BARUAH, MURCHANA and BANERJEE, BONNY and Nagar, Atulya K. (2023) Intent Prediction in Human-Human Interactions. IEEE Transactions on Human-Machine Systems. ISSN 2168-2291 (Accepted for Publication)
Preview |
Text
arXiv_IEEETHMS_InteractionGenerationClassification_v9.pdf - Accepted Version Download (1MB) | Preview |
Abstract
The human ability to infer others' intent is innate and crucial to development. Machines ought to acquire this ability for seamless interaction with humans. We propose an agent model for predicting the intent of actors in human-human interactions. This requires simultaneous generation and recognition of an interaction at any time, for which end-to-end models are scarce. The proposed agent actively samples its environment via a sequence of glimpses. At each sampling instant, the model infers the observation class and completes the partially observed body motion. It learns the sequence of body locations to sample by jointly minimizing the classi�cation and generation errors. The model is evaluated on videos of two-skeleton interactions under two settings: (fi�rst person) one skeleton is the modeled agent and the other skeleton's joint movements constitute its visual observation, and (third person) an audience is the modeled agent and the two interacting skeletons' joint movements constitute its visual observation. Three methods for implementing the attention mechanism are analyzed using benchmark datasets. One of them, where attention is driven by sensory prediction error, achieves the highest classi�cation accuracy in both settings by sampling less than 50% of the skeleton joints, while also being the most efficient in terms of model size. This is the �first known attention-based agent to learn end-to-end from two-person interactions for intent prediction, with high accuracy and efficiency.
| Item Type: | Article |
|---|---|
| Additional Information and Comments: | © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| Keywords: | Agent, intent prediction, interaction recognition and generation, attention, perception, proprioception. |
| Faculty / Department: | Faculty of Human and Digital Sciences > Mathematics and Computer Science |
| Depositing User: | Atulya Nagar |
| Date Deposited: | 13 Mar 2023 10:11 |
| Last Modified: | 13 Mar 2023 10:11 |
| URI: | https://hira.hope.ac.uk/id/eprint/3778 |
Actions (login required)
 |
View Item |
Altmetric
Altmetric
