Deformable Convolutional Detection

Deformable Convolutional Detection is a detection framework in object detection that extends standard convolutional networks by integrating deformable convolutional layers, which enable adaptive sampling of feature maps through learnable offsets, thereby improving the modeling of geometric transformations and object deformations.

69

Publications

4.1K

Citations

321

Authors

123

Institutions

Publications per year

2017–2026

64

Authors

321

  1. CC
    Chen Change Loy

    Nanyang Technological University, Singapore

    4 publications · 834 citations

    4

    h-index

  2. YT
    Yonglong Tian

    Massachusetts Institute of Technology, United States

    4 publications · 834 citations

    4

    h-index

  3. SQ
    Shi Qiu

    Chinese University of Hong Kong, Hong Kong SAR China

    4 publications · 834 citations

    4

    h-index

  4. XW
    Xiaogang Wang

    European Organization for Nuclear Research, Switzerland

    4 publications · 834 citations

    4

    h-index

  5. XT
    Xiaoou Tang

    Chinese University of Hong Kong, Hong Kong SAR China

    4 publications · 834 citations

    4

    h-index

1–5 of 321

Venues

  1. IEEE Access

    7 publications · 305 citations

    7

    h-index

  2. Remote Sensing

    9 publications · 412 citations

    7

    h-index

  3. arXiv (Cornell University)

    Repository · 3 publications · 242 citations

    3

    h-index

  4. Sensors

    2 publications · 82 citations

    2

    h-index

  5. Agriculture

    2 publications · 47 citations

    2

    h-index

1–5