Research

Guosheng Lin's homepage


Research

Conference publications (selected)

  • Hao Wang, Guosheng Lin, Steven Hoi, Chunyan Miao;
    Structure-Aware Generation Network for Recipe Generation from Images;
    European Conference on Computer Vision (ECCV) 2020;

  • Tianyi Zhang, Guosheng Lin, Weide Liu, Jianfei Cai, Alex Kot;
    Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation;
    European Conference on Computer Vision (ECCV) 2020;

  • Xiaofeng Yang, Guosheng Lin, Fengmao Lv, Fayao Liu;
    TRRNet: Tiered Relation Reasoning for Compositional Visual Question Answering;
    European Conference on Computer Vision (ECCV) 2020;

  • Lichang Chen, Guosheng Lin, Shijie Wang, Qingyao Wu;
    Graph Edit Distance Reward: Learning to Edit Scene Graph;
    European Conference on Computer Vision (ECCV) 2020;

  • Yukun Su, Guosheng Lin, Jinhui Zhu, Qingyao Wu;
    Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition;
    European Conference on Computer Vision (ECCV) 2020;

  • Weide Liu, Chi Zhang, Guosheng Lin, Tzu-Yi HUNG, Chunyan Miao;
    Weakly Supervised Segmentation with Maximum Bipartite Graph Matching;
    ACM International Conference on Multimedia (ACM MM) 2020;

  • Jiacheng Wei, Guosheng Lin, Kim-Hui Yap, Tzu-Yi HUNG, Lihua Xie;
    Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020;

  • Hanyu Shi, Guosheng Lin, Hao Wang, Tzu-Yi HUNG, Zhenhua Wang;
    SpSequenceNet: Semantic Segmentation Network on 4D Point Clouds;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020;

  • Chi Zhang, Yujun Cai, Guosheng Lin, Chunhua Shen;
    DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover’s Distance and Structured Classifiers;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020;

  • Weide Liu, Chi Zhang, Guosheng Lin, Fayao Liu;
    CRNet: Cross-Reference Networks for Few-Shot Segmentation;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020;

  • Fengmao Lv, Tao Liang, Xiang Chen, Guosheng Lin;
    Cross-domain semantic segmentation via domain-invariant interactive relation transfer;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020;

  • Zhonghua Wu, Qingyi Tao, Guosheng Lin, Jianfei Cai;
    Exploring Bottom-up and Top-down Cues with Attentive Learning for Webly Supervised Object Detection;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020;

  • Chi Zhang, Guosheng Lin, Fayao Liu, Jiushuang Guo, Qingyao Wu, Rui Yao;
    Pyramid Graph Networks with Connection Attentions for Region-Based One-Shot Semantic Segmentation;
    International Conference on Computer Vision (ICCV), 2019;

  • Haonan Luo, Guosheng Lin, Zichuan Liu, Fayao Liu, Zhenmin Tang, Yazhou Yao;
    SegEQA: Video Segmentation based Visual Attention for Embodied Question Answering;
    International Conference on Computer Vision (ICCV), 2019;

  • Zhonghua Wu, Guosheng Lin, Qingyi Tao, Jianfei Cai;
    M2E-Try On Net: Fashion from Model to Everyone;
    ACM Multimedia (ACMMM) 2019;

  • Chi Zhang, Guosheng Lin, Fayao Liu, Rui Yao, Chunhua Shen;
    CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019;

  • Zichuan Liu, Guosheng Lin, Sheng Yang, Fayao Liu, Weisi Lin, Wang Ling Goh;
    Towards Robust Curve Text Detection with Conditional Spatial Expansion;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2019;

  • Linshan Jiang, Rui Tan, Xin Lou, Guosheng Lin;
    On Lightweight Privacy-Preserving Collaborative Learning for Internet-of-Things Objects;
    The 4th ACM/IEEE International Conference on Internet of Things Design and Implementation (IoTDI) 2019;

  • Fengmao Lv, Qing Lian, Guowu Yang, Guosheng Lin, Sinno Jialin Pan and Lixin Duan;
    Domain Adaptive Semantic Segmentation through Structure Enhancement.
    ECCV18 Workshop on Transferring Knowledge and Adapting Source Knowledge in Computer Vision and VisDA Challenge 2018.

