Search Results for author: Nikhil Churamani

Found 12 papers, 3 papers with code

Federated Learning of Socially Appropriate Agent Behaviours in Simulated Home Environments

1 code implementation12 Mar 2024 Saksham Checker, Nikhil Churamani, Hatice Gunes

In this paper, we present a novel FL benchmark that evaluates different strategies, using multi-label regression objectives, where each client individually learns to predict the social appropriateness of different robot actions while also sharing their learning with others.

Continual Learning Federated Learning

Continual Facial Expression Recognition: A Benchmark

no code implementations10 May 2023 Nikhil Churamani, Tolga Dimlioglu, German I. Parisi, Hatice Gunes

Understanding human affective behaviour, especially in the dynamics of real-world settings, requires Facial Expression Recognition (FER) models to continuously adapt to individual differences in user expression, contextual attributions, and the environment.

Continual Learning Facial Expression Recognition +1

Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition

no code implementations15 Mar 2021 Nikhil Churamani, Ozgur Kara, Hatice Gunes

As Facial Expression Recognition (FER) systems become integrated into our daily lives, these systems need to prioritise making fair decisions instead of aiming at higher individual accuracy scores.

Continual Learning Facial Expression Recognition +3

Towards Fair Affective Robotics: Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition

no code implementations15 Mar 2021 Ozgur Kara, Nikhil Churamani, Hatice Gunes

As affective robots become integral in human life, these agents must be able to fairly evaluate human affective expressions without discriminating against specific demographic groups.

Continual Learning Facial Expression Recognition +2

Spatio-Temporal Analysis of Facial Actions using Lifecycle-Aware Capsule Networks

no code implementations17 Nov 2020 Nikhil Churamani, Sinan Kalkan, Hatice Gunes

In real-world interactions, however, facial expressions are usually more subtle and evolve in a temporal manner requiring AU detection models to learn spatial as well as temporal information.

Affect-Driven Modelling of Robot Personality for Collaborative Human-Robot Interactions

no code implementations14 Oct 2020 Nikhil Churamani, Pablo Barros, Hatice Gunes, Stefan Wermter

Collaborative interactions require social robots to adapt to the dynamics of human affective behaviour.

CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions

1 code implementation14 Sep 2020 Vincenzo Lomonaco, Lorenzo Pellegrini, Pau Rodriguez, Massimo Caccia, Qi She, Yu Chen, Quentin Jodelet, Ruiping Wang, Zheda Mai, David Vazquez, German I. Parisi, Nikhil Churamani, Marc Pickett, Issam Laradji, Davide Maltoni

In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous.

Benchmarking Continual Learning

Continual Learning for Affective Computing

no code implementations10 Jun 2020 Nikhil Churamani

Real-world application requires affect perception models to be sensitive to individual differences in expression.

Continual Learning

The OMG-Empathy Dataset: Evaluating the Impact of Affective Behavior in Storytelling

no code implementations30 Aug 2019 Pablo Barros, Nikhil Churamani, Angelica Lim, Stefan Wermter

In this paper, we propose a novel dataset composed of dyadic interactions designed, collected and annotated with a focus on measuring the affective impact that eight different stories have on the listener.

The OMG-Emotion Behavior Dataset

no code implementations14 Mar 2018 Pablo Barros, Nikhil Churamani, Egor Lakomkin, Henrique Siqueira, Alexander Sutherland, Stefan Wermter

This paper is the basis paper for the accepted IJCNN challenge One-Minute Gradual-Emotion Recognition (OMG-Emotion) by which we hope to foster long-emotion classification using neural models for the benefit of the IJCNN community.

Human-Computer Interaction

Cannot find the paper you are looking for? You can Submit a new open access paper.