{
  "input_shape": [
    1,
    3,
    16,
    224,
    224
  ],
  "detect_threshold": 0.97,
  "consec": 3,
  "target_fps": 16,
  "window_frames": 16,
  "stride": 3,
  "tolerance_s": 1.0,
  "mean": [
    0.485,
    0.456,
    0.406
  ],
  "std": [
    0.229,
    0.224,
    0.225
  ],
  "arch": "videomae_base"
}