  • Tong Shen, Guosheng Lin, Chunhua Shen, Ian Reid;
    Bootstrapping the Performance of Webly Supervised Semantic Segmentation;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018;
    Code: https://github.com/ascust/BDWSS

  • Zichuan Liu, Guosheng Lin, Sheng Yang, Jiashi Feng, Weisi Lin, Wangling Goh;
    Learning Markov Clustering Networks for Scene Text Detection;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018;

  • Huaxin Xiao, Jiashi Feng, Guosheng Lin, Yu Liu, Maojun Zhang;
    MoNet: Deep Motion Exploitation for Video Object Segmentation
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018;

  • Anton Milan, et al;
    Semantic segmentation from limited training data;
    IEEE International Conference on Robotics and Automation (ICRA), 2018;
    Winning solution based on our RefineNet for Amazon Robotics Challenge (ARC) 2017

  • Guosheng Lin, Anton Milan, Chunhua Shen, Ian Reid;
    RefineNet: MultiPath Refinement Networks for HighResolution Semantic Segmentation;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017;
    Top performance on PASCAL VOC 2012 dataset.
    Our source code and trained models are available at:
    https://github.com/guosheng/refinenet
    (MATLAB based framework for semantic segmentation and dense preidction)

  • Yao Li, Guosheng Lin, Bohan Zhuang, Lingqiao Liu, Chunhua Shen, Anton van den Hengel;
    Sequential Person Recognition in Photo Albums with a Recurrent Network;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017;

  • Tong Shen, Guosheng Lin, Lingqiao Liu, Chunhua Shen, Ian Reid;
    Weakly Supervised Semantic Segmentation Based on Cosegmentation;
    The British Machine Vision Conference (BMVC) 2017;

  • Tong Shen*, Guosheng Lin*, Chunhua Shen, Ian Reid;
    ( * indicates equal contribution )
    Learning Multilevel Region Consistency with Dense Multilabel Networks for Semantic Segmentation;
    International Joint Conference on Artificial Intelligence (IJCAI) 2017;

  • Guosheng Lin, Chunhua Shen, Anton van den Hengel, Ian Reid; Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, Spotlight presentation;

  • Bohan Zhuang, Guosheng Lin, Chunhua Shen, Ian Reid;
    Fast training of tripletbased deep binary embedding networks;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016;

  • Guosheng Lin, Chunhua Shen, Ian Reid, Anton van den Hengel;
    Deeply Learning the Messages in Message Passing Inference;
    Advances in Neural Information Processing Systems (NIPS), 2015,

  • Fayao Liu, Chunhua Shen, Guosheng Lin;
    Deep Convolutional Neural Fields for Depth Estimation from a Single Image;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015;
    Code: https://bitbucket.org/fayao/dcnffcsp/

  • Michael Milford, Chunhua Shen, Stephanie Lowry, Niko Suenderhauf, Sareh Shirazi, Guosheng Lin, Fayao Liu, Edward Pepperell, Cesar Lerma, Ben Upcroft, Ian Reid;
    Sequence Searching With DeepLearnt Depth for Condition and ViewpointInvariant RouteBased Place Recognition;
    The 6th international Workshop on Computer Vision in Vehicle Technology, CVPR2015 workshop.

  • Guosheng Lin, Chunhua Shen, Qinfeng Shi, Anton van den Hengel and David Suter;
    Fast Supervised Hashing with Decision Trees for HighDimensional Data;
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014;
    Code: https://bitbucket.org/chhshen/fasthash/

  • Guosheng Lin, Chunhua Shen, Jianxin Wu;
    Optimizing Ranking Measures For Compact Binary Code Learning;
    European Conference on Computer Vision (ECCV), 2014;
    Code: https://bitbucket.org/guosheng/structhash
    Extensions of this method for efficient training are also included.

