Tutorial #2 Action Spotting & Replay Grounding - 2022 SoccerNet Challenges - ft. Silvio Giancola

แชร์
ฝัง
  • เผยแพร่เมื่อ 17 พ.ย. 2024

ความคิดเห็น • 2

  • @abdelrahmanhelaly1808
    @abdelrahmanhelaly1808 ปีที่แล้ว

    In case of using GCN, it's not clear in the paper how would you handle the dynamic graph (Edges not being constant throughout the video chunk)

    • @ACADResearch
      @ACADResearch  ปีที่แล้ว

      Hi, great question! All graph convolution operations can be applied on any graph. After the graph convolution layers, we apply a global max pooling (see github.com/SoccerNet/sn-spotting/blob/main/Benchmarks/CALF_Calibration_GCN/src/model.py#L473) to aggregate the feature representation of each node into a single vector representation. This operation is independent on the number of nodes or edges and puts everything back to the same sized vector for the remaining of the network. I hope this helps.