# Real-time Addressee Estimation: Deployment of a Deep-Learning Model on the iCub Robot

arXiv: https://arxiv.org/abs/2311.05334 · HTML: https://mlsanity.com/paper/2311.05334/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 19 references that are in the map.
- First posted on arXiv 9 Nov 2023.

## Builds on (most cited first, 4 of 4)

- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose](https://mlsanity.com/paper/1811.12004/) (2018)
- [Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances](https://mlsanity.com/paper/1809.04288/) (2018)
- [To Whom are You Talking? A Deep Learning Model to Endow Social Robots with Addressee Estimation Skills](https://mlsanity.com/paper/2308.10757/) (2023)

## Built on by (most cited first, 2 of 2)

- [A Multi-Modal Explainability Approach for Human-Aware Robots in Multi-Party Conversation](https://mlsanity.com/paper/2407.03340/) (2024)
- [Inclusive AI for Group Interactions: Predicting Gaze-Direction Behaviors in People with Intellectual and Developmental Disabilities](https://mlsanity.com/paper/2603.14460/) (2026)

## Abstract (arXiv)

Addressee Estimation is the ability to understand to whom a person is talking, a skill essential for social robots to interact smoothly with humans. In this sense, it is one of the problems that must be tackled to develop effective conversational agents in multi-party and unstructured scenarios. As humans, one of the channels that mainly lead us to such estimation is the non-verbal behavior of speakers: first of all, their gaze and body pose. Inspired by human perceptual skills, in the present work, a deep-learning model for Addressee Estimation relying on these two non-verbal features is designed, trained, and deployed on an iCub robot. The study presents the procedure of such implementation and the performance of the model deployed in real-time human-robot interaction compared to previous tests on the dataset used for the training.