Obtaining Cross Modal Similarity Metric with Deep Neural Architecture

<div>The effect of hyperparameter <svg height="6.20645pt" id="M125" style="vertical-align:-0.2063999pt" version="1.1" viewbox="-0.0498162 -6.00005 7.69399 6.20645" width="7.69399pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M558 106L533 129C501 84 476 67 464 67C446 67 435 116 414 239C457 297 508 367 550 440L539 451L484 438C458 390 429 338 404 300H402C375 407 351 451 285 451C168 451 24 312 24 153C24 56 66 -12 132 -12C206 -12 284 64 345 156H347C367 24 386 -12 422 -12C457 -12 503 7 558 106ZM338 206C272 99 215 56 173 56C140 56 116 96 116 170C116 303 194 405 255 405C304 405 324 299 338 206Z" id="g50-223"></path><glyph.data ascent="3443" descent="-2856" horiz-adv-x="582" vert-adv-y="582"></glyph.data></g></svg> on our system.</div>

Mathematical Problems in Engineering

fig6

Figure 6

Figure 6: Obtaining Cross Modal Similarity Metric with Deep Neural Architecture 