.hWlpPn::after{position:absolute;z-index:1000000;display:none;padding:0.5em 0.75em;font:normal normal 11px/1.5 -apple-system,BlinkMacSystemFont,"Segoe UI","Noto Sans",Helvetica,Arial,sans-serif,"Apple Color Emoji","Segoe UI Emoji";-webkit-font-smoothing:subpixel-antialiased;color:var(--tooltip-fgColor,var(--fgColor-onEmphasis,var(--color-fg-on-emphasis,#ffffff)));text-align:center;-webkit-text-decoration:none;text-decoration:none;text-shadow:none;text-transform:none;-webkit-letter-spacing:normal;-moz-letter-spacing:normal;-ms-letter-spacing:normal;letter-spacing:normal;word-wrap:break-word;white-space:pre;pointer-events:none;content:attr(aria-label);background:var(--tooltip-bgColor,var(--bgColor-emphasis,var(--color-neutral-emphasis-plus,#24292f)));border-radius:6px;opacity:0;}/*!sc*/, This is used quite commonly for "Optical Character Recognition" (e.g Handwriting recognition) in non-game scenarios, but can easily be adapted to work for "made up" symbols like in the games you specified. If you're interested in finding out more specific implementations of these networks, I suggest googling something along the lines of:, shape recognition model capable of recognizing seen and unseen geometric shapes. ii. We propose a dual attention architecture to learn shape primitives to improve shape representation learning. We add supervision through shape masks and the edge of objects to guide shape-aware feature learning. iii. We collect a dedicated shape recognition .