We tackle the problem of generating long-term 3D human motion from multiple action labels. Two main previous approaches, such as action- and motion-conditioned methods, have limitations to solve this problem. The action-conditioned methods generate a sequence of motion from a single action. Hence, it cannot generate long-term motions composed of multiple actions and transitions between actions. Meanwhile, the motion-conditioned methods generate future motions from initial motion. The generated future motions only depend on the past, so they are not controllable by the user's desired actions. We present MultiAct, the first framework to generate long-term 3D human motion from multiple action labels. MultiAct takes account of both action and motion conditions with a unified recurrent generation system. It repetitively takes the previous motion and action label; then, it generates a smooth transition and the motion of the given action. As a result, MultiAct produces realistic long-term motion controlled by the given sequence of multiple action labels. Codes are available here at https://github.com/TaeryungLee/MultiAct_RELEASE.

翻译：我们解决了从多个动作标签生成长时三维人体运动的问题。两种主流方法——基于动作条件的方法和基于运动条件的方法——在解决该问题时均存在局限性。基于动作条件的方法仅能从单一动作生成运动序列，因此无法生成由多个动作及其过渡组成的长时间运动；而基于运动条件的方法则从初始运动生成后续运动，生成的运动仅依赖于历史状态，因此无法根据用户期望的动作进行控制。我们提出MultiAct框架，这是首个能基于多个动作标签生成长期三维人体运动的系统。MultiAct通过统一的递归生成系统同时融合动作条件与运动条件：它循环输入上一帧运动及当前动作标签，依次生成平滑过渡及对应动作的运动。由此，MultiAct可生成由多动作标签序列控制的逼真长时运动。代码已开源至：https://github.com/TaeryungLee/MultiAct_RELEASE。