shot learning
    • Fengmao Lv, Jianyang Zhang, Guowu Yang, Lei Feng, Yufeng Yu, Lixin Duan
    Pattern Recognition, 2023, accepted.
  • Self-training vision language BERTs with a unified conditional model
    • Xiaofeng yang, Fengmao Lv, Fayao Liu, Guosheng Lin
    IEEE Transactions on Circuits and Systems for Video Technology, 2023, accepted.
  • Curriculum knowledge distillation for emoji-supervised cross-lingual sentiment analysis
    • Jianyang Zhang, Tao Liang, Mingyang Wan, Guowu Yang, Fengmao Lv*
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022, accepted, oral paper.
  • Progressive multi-granularity information propagation for coupled aspect-opinion extraction
    • Fengmao Lv, Tao Liang, Zhihui Fei, Wenya Wang
    IEEE Transactions on Neural Networks and Learning Systems, 2022, accepted.
  • Partial label learning with semantic label representations
    • Shuo He, Lei Feng, Fengmao Lv, Wen Li, Guowu Yang
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022, accepted.
  • Expanding large pre-trained unimodal models with multimodal information injection for image-text multimodal classification
    • Tao Liang, Guosheng Lin, Mingyang Wan, Tianrui Li, Guojun Ma, Fengmao Lv*
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2022, accepted
  • Attention is not enough: mitigating the distribution discrepancy in asynchronous multimodal sequence fusion
    • Tao Liang, Guosheng Lin, Lei Feng, Yan Zhang, Fengmao Lv*
    IEEE International Conference on Computer Vision (ICCV), 2021, accepted.
  • Weakly-supervised domain adaptation for aspect term extraction via multi-level interaction transfer
    • Tao Liang, Wenya Wang, Fengmao Lv*
    IEEE Transactions on Neural Networks and Learning Systems, 2021, accepted.
  • Progressive modality reinforcement for human multimodal emotion recognition from unaligned multimodal sequences
    • Fengmao Lv, Xiang Chen, Yanyong Huang, Lixin Duan, Guosheng Lin
    IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2021, accepted.
  • Weakly-supervised cross-domain road scene segmentation via multi-level curriculum adaptation
    • Fengmao Lv, Guosheng Lin, Peng Liu, Guowu Yang, Sinno Jialin Pan, Lixin Duan
    IEEE Transactions on Circuits and Systems for Video Technology, 2021, accepted.
  • TRRNet: tiered relation reasoning for compositional visual question answering
    • Xiaofeng Yang, Guosheng Lin, Fengmao Lv, Fayao Liu
    Proceedings of the European Conference on Computer Vision (ECCV), 2020:414-430.
  • Can cross entropy loss be robust to label noise
    • Lei Feng, Senlin Shu, Zhuoyi Lin, Fengmao Lv, Li Li, Bo An
    Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2020:2206-2212.
  • Cross-domain semantic segmentation via domain-invariant interactive relation transfer
    • Fengmao Lv, Tao Liang, Xiang Chen, Guosheng Lin
    Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2020:4334-4343.
  • Constructing self-motivated pyramid curriculums for cross-domain semantic segmentation: a non-adversarial approach
    • Qing Lian, Fengmao Lv, Lixin Duan, Boqing Gong.
    Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019:6758-6767.

    Service

    Conference PC Member AAAI 2021, CVPR 2021, ICCV 2021, CIKM 2021, AAAI 2022, CVPR 2022, ECCV 2022, AAAI 2023.
    Journal Reviewer IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Transactions on Image Processing (TIP), IEEE Transactions on Neural Networks and Learning Systems (TNNLS), IEEE Transactions on Geoscience and Remote Sensing (TGRS), IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), IEEE Transactions on Instrumentation and Measurement (TIM), ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Pattern Recognition (PR), Computer Vision and Image Understanding (CVIU), Knowledge-Based Systems (KBS), Expert Systems With Applications (ESWA), Multimedia Tools and Applications (MTA), IET Computer Vision (IET-CVI), IET Intelligent Transport Systems (IET-ITS), Security and Communication Networks (SCN).

    Group

    Jianyang Zhang, Phd student (From Jul. 2019, co-advised from UESTC)
    Peng Liu, Phd student (From Sept. 2021, co-advised from UESTC)
    Enping Li, Phd student (From Apr. 2022)
    Tao Liang, Research assistant (From Apr. 2019)
    Xiang Chen, Research assistant (From Sept. 2019)
    Changru Nie, Master student (From Sept. 2022)
    Mengting Xiong, Master student (From Sept. 2022)
    Boyu Lu, Master student (From Sept. 2022)
    Junlin Fang, Undergraduate student (From Jan. 2022)
    Zhantao Cao, Phd student (From May. 2019 to Jun. 2020, co-advised from UESTC)
    Defu Liu, Phd student (From Sept. 2019 to Jun. 2022, co-advised from UESTC)
    Jiayi Zhao, Undergraduate student (From Oct. 2019 to Jun. 2020, graduated from SWUFE. Now - Master student @ Yale University, USA)
    Xinyu Zhang, Undergraduate student (From Oct. 2019 to Jun. 2021, graduated from SWUFE. Now - Master student @ Yale University, USA)