PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

Kehong Gong*, Bingbing Li*, Jianfeng Zhang*, Tao Wang*, Jing Huang, Bi Mi, Jiashi Feng, Xinchao Wang CVPR 2022 (Oral Presentation, arxiv) Framework Pose-triplet contains three components: estimator, imitator and hallucinator The three components form dual-loop during the training process, complementing and strengthening one another. Improvement through co-evolving Here is imitated motion of different rounds, the estimator and imitator get improved over the rounds of training, and thus the imitated motion becomes more accurate and realistic from round 1 to 3. […]

Read more

Versatile Multi-Modal Pre-Training for Human-Centric Perception

1S-Lab, Nanyang Technological University  2SenseTime Research  3Shanghai AI Laboratory Accepted to CVPR 2022 This repository contains the official implementation of Versatile Multi-Modal Pre-Training for Human-Centric Perception. For brevity, we name our method HCMoCo. arXiv • Project Page • Dataset Citation If you find our work useful for your research, please consider citing the paper: Updates [03/2022] Code release! [03/2022] HCMoCo is accepted to CVPR 2022🥳! Installation We recommend using conda to manage the python environment. The commands below are provided […]

Read more

Shallow Convolutional Neural Networks for Human Activity Recognition using Wearable Sensors

[IEEE TIM 2021-1] Shallow Convolutional Neural Networks for Human Activity Recognition using Wearable SensorsAll of datasets we use in this paper can be download from Internet and you can find we how to process data in this paper.This is my first time to open source, so there maybe some problems in my codes and I will improve this project in the near feature.Thanks! Requirements ● Python3● PyTorch (My version 1.9.0+cu111, please choose compatibility with your computer)● Scikit-learn● Numpy How to […]

Read more