Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

HOTA and IDF1 metric results on MOT17 (left) and MOT20 (right) test sets.

More »

Fig 1 Expand

Fig 2.

Overview of the proposed model architecture.

More »

Fig 2 Expand

Fig 3.

Each row shows one sequence: the object before occlusion, during occlusion, and after reappearing with the same ID.

More »

Fig 3 Expand

Table 1.

Ablation results for individual components on the MOT17 public validation split.

More »

Table 1 Expand

Table 2.

Individual Component Ablation on MOT20 (Validation Split).

More »

Table 2 Expand

Fig 4.

Ablation study: individual component performance on the MOT17 validation set.

More »

Fig 4 Expand

Fig 5.

Ablation study: individual component performance on the MOT20 validation set.

More »

Fig 5 Expand

Table 3.

Cumulative component ablation on MOT17 (Public Validation Split).

More »

Table 3 Expand

Fig 6.

Ablation study: cumulative component performance on the MOT17 validation set.

More »

Fig 6 Expand

Table 4.

Cumulative component ablation on MOT20 (Validation Split).

More »

Table 4 Expand

Fig 7.

Ablation study: cumulative component performance on the MOT20 validation set.

More »

Fig 7 Expand

Table 5.

Comparison of state-of-the-art methods on MOT17 and MOT20 benchmarks.

More »

Table 5 Expand