  • Guosheng Lin, Chunhua Shen, David Suter and Anton van den Hengel;
    A General TwoStep Approach to LearningBased Hashing;
    International Conference on Computer Vision (ICCV), 2013;
    Code: https://bitbucket.org/guosheng/twostephashing

  • Xi Li*, Guosheng Lin*, Chunhua Shen, Anton van den Hengel and Anthony Dick;
    ( * indicates equal contribution );
    Learning Hash Functions Using Column Generation;
    International Conference on Machine Learning (ICML), 2013; Oral Presentation;
    Code: https://bitbucket.org/guosheng/columngenerationhashing/

  • Guosheng Lin, Chunhua Shen and Anton van den Hengel;
    Approximate Constraint Generation for Efficient Structured Boosting;
    International Conference on Image Processing (ICIP), 2013;

  • Guosheng Lin, Chunhua Shen, Anton van den Hengel and David Suter;
    Fast Training of Effective Multiclass Boosting Using Coordinate Descent Optimization;
    Asian Conference on Computer Vision (ACCV), 2012;
    Code: https://bitbucket.org/guosheng/fastmultiboostcw

Journal publications

  • Hao Chen, Youfu Li, Yongjian Deng, Guosheng Lin;
    CNN-based RGB-D Salient Object Detection: Learn, Select, and Fuse;
    International Journal of Computer Vision (IJCV); 2021;

  • Zichuan Liu, Guosheng Lin*, Wang Ling Goh;
    Bottom-Up Scene Text Detection with Markov Clustering Networks;
    International Journal of Computer Vision (IJCV); 2020;

  • Guosheng Lin, Fayao Liu, Anton Milan, Chunhua Shen, Ian Reid;
    RefineNet: Multi-Path Refinement Networks for Dense Prediction;
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019;
    Code: https://github.com/guosheng/refinenet

  • Guosheng Lin, Chunhua Shen, Anton van den Hengel, Ian Reid;
    Exploring Context with Deep Structured models for Semantic Segmentation;
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018;

  • Guosheng Lin, Fayao Liu, Chunhua Shen, Jianxin Wu, Heng Tao Shen;
    Structured Learning of Binary Codes with Column Generation for Optimizing Ranking Measures;
    International Journal of Computer Vision (IJCV); 2017;
    Code: https://bitbucket.org/guosheng/structhash

  • Fayao Liu, Chunhua Shen, Guosheng Lin, Ian Reid;
    Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields;
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI); 2016;
    Code: https://bitbucket.org/fayao/dcnffcsp/

  • Guosheng Lin, Chunhua Shen, Anton van den Hengel;
    Supervised Hashing Using Graph Cuts and Boosted Decision Trees;
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015;
    Code: https://bitbucket.org/chhshen/fasthash/

  • Chunhua Shen, Guosheng Lin, Anton van den Hengel;
    StructBoost: Boosting Methods For Predicting Structured Output Variables;
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014;
    The following code provides the implementation of cutting-plane and an example of column generation:
    https://bitbucket.org/guosheng/structhash


  • Xiaoqian Ruan, Guosheng Lin, Cheng Long, Shengli Lu;
    Few-Shot Fine-Grained Classification with Spatial Attentive Comparison;
    Knowledge-Based Systems, 2021;

  • Pengshuai Yin, Jiayong Ye, Guoshen Lin, Qingyao Wu;
    Graph neural network for 6D object pose estimation;
    Knowledge-Based Systems, 2021;

  • Fengmao Lv, Guosheng Lin, Peng Liu, Guowu Yang, Sinno Jialin Pan, Lixin Duan;
    Weakly-supervised Cross-domain Road Scene Segmentation via Multi-level Curriculum Adaptation
    IEEE Transactions on Circuits and Systems for Video Technology, 2020;

