• mcl_POD
    • mcl_semi-supervised_vos
    • mcl_video_segmentation
    • mcl_videoObjectSegmentation
    • mcl_VideoStabilization
    • mcl_Featured
    • feature_ImageQualityAssessment
    • PPT
    • Featured
    • Featured
    • Featured_bcce
    • dehazing_featured_


    [2017] Our object discovery technique will be published in TIP.

    Yeong Jun Koh and Chang-Su Kim, “Unsupervised primary object discovery in videos based on evolutionary primary object modeling with reliable object proposals,” to appear in IEEE Tran...

    [2017] Our techniques for semantic line detection, superpixels, and joint tracking and segmentation will be presented in ICCV 2017.

    [2017] Our first AVSS paper



    [Weekly] Deformable Convolutional Networks

    Presenter : Mingyeok Heo Date : 23, Sep. Seminar Room : Engineering Building 164(a.m 10:00~) Paper : Deformable Convolutional Networks [arXiv 2017]

    [Weekly] Fully Convolutional Instance-aware Semantic Segmentation

    [Weekly] FC^4: Fully Convolutional Color Constancy with Confidence-weighted Pooling