Finetuned Language Models Are Zero-Shot Learners

微调的语言模型是零样本学习器.

SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos

SmoothNet：一种用于视频中人体姿态细化的即插即用网络.

Pose for Everything: Towards Category-Agnostic Pose Estimation

估计一切姿态：面向类别无关的姿态估计.

Localization with Sampling-Argmax

通过Sampling-Argmax来定位.

Poseur: Direct Human Pose Regression with Transformers

Poseur：使用Transformer直接进行人体姿态回归.

Next-Generation Pose Detection with MoveNet and TensorFlow

通过MoveNet和TensorFlow实现下一代姿态检测.