  • Linshan Jiang, Rui Tan, Xin Lou, Guosheng Lin;
    On Lightweight Privacy-Preserving Collaborative Learning for Internet of Things by Independent Random Projections;
    ACM Transactions on Internet of Things, 2020;

  • Ruibing Jin, Guosheng Lin, Changyun Wen, Jianliang Wang;
    Motion Context Network for Weakly Supervised Object Detection in Videos;
    IEEE Signal Processing Letters, 2020;

  • Hao Chen, Yongjian Deng, Youfu Li, Tzu-Yi Hung, Guosheng Lin;
    RGBD Salient Object Detection via Disentangled Cross-modal Fusion;
    IEEE Transactions on Image Processing (TIP), 2020;

  • Hanrui Wu, Yuguang Yan, Guosheng Lin, Min Yang, Michael Kwok-Po Ng, Qingyao Wu;
    Iterative Refinement for Multi-source Visual Domain Adaptation;
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 2020;

  • Weide Liu, Guosheng Lin, Tianyi Zhang, Zichuan Liu;
    Guided Co-Segmentation Network for Fast Video Object Segmentation;
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020;

  • Video Object Segmentation and Tracking: A Survey;
    Rui Yao, Guosheng Lin, Shixiong Xia, Jiaqi Zhao, Yong Zhou;
    Transactions on Intelligent Systems and Technology, 2020;

  • A Dilated Inception Network for Visual Saliency Prediction;
    Sheng Yang, Guosheng Lin, Qiuping Jiang, Weisi Lin;
    IEEE Transactions on Multimedia (TMM), 2019;

  • Tianyi Zhang, Guosheng Lin*, Jianfei Cai, Tong Shen, Chunhua Shen, Alex C Kot;
    Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation;
    IEEE Transactions on Multimedia (TMM), 2019;

  • Zhonghua Wu, Guosheng Lin*, Jianfei Cai;
    Keypoint Based Weakly Supervised Human Parsing;
    Image and Vision Computing (IVC), 2019;

  • Feixiang He, Fayao Liu, Rui Yao, Guosheng Lin*;
    Local Fusion Networks with Chained Residual Pooling for Video Action Recognition;
    Image and Vision Computing (IVC), 2019;

  • Rui Yao, Guosheng Lin*, Chunhua Shen, Yanning Zhang, Qinfeng Shi;
    SemanticsAware Visual Object Tracking;
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2018;

  • Rui Yao, Guosheng Lin, Qinfeng Shi, DC Ranasinghe;
    Efficient Dense Labelling of Human Activity Sequences from Wearables using Fully Convolutional Networks;
    Pattern Recognition (PR), 2018; ;

  • Fayao Liu, Guosheng Lin*, Chunhua Shen;
    Discriminative Training of Deep Fullyconnected Continuous CRF with Taskspecific Loss;
    IEEE Transactions on Image Processing (TIP), 2017;

  • Fayao Liu, Guosheng Lin*, Ruizhi Qiao, Chunhua Shen;
    Structured Learning of Tree Potentials in CRF for Image Segmentation;
    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2017;

  • Biyun Sheng, Chunhua Shen, Guosheng Lin, Jun Li, Wankou Yang, Changyin Sun;
    Crowd Counting via Weighted VLAD on Dense Attribute Feature Maps;
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT); 2016;

  • Fayao Liu, Guosheng Lin, Chunhua Shen;
    CRF Learning with CNN Features for Image Segmentation;
    Pattern Recognition (PR), 2015;

Released research code:

Preprints:

  • Zichuan Liu, Guosheng Lin*, Wang Ling Goh, Fayao Liu, Chunhua Shen, Xiaokang Yang;
    Correlation Propagation Networks for Scene Text Detection; 2018;