@inproceedings{e7f1157331fd40fda2f6f63e4a4e1a18,
title = "Top-1 CORSMAL Challenge 2020 Submission: Filling Mass Estimation Using Multi-modal Observations of Human-Robot Handovers",
abstract = "Human-robot object handover is a key skill for the future of human-robot collaboration. CORSMAL 2020 Challenge focuses on the perception part of this problem: the robot needs to estimate the filling mass of a container held by a human. Although there are powerful methods in image processing and audio processing individually, answering such a problem requires processing data from multiple sensors together. The appearance of the container, the sound of the filling, and the depth data provide essential information. We propose a multi-modal method to predict three key indicators of the filling mass: filling type, filling level, and container capacity. These indicators are then combined to estimate the filling mass of a container. Our method obtained Top-1 overall performance among all submissions to CORSMAL 2020 Challenge on both public and private subsets while showing no evidence of overfitting. Our source code is publicly available: github.com/v-iashin/CORSMAL.",
keywords = "Audio, CORSMAL, Depth, IR, Multi-modal, RGB",
author = "Vladimir Iashin and Francesca Palermo and G{\"o}khan Solak and Claudio Coppola",
note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG. jufoid=62555; International Conference on Pattern Recognition ; Conference date: 10-01-2021 Through 15-01-2021",
year = "2021",
doi = "10.1007/978-3-030-68793-9_31",
language = "English",
isbn = "9783030687922",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "423--436",
editor = "{Del Bimbo}, Alberto and Rita Cucchiara and Stan Sclaroff and Farinella, {Giovanni Maria} and Tao Mei and Marco Bertini and Escalante, {Hugo Jair} and Roberto Vezzani",
booktitle = "Pattern Recognition. ICPR International Workshops and Challenges, 2021, Proceedings",
}