Exploring deep models for comprehension of deictic gesture-word combinations in cognitive robotics

G Pizzuto, A Cangelosi - 2019 International Joint Conference …, 2019 - ieeexplore.ieee.org
In the early stages of infant development, gestures and speech are integrated during
language acquisition. Such a natural combination is therefore a desirable, yet challenging …

SR-EM: episodic memory aware of semantic relations based on hierarchical clustering resonance network

JW Choi, GM Park, JH Kim - IEEE Transactions on Cybernetics, 2021 - ieeexplore.ieee.org
An intelligent robot requires episodic memory that can retrieve a sequence of events for a
service task learned from past experiences to provide a proper service to a user. Various …

Compositional models for VQA: Can neural module networks really count?

G Sejnova, M Tesar, M Vavrecka - Procedia computer science, 2018 - Elsevier
Large neural networks trained in an end-to-end fashion usually fail to generalize over novel
inputs which were not included in the training data. In contrast, biologically-inspired …

Where is my stuff? an interactive system for spatial relations

EA Sisbot, JH Connell - arXiv preprint arXiv:1909.06331, 2019 - arxiv.org
In this paper we present a system that detects and tracks objects and agents, computes
spatial relations, and communicates those relations to the user using speech. Our system is …

Human robot social interaction framework based on emotional episodic memory

WH Lee, SM Yoo, JW Choi, UH Kim, JH Kim - … Intelligence Technology and …, 2019 - Springer
Nowadays the application of robots are emerging in areas of modern life. It is expected we
will be living in a new era in which robots such as socially interactive robots will make an …

Exploring logical consistency and viewport sensitivity in compositional VQA models

G Sejnova, M Vavrecka, M Tesar… - 2019 IEEE/RSJ …, 2019 - ieeexplore.ieee.org
The most recent architectures for Visual Question Answering (VQA), such as TbD or
DDRprog, have already outperformed human-level accuracy on benchmark datasets (eg …

[PDF][PDF] Towards Environment Aware Social Robots using Visual Dialog

A Singh, M Ramanathan, R Satapathy… - aalind0.github.io
State of the art social robots are limited in their ability to understand their environment and
have a meaningful conversation based on it. Visual Dialog is a research field that combines …

Human-Robot Full-Sentence VQA Interaction System with Highway Memory Network

S Cho, JM Park, TJ Song, JH Kim - RITA 2018: Proceedings of the 6th …, 2020 - Springer
Intelligent robots such as social robots and home service robots that are being developed
nowadays are required to have the ability to naturally communicate with users in natural …

[引用][C] Multi-label categorizations and question answering for imbalanced raw web-based data

J Lacombe, R Chaput, J Perier-Camby, F Al Kassar…