The Multidimensional Motion Features of Spatial Depth Feature Maps: An Effective Motion Information Representation Method for Video-Based Action Recognition

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_center" colspan="2">UCF11</td></tr><tr class="thead"><td class="align_left">Method</td><td class="align_center">Accuracy (%)</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Dense trajectories [<a href="/journals/mpe/2021/6670087/#B42" target="_blank">42</a>]</td><td class="align_center">84.2</td></tr><tr><td class="align_left">Soft attention [<a href="/journals/mpe/2021/6670087/#B34" target="_blank">34</a>]</td><td class="align_center">84.9</td></tr><tr><td class="align_left">Cho et al. [<a href="/journals/mpe/2021/6670087/#B35" target="_blank">35</a>]</td><td class="align_center">88.0</td></tr><tr><td class="align_left">Snippets [<a href="/journals/mpe/2021/6670087/#B36" target="_blank">36</a>]</td><td class="align_center">89.5</td></tr><tr><td class="align_left">Ours (MDF:MD3DCNN+4<svg height="10.335pt" id="M99" style="vertical-align:-0.2325001pt" version="1.1" viewbox="-0.0498162 -10.1025 38.8397 10.335" width="38.8397pt" 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="M495 163C480 117 462 85 444 65C421 39 387 34 332 34C290 34 256 36 236 47C218 57 213 77 213 131V526C213 612 222 616 301 622V650H40V622C122 616 128 611 128 526V126C128 41 120 34 36 28V0H489C498 31 519 126 525 157L495 163Z"></path></g><g transform="matrix(.013,0,0,-0.013,6.994,0)"><path d="M409 504C401 567 396 607 392 642C354 654 312 665 266 665C137 665 60 583 60 487C60 374 161 325 225 290C300 250 355 215 355 141C355 68 311 21 235 21C131 21 86 122 71 183L41 176C48 128 61 42 68 21C78 16 93 8 118 0C142 -7 175 -15 216 -15C349 -15 438 69 438 174C438 287 344 333 265 374C186 414 138 449 138 522C138 576 172 631 249 631C336 631 363 562 380 499L409 504Z"></path></g><g transform="matrix(.013,0,0,-0.013,13.026,0)"><path d="M592 498C586 556 582 629 581 675H560C545 656 537 650 510 650H115C87 650 74 652 60 675H40C38 620 33 555 28 495H57C69 539 77 568 89 585C102 607 122 616 205 616H267V123C267 44 259 34 168 28V0H454V28C360 34 352 44 352 123V616H422C498 616 514 608 531 584C542 568 552 543 562 495L592 498Z"></path></g><g transform="matrix(.013,0,0,-0.013,20.955,0)"><path d="M861 0V28C774 35 771 41 768 147L759 509C756 612 762 614 851 622V650H681L449 149L221 650H57V622C148 613 153 609 144 479L130 271C123 166 117 123 111 88C104 46 85 34 26 28V0H259V28C192 35 169 42 167 90C166 130 166 173 170 256L185 541H187L411 7H431L675 555H679L683 147C683 41 680 35 598 28V0H861Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,32.661,-5.741)"><path d="M486 158C486 177 478 202 466 220C413 228 386 236 336 262C386 288 413 297 466 304C478 323 486 347 485 366C470 376 444 381 422 380C389 338 368 319 321 288C323 345 329 372 349 422C339 442 322 461 305 470C289 461 271 442 262 422C281 372 287 345 290 288C243 319 222 338 189 380C167 381 142 376 125 366C125 347 133 322 145 304C198 296 225 288 275 262C225 236 198 227 145 220C133 201 125 177 126 158C141 148 167 143 189 144C222 186 243 205 290 236C288 179 282 152 262 102C272 82 289 63 306 54C322 63 340 82 350 102C330 152 324 179 321 236C368 205 390 186 422 144C444 143 470 148 486 158Z"></path></g></svg></td><td class="align_center">97.7</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of our results to the state-of-the-arts on action recognition dataset UCF11.</div>

Mathematical Problems in Engineering

tab3

Table 3

Table 3: The Multidimensional Motion Features of Spatial Depth Feature Maps: An Effective Motion Information Representation Method for Video-Based Action Recognition 

Table 3 | The Multidimensional Motion Features of Spatial Depth Feature Maps: An Effective Motion Information Representation Method for Video-Based Action Recognition 