Awesome

<h3 align="center">European Conference on Computer Vision 2022</h3> <h1 align="center">Pose Forecasting in Industrial Human-Robot Collaboration</h1> <div align="center"> Alessio Sampieri, Guido D'Amely, Andrea Avogaro, Federico Cunico, Geri Skenderi, Francesco Setti, Marco Cristani, and Fabio Galasso. </div> <h2 align="center">Abstract</h2> <div align="center"> <p> Pushing back the frontiers of collaborative robots in industrial environments, we propose a new Separable-Sparse Graph Convolutional Network (SeS-GCN) for pose forecasting. For the first time, SeS-GCN bottlenecks the interaction of the spatial, temporal and channel-wise dimensions in GCNs, and it learns sparse adjacency matrices by a teacher-student framework. Compared to the state-of-the-art, it only uses 1.72% of the parameters and it is ~4 times faster, while still performing comparably in forecasting accuracy on Human3.6M at 1 second in the future, which enables cobots to be aware of human operators. As a second contribution, we present a new benchmark of Cobots and Humans in Industrial COllaboration (CHICO). CHICO includes multi-view videos, 3D poses and trajectories of 20 human operators and cobots, engaging in 7 realistic industrial actions. Additionally, it reports 226 genuine collisions, taking place during the human-cobot interaction. We test SeS-GCN on CHICO for two important perception tasks in robotics: human pose forecasting, where it reaches an average error of 85.3 mm (MPJPE) at 1.00 sec in the future with a run time of 2.3 msec, and collision detection, by comparing the forecasted human motion with the known cobot motion, obtaining an F1-score of 0.64. </p> </div>

<h3 align="center"> <b>Read the <a href="https://arxiv.org/abs/2208.07308">Paper</a>!</b> </h3> <h3 align="center"> <b>Download the dataset <a href="https://univr-my.sharepoint.com/:f:/g/personal/federico_cunico_univr_it/Eh3Mau4d7WpLpP06TsMimzABKD344Bmy3xFFk473QlPrhA?e=rwLhhV">here</a>!</b> </h3> <h3 align="center"> <b>Watch the illustrative <a href="https://drive.google.com/file/d/1-5Gl0QUfklUEXc7x-7jv2DXITJJHfjqb/view?usp=sharing">video</a>!</b> </h3>