自适应人体姿势预测的元辅助学习（英文版）

英文标题：Meta-Auxiliary Learning for Adaptive Human Pose Prediction中文摘要：提出了一种测试相适应的深度学习框架，它结合了自监督辅助任务和元辅助学习来帮助主要预测网络适应测试序列，该方法在预测人类姿势方面取得了更高的准确性。英文摘要：Predicting high-fidelity future human poses, from a historically observedsequence, is decisive for intelligent robots to interact with humans. Deepend-to-end learning approaches, which typically train a generic pre-trainedmodel on external datasets and then directly apply it to all test samples,emerge as the dominant solution to solve this issue. Despi