Proceedings of the 19th ACM International Conference on Multimodal Interaction 2017
DOI: 10.1145/3136755.3143021
|View full text |Cite
|
Sign up to set email alerts
|

Rapid development of multimodal interactive systems: a demonstration of platform for situated intelligence

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
27
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 38 publications
(27 citation statements)
references
References 2 publications
0
27
0
Order By: Relevance
“…This component consumes video streams from video stream producers, and produces detection results for each frame which can be consumed by latter components in the pipeline. Additionally, the base functionality of OpenFace is extended with a facial expression recognition model 5 . Integration of this functionality into OpenSense involves the use of ML.NET 6 with Open Neural Network Exchange 7 to import the pre-trained model into the system.…”
Section: Exportersmentioning
confidence: 99%
See 1 more Smart Citation
“…This component consumes video streams from video stream producers, and produces detection results for each frame which can be consumed by latter components in the pipeline. Additionally, the base functionality of OpenFace is extended with a facial expression recognition model 5 . Integration of this functionality into OpenSense involves the use of ML.NET 6 with Open Neural Network Exchange 7 to import the pre-trained model into the system.…”
Section: Exportersmentioning
confidence: 99%
“…Figure 1 provides a screenshot of the system in action (currently only available on Windows). OpenSense is built on the Microsoft's Platform for Situated Intelligence 2 (\psi) [5], an open source and extensible framework that enables the development of situated integrative-AI systems. Consequently, OpenSense inherits all computational tools provided by the \psi runtime and core libraries, including parallel computing over streams of data, reasoning about time, data stream synchronization, and multimodal data fusion.…”
mentioning
confidence: 99%
“…TeamTalk (Marge and Rudnicky, 2019) for example, controls multiple ground robots by way of a predefined grammar, while DIARC (Scheutz et al, 2019) also supports dialogue with multiple robots, and has been implemented on ground, aerial, and social robots. Open-source architectures such as OpenDial (Lison and Kennington, 2016), IrisTK (Skantze and Al Moubayed, 2012), and Microsoft's PSI (Bohus et al, 2017) can be used to build many situated dialogue agents, including robots. Compared to similar architectures, MultiBot leverages wizardswappable components from ScoutBot and extends the mode of interaction to multi-participant dialogue.…”
Section: Related Workmentioning
confidence: 99%
“…One such system is the virtual receptionist, "which keeps track of users attention and engagement through visual cues (such as gaze tracking, head orientation etc.) to initiate the interaction at the most appropriate moment [45]. Further, it can also make use of hesitation (e.g., "hmmm .…”
Section: Asi a New Challengementioning
confidence: 99%