Encoding Longer-Term Contextual Information with Predictive Coding and Ego-Motion

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/complexity/volume-2018/7609587/figures/7609587.fig.007a.svgz" name="7609587.fig.007a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Frame 1</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/complexity/volume-2018/7609587/figures/7609587.fig.007b.svgz" name="7609587.fig.007b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Frame 10</td></tr><tr class="fig-image" id="c"><td><object data="https://static.hindawi.com/articles/complexity/volume-2018/7609587/figures/7609587.fig.007c.svgz" name="7609587.fig.007c" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(c) </b>Frame 50</td></tr><tr class="fig-image" id="d"><td><object data="https://static.hindawi.com/articles/complexity/volume-2018/7609587/figures/7609587.fig.007d.svgz" name="7609587.fig.007d" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(d) </b>Frame 100</td></tr><tr class="fig-image" id="e"><td><object data="https://static.hindawi.com/articles/complexity/volume-2018/7609587/figures/7609587.fig.007e.svgz" name="7609587.fig.007e" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(e) </b>Frame 130</td></tr></table>

<div>Image generated from the <svg height="8.398635pt" id="M110" style="vertical-align:-0.04981613pt" version="1.1" viewbox="-0.049816 -8.348819 6.363025 8.398635" width="6.363025pt" 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="M384 0V27C293 34 287 42 287 114V635C232 613 172 594 109 583V559L157 557C201 555 205 550 205 499V114C205 42 199 34 109 27V0H384Z"></path></g></svg>st <svg height="8.842299pt" id="M111" style="vertical-align:-0.2063942pt" version="1.1" viewbox="-0.049816 -8.635905 18.772362 8.842299" width="18.772362pt" 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="M673 297H417L411 270C517 261 522 258 506 183L487 92C476 38 428 19 360 19C207 19 123 132 123 287C123 472 243 631 441 631C557 631 617 583 617 469L647 472C650 545 655 604 658 632C625 643 554 666 467 666C201 666 23 502 23 278C23 90 156 -16 339 -16C410 -16 501 6 569 24C566 43 567 70 573 101L589 183C604 259 607 262 667 271L673 297Z"></path></g><g transform="matrix(.013,0,0,-0.013,9.186,0)"><path d="M715 650H476L470 622C550 619 562 610 562 570C562 536 553 481 535 384L523 321C485 121 408 37 283 37C178 37 99 109 134 297L178 532C193 612 199 616 278 622L284 650H29L23 622C105 616 109 609 94 532L48 291C23 160 51 83 98 40C143 -1 202 -16 260 -16C321 -16 387 3 439 49C509 111 542 204 563 312L577 384C595 479 608 533 619 569C629 603 637 620 709 622L715 650Z"></path></g></svg> output (Layer 3), <span class="nowrap"><svg height="8.555213pt" id="M112" style="vertical-align:-0.2063942pt" version="1.1" viewbox="-0.049816 -8.348819 36.827397 8.555213" width="36.827397pt" 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="M471 456L444 459C426 433 414 430 388 430C324 430 270 434 216 434C103 434 51 374 23 338L43 317C96 366 146 380 221 375L154 109C149 86 147 68 147 52C147 4 168 -12 197 -12C240 -12 291 25 334 71L320 96C295 75 268 58 252 58C238 58 227 79 238 138C251 211 272 296 292 372C310 372 332 368 350 368C391 368 421 369 434 371C444 388 455 413 471 456Z"></path></g><g transform="matrix(.013,0,0,-0.013,9.934,0)"><path d="M535 323V373H52V323H535ZM535 138V188H52V138H535Z"></path></g><g transform="matrix(.013,0,0,-0.013,21.226,0)"><path d="M412 140C382 77 369 73 315 73H129L270 222C362 320 402 379 402 466C402 571 322 635 234 635C177 635 130 609 99 576L42 495L64 475C90 514 133 568 201 568C274 568 318 519 318 435C318 349 255 267 193 193C144 135 87 78 32 23V0H405C417 45 427 89 440 131L412 140Z"></path></g><g transform="matrix(.013,0,0,-0.013,27.489,0)"><path d="M113 -12C146 -12 170 11 170 46C170 78 146 103 114 103S58 78 58 46C58 11 82 -12 113 -12Z"></path></g><g transform="matrix(.013,0,0,-0.013,30.464,0)"><path d="M241 635C89 635 35 457 35 312C35 153 89 -12 240 -12C390 -12 443 166 443 312C443 466 390 635 241 635ZM238 602C329 602 354 454 354 312C354 172 330 22 240 22C152 22 124 173 124 313S148 602 238 602Z"></path></g></svg>.</span></div>

Complexity

fig7

Figure 7

Figure 7: Encoding Longer-Term Contextual Information with Predictive Coding and Ego-Motion 