| Natural boxes: natural-trained grounders | Activated dynamic sigmoid | YOLO IoU | 0.4741 | 0.4695 +/- 0.0074 | -0.0045 | [-0.0176, 0.0088] | -0.0081898868;0.0057299137;-0.011174262 |
| Natural boxes: natural-trained grounders | Activated dynamic sigmoid | Detection rate | 0.9900 | 0.9867 +/- 0.0021 | -0.0033 | [-0.0103, 0.0037] | -0.00099998713;-0.003000021;-0.0059999824 |
| Natural boxes: natural-trained grounders | Activated dynamic sigmoid | ResNet target-class accuracy | 0.9530 | 0.9587 +/- 0.0048 | 0.0057 | [-0.0077, 0.0193] | 0.0080000162;-0.00099998713;0.0099999905 |
| Natural boxes: natural-trained grounders | Activated pinned sigmoid | YOLO IoU | 0.4687 | 0.4876 +/- 0.0108 | 0.0189 | [0.0045, 0.0336] | 0.031520605;0.0050692558;0.020117402 |
| Natural boxes: natural-trained grounders | Activated pinned sigmoid | Detection rate | 0.9880 | 0.9857 +/- 0.0041 | -0.0023 | [-0.0097, 0.0057] | -0.0029999614;-0.0069999695;0.003000021 |
| Natural boxes: natural-trained grounders | Activated pinned sigmoid | ResNet target-class accuracy | 0.9550 | 0.9537 +/- 0.0050 | -0.0013 | [-0.0143, 0.0120] | 0.0040000081;0;-0.0079999566 |
| Natural boxes: natural-trained grounders | Raw pinned sigmoid + CE | YOLO IoU | 0.4664 | 0.4855 +/- 0.0059 | 0.0191 | [0.0047, 0.0336] | 0.021548361;0.024865419;0.01102829 |
| Natural boxes: natural-trained grounders | Raw pinned sigmoid + CE | Detection rate | 0.9850 | 0.9813 +/- 0.0068 | -0.0037 | [-0.0120, 0.0050] | -0.00099998713;-0.013000011;0.0029999614 |
| Natural boxes: natural-trained grounders | Raw pinned sigmoid + CE | ResNet target-class accuracy | 0.9410 | 0.9277 +/- 0.0160 | -0.0133 | [-0.0277, 0.0017] | -0.014999986;0.0070000291;-0.032000005 |
| Traversal boxes: natural-trained grounders | Activated dynamic sigmoid | YOLO IoU | 0.4600 | 0.4589 +/- 0.0009 | -0.0011 | [-0.0057, 0.0033] | 8.2135201e-05;-0.0012937784;-0.0022078156 |
| Traversal boxes: natural-trained grounders | Activated dynamic sigmoid | Detection rate | 0.9847 | 0.9822 +/- 0.0007 | -0.0025 | [-0.0051, 0.0001] | -0.0017999411;-0.0034999847;-0.0021999478 |
| Traversal boxes: natural-trained grounders | Activated dynamic sigmoid | ResNet target-class accuracy | 0.9525 | 0.9576 +/- 0.0014 | 0.0051 | [0.0006, 0.0097] | 0.0039000511;0.0042000413;0.0070999861 |
| Traversal boxes: natural-trained grounders | Activated pinned sigmoid | YOLO IoU | 0.4605 | 0.4762 +/- 0.0041 | 0.0157 | [0.0104, 0.0211] | 0.018555701;0.0099299252;0.018529534 |
| Traversal boxes: natural-trained grounders | Activated pinned sigmoid | Detection rate | 0.9823 | 0.9783 +/- 0.0005 | -0.0040 | [-0.0071, -0.0009] | -0.0032999516;-0.0041999221;-0.0043998957 |
| Traversal boxes: natural-trained grounders | Activated pinned sigmoid | ResNet target-class accuracy | 0.9505 | 0.9516 +/- 0.0012 | 0.0011 | [-0.0049, 0.0071] | 0.0019999743;-0.00050002337;0.0019000173 |
| Traversal boxes: natural-trained grounders | Raw pinned sigmoid + CE | YOLO IoU | 0.4598 | 0.4812 +/- 0.0076 | 0.0213 | [0.0162, 0.0264] | 0.028934926;0.0240556;0.010950446 |
| Traversal boxes: natural-trained grounders | Raw pinned sigmoid + CE | Detection rate | 0.9843 | 0.9777 +/- 0.0032 | -0.0066 | [-0.0097, -0.0037] | -0.0049999952;-0.011099994;-0.0038000345 |
| Traversal boxes: natural-trained grounders | Raw pinned sigmoid + CE | ResNet target-class accuracy | 0.9498 | 0.9297 +/- 0.0174 | -0.0201 | [-0.0261, -0.0140] | -0.010999978;-0.004799962;-0.044399977 |
| Traversal boxes: traversal-trained grounders | Activated dynamic sigmoid | YOLO IoU | 0.4602 | 0.4600 +/- 0.0014 | -0.0001 | [-0.0046, 0.0042] | 0.00084516406;-0.0021348894;0.0008880496 |
| Traversal boxes: traversal-trained grounders | Activated dynamic sigmoid | Detection rate | 0.9848 | 0.9819 +/- 0.0005 | -0.0029 | [-0.0056, -0.0002] | -0.0035000443;-0.0022999644;-0.0028999448 |
| Traversal boxes: traversal-trained grounders | Activated dynamic sigmoid | ResNet target-class accuracy | 0.9516 | 0.9544 +/- 0.0025 | 0.0028 | [-0.0015, 0.0071] | 0;0.0024000406;0.006000042 |
| Traversal boxes: traversal-trained grounders | Activated pinned sigmoid | YOLO IoU | 0.4566 | 0.4757 +/- 0.0032 | 0.0191 | [0.0137, 0.0243] | 0.023628682;0.016345978;0.017363757 |
| Traversal boxes: traversal-trained grounders | Activated pinned sigmoid | Detection rate | 0.9848 | 0.9762 +/- 0.0018 | -0.0086 | [-0.0121, -0.0052] | -0.010500014;-0.0091000199;-0.0062000155 |
| Traversal boxes: traversal-trained grounders | Activated pinned sigmoid | ResNet target-class accuracy | 0.9517 | 0.9499 +/- 0.0006 | -0.0018 | [-0.0084, 0.0049] | -0.0021999478;-0.00099998713;-0.0021998882 |
| Traversal boxes: traversal-trained grounders | Raw pinned sigmoid + CE | YOLO IoU | 0.4615 | 0.4778 +/- 0.0083 | 0.0164 | [0.0113, 0.0215] | 0.0048620999;0.023947775;0.02025792 |
| Traversal boxes: traversal-trained grounders | Raw pinned sigmoid + CE | Detection rate | 0.9833 | 0.9793 +/- 0.0010 | -0.0040 | [-0.0068, -0.0012] | -0.002599895;-0.0046999454;-0.0046999454 |
| Traversal boxes: traversal-trained grounders | Raw pinned sigmoid + CE | ResNet target-class accuracy | 0.9554 | 0.9461 +/- 0.0054 | -0.0093 | [-0.0145, -0.0042] | -0.003000021;-0.016300082;-0.0087000728 |