图共 6个 表共 2
    • 图  1  区域时空二合一网络结构图

      Figure 1.  Region spatiotemporal two-in-one network structure

    • 图  2  区域时空二合一模块结构

      Figure 2.  Region spatiotemporal two-in-one module structure

    • 图  3  标记筛选器原理图

      Figure 3.  Schematic diagram of mark selector

    • 图  4  “滑雪”动作数据集示例

      Figure 4.  Example of action Skiing in dataset

    • 图  5  区域时空二合一模块前后特征图可视化结果示例

      Figure 5.  Example of visualization of the region spatiotemporal two-in-one module

    • 图  6  区域时空二合一网络对于UCF-24数据集中部分示例检测结果

      Figure 6.  Detection results of proposed network for ucf-24 dataset

    • Classframe_AP/%$ \Delta $(diff)
      SSDThis paper
      Basketball28.9132.373.46
      Basketball_dunk49.9049.61-0.29
      Biking78.3678.27-0.09
      Cliff_diving50.1957.957.76
      Crick_bowling27.6831.443.76
      Diving78.9780.701.73
      Fencing87.9588.160.21
      Floor_gymnastics83.3885.442.06
      Golf_swing43.4444.831.39
      Horse_riding88.5788.41-0.16
      Ice_dancing71.6172.400.79
      Long_jump56.7759.442.67
      Pole_vault55.0456.721.68
      Rope-climbing81.3682.120.76
      Salsa_spin69.2669.01-0.25
      Skate_boarding68.6371.713.08
      Skiing68.0977.739.64
      Skijet84.4487.453.01
      Soccer_juggling79.9780.140.17
      Surfing82.8886.503.62
      Tennis_swing37.2637.18-0.08
      Trampoline_jumping60.6360.54-0.09
      Volleyball_spiking35.5136.500.99
      Walking_with_dog74.2674.440.18
      frame_mAP64.2966.211.92

      表 1  UCF101-24数据集中各类别在IoU阈值为0.5时的frame_AP(%)对比结果

      Table 1.  Comparison of frame_AP of UCF101-24 at IOU threshold of 0.5

    • Algorithmvideo_mAP/%
      0.200.500.750.50:0.95
      Literature [9]71.8035.901.608.80
      Literature[10]69.840.915.518.7
      Literature [15]66.7035.907.9014.40
      Literature [16]73.537.8--
      Literature [17]71.5340.0713.9117.90
      Literature [18]56.736.6--
      Literature [19]72.941.4--
      This paper74.2243.1714.8219.05

      表 2  动作检测算法在UCF101-24数据集上的video_mAP结果对比

      Table 2.  Comparison of video_mAP on UCF101-24