Multiple Traffic Target Tracking with Spatial-Temporal Affinity Network

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left">Method</td><td class="align_center">FP↓ (%)</td><td class="align_center">FN↓ (%)</td><td class="align_center">MOTA↑ (%)</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">P1-tracker</td><td class="align_center">7.9</td><td class="align_center">9.4</td><td class="align_center">84.3</td></tr><tr><td class="align_left">P2-tracker</td><td class="align_center">6.4</td><td class="align_center">7.1</td><td class="align_center">86.5</td></tr><tr><td class="align_left">Ours</td><td class="align_center">5.2</td><td class="align_center">5.9</td><td class="align_center">88.4</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Different input queries for spatial transformer decoder model on KITTI validation set.</div>

Computational Intelligence and Neuroscience

tab2

Table 2

Table 2: Multiple Traffic Target Tracking with Spatial-Temporal Affinity Network 