Extending Ginga-NCL to Specify Multimodal Interactions With Multiple Users

Barreto, Fábio; Abreu, Raphael; Montevecchi, Eyre Brasil B.; Josué, Marina I. P.; Valentim, Pedro Alves; Muchaluat-Saade, Débora C.

doi:10.1145/3428658.3431076

Cited by 9 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…No que diz respeito ao desempenho, este trabalho segue uma abordagem similar a [2] , que apresenta uma proposta para interação em Ginga-NCL através de reconhecimento de voz. Em [2], os autores apresentam resultados mostrando que a segunda implementação integrada ao middleware Ginga tem desempenho superior à primeira implementação em NCLua. Como trabalhos futuros, serão realizados testes para comprovar a potencial superioridade de desempenho da segunda proposta.…”

Section: Discussionunclassified

See 1 more Smart Citation

Possibilitando o Reconhecimento de Expressões Faciais em Aplicações Ginga-NCL

Valentim¹,

Barreto²,

Muchaluat-Saade³

2020

Anais Estendidos Do XXVI Simpósio Brasileiro De Sistemas Multimídia E Web (WebMedia 2020)

Self Cite

View full text Add to dashboard Cite

As the facial recognition research field grows, so do the possibilities for digital TV applications. However, in the current state of the art, it is not safe to assume there is a certain algorithm that would be the best for all kinds of applications. This work proposes an architecture to enable facial expression recognition for TV in a way that is agnostic to the recognition algorithm. As proof of concept, the proposal was developed for the Ginga middleware. There are two implementations: the first one, based on the current version of the Ginga middleware, and the second one, based on a proposed extended version of the middleware, exploring the viability of the present work.

show abstract

Section: Discussionunclassified

“…São duas as implementações deste trabalho: uma, feita na versão atual do middleware Ginga-NCL, e outra, feita sobre uma proposta de extensão do middleware [2] . A Figura 2 ilustra a principal diferença entre as implementações, em termos de arquitetura.…”

Section: Implementaçõesunclassified

Possibilitando o Reconhecimento de Expressões Faciais em Aplicações Ginga-NCL

Valentim¹,

Barreto²,

Muchaluat-Saade³

2020

Anais Estendidos Do XXVI Simpósio Brasileiro De Sistemas Multimídia E Web (WebMedia 2020)

Self Cite

View full text Add to dashboard Cite

show abstract

“…advancements in this field, and one example of this is the proliferation of voice assistants that are able to provide recommendations and directions based on the physical location of the user [15]. Multimodal interfaces have been developed by developers in order to facilitate the integration of a variety of forms of input, including voice interaction, gesture recognition, spatial orientation, and other forms of input respectively [16]. When you do this, it is much simpler to begin things in a manner that is more realistic, engaging, and laid-back.…”

Section: ░ 2 Related Workmentioning

confidence: 99%

An Innovative Guidotronic Bot with Integrated LiDAR and AI Voice Assistance

Aswin N.,

Teni Jio F.,

Pragnesh M.

et al. 2024

IIJSR

View full text Add to dashboard Cite

This research paper discusses the futuristic combination of LiDAR technology and Guidotronic Bot with AI Voice Assistance to improve robotic systems. AI Voice Assistance launches a new era of human-machine interaction. Today, intuitive communication and robot integration are crucial. This section discusses how AI Voice Assistance improves user experience and how people will soon be able to talk to robots in natural language. This will set the stage for Guidotronic Bot implementation discussions. This study shows the Guidotronic Bot, which can multitask without human assistance. We observe it and its effects in various situations. The integration method integrates LiDAR technology with the Guidotronic Bot's infrastructure to enable real-time mapping and vision. Accurate three-dimensional mapping from LiDAR sensors helps you avoid obstacles and navigate rough terrain. The integrated algorithm simplifies Guidotronic Bot, LiDAR sensor, and AI Voice Assistance system collaboration by combining sensors and making decisions. The bot uses AI algorithms to translate voice commands, use LiDAR for environmental data, and drive itself. This integration should improve navigation, awareness of surroundings, and voice control. This research expands robotic systems and prepares for future advances in human-robot interaction. Combining the Guidotronic Bot with LiDAR and AI Speech Recognition opens up new ways to navigate, interact with smart home devices, and work.

show abstract

“…Lastly, the ITV application receives those results and can behave accordingly. We provide different interaction modes, such as face recognition, facial expression recognition, voice recognition, gesture recognition, etc., and this set could be extended as desired [2]. In this paper, we focus on facial expression recognition in order to understand viewer's sentiments.…”

Section: Affective Tv Proposalmentioning

confidence: 99%

“…The first one is based on the current standard of the middleware, which relies on Lua scripting for recognizing facial expressions. The second one, which actually implements the proposal of this paper, is based on a modified version of the middleware [2]. Figure 3 illustrates the difference between the implementations.…”

Section: Implementation and Evaluationmentioning

confidence: 99%

Towards Affective TV with Facial Expression Recognition

Valentim¹,

Barreto²,

Muchaluat-Saade³

2021

Proceedings of the Life Improvement in Quality by Ubiquitous Experiences Workshop (LIQUE 2021)

Self Cite

View full text Add to dashboard Cite

Facial recognition techniques, fantasized in fiction movie classics, have already become reality. Such technology opens up a wide range of possibilities for different kinds of systems. From the point of view of interactive applications, facial expression as input data may be more immediate and more trustworthy to the user’s sentiment than the click of a button. For interactive television, facial expression recognition could be used for bringing broadcasters and viewers closer, enabling TV content to be personalized by the user sentiment. In fact, not only facial expression recognition, but any interaction that enables affective computing. In this work, we call this concept Affective TV. In order to support it, this work proposes facial expression recognition for digital TV applications. Our proposal is implemented and evaluated in the Ginga-NCL middleware, a digital TV standard used in several Latin American countries.

show abstract

Extending Ginga-NCL to Specify Multimodal Interactions With Multiple Users

Cited by 9 publications

References 15 publications

Possibilitando o Reconhecimento de Expressões Faciais em Aplicações Ginga-NCL

Possibilitando o Reconhecimento de Expressões Faciais em Aplicações Ginga-NCL

An Innovative Guidotronic Bot with Integrated LiDAR and AI Voice Assistance

Towards Affective TV with Facial Expression Recognition

Contact Info

Product

Resources

About