IIPA-Net: Joint Illumination-Invariant and Pose-Aligned Feature Learning for Person Reidentification

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/js/volume-2022/3852243/figures/3852243.fig.005a.svgz" name="3852243.fig.005a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Low-light Duke</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/js/volume-2022/3852243/figures/3852243.fig.005b.svgz" name="3852243.fig.005b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Low-light Market</td></tr></table>

<div>Examples of synthetic low-light image.</div>

Journal of Sensors

fig5

Figure 5

Figure 5: IIPA-Net: Joint Illumination-Invariant and Pose-Aligned Feature Learning for Person Reidentification 