We present a model that generates natural language descr iptions of images and their regions. Our approach leverages datasets of images and their sentence descr iptions to learn about the inter-modal correspondences between language and visual data.
https://github.com/NVIDIA-AI-IOT/trt_pose
This project features multi-instance pose estimation accelerated by NVIDIA TensorRT. It is ideal for applications where low latency is necessary. It includes
Training scr ipts to train on any keypoint task
https://github.com/NVIDIA-AI-IOT/trt_pose
This project features multi-instance pose estimation accelerated by NVIDIA TensorRT. It is ideal for applications where low latency is necessary. It includes
Training scr ipts to train on any keypoint task
CrowdPose：有效的拥挤场景姿势估计和新基准
引文
如果您发现我们的作品对您的研究有用，请考虑引用：
article{li2018crowdpose,
title={CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark},
author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and
