2016 Proceeding- General Chairs:
- Stefanos Vrochidis,
- Leo Wanner,
- Elisabeth André,
- Stephanie Elzer Schwartz
It is our great pleasure to welcome you to the 1st International Workshop on Multimedia Analysis and Retrieval for Multimodal Interaction (MARMI2016) held within ICMR2016, in New York, USA.
The goal of MARMI workshop is threefold. First, the workshop aims at presenting the most recent methods for analysis, retrieval and semantic interpretation of multimedia and multilingual data in multimodal interaction scenarios and agent-based applications. Second, it aims at bringing together practitioners and researchers, both from multimedia retrieval and multimodal interaction domains, to share ideas and experiences in designing and implementing novel multimedia analysis and retrieval techniques and tools for interactive agent-based applications. Third, the workshop aims at evaluating the maturity and efficiency of the multimedia retrieval and analysis techniques for real world multimodal interactive agent-based applications.
In total the Program Committee of MARMI 2016 accepted 6 (over 7 submitted) papers covering the following topics: a) speech analysis and audio retrieval, b) affective behaviour analysis and human activity recognition, c) dialogue systems and knowledge-based agents.
In addition, Dr. Benoit Huet from EURECOM delivers the keynote for MARMI 2016 workshop entitled: "Event-based Multimedia Search and Retrieval for Question Answering".
Proceeding Downloads
Event-based MultiMedia Search and Retrieval for Question Answering
User generated content, available in massive amounts on the Internet, comes in many "flavors" (i.e. micro messages, text documents, images and videos) and is receiving increasing attention due to its many potential applications. One important ...
Action Recognition Using Convolutional Restricted Boltzmann Machines
In this work we study deep learning architectures for the problem of action recognition in image sequences focusing on generative neural networks, namely the convolutional extension of restricted Boltzmann machines (RBMs). We first use a stack of ...
A Multimodal Annotation Schema for Non-Verbal Affective Analysis in the Health-Care Domain
- Federico Sukno,
- Mónica Domínguez,
- Adria Ruiz,
- Dominik Schiller,
- Florian Lingenfelser,
- Louisa Pragst,
- Ekeni Kamateri,
- Stefanos Vrochidis
The development of conversational agents with human interaction capabilities requires advanced affective state recognition integrating non-verbal cues from the different modalities constituting what in human communication we perceive as an overall ...
Towards an Ontology-Driven Adaptive Dialogue Framework
- Georgios Meditskos,
- Stamatia Dasiopoulou,
- Louisa Pragst,
- Stefan Ultes,
- Stefanos Vrochidis,
- Ioannis Kompatsiaris,
- Leo Wanner
In this paper, we describe the principles and technologies that underpin the development of an adaptive dialogue manager framework, tailored to carrying out human-agent conversations in a natural, robust and flexible manner. Our research focus is ...
Towards a Multimedia Knowledge-Based Agent with Social Competence and Human Interaction Capabilities
- Leo Wanner,
- Josep Blat,
- Stamatia Dasiopoulou,
- Mónica Domínguez,
- Gerard Llorach,
- Simon Mille,
- Federico Sukno,
- Eleni Kamateri,
- Stefanos Vrochidis,
- Ioannis Kompatsiaris,
- Elisabeth André,
- Florian Lingenfelser,
- Gregor Mehlmann,
- Andries Stam,
- Ludo Stellingwerff,
- Bianca Vieru,
- Lori Lamel,
- Wolfgang Minker,
- Louisa Pragst,
- Stefan Ultes
We present work in progress on an intelligent embodied conversation agent in the basic care and healthcare domain. In contrast to most of the existing agents, the presented agent is aimed to have linguistic cultural, social and emotional competence ...
Effective Speaker Retrieval and Recognition through Vector Quantization and Unsupervised Distance Learning
The huge amount of multimedia content accumulated daily has demanded the development of effective retrieval approaches. In this context, speaker recognition methods capable of automatically identifying a person through their voice is of great relevance. ...
A Probabilistic Ranking Model for Audio Stream Retrieval
In Audio Stream Retrieval (ASR) systems, clients periodically query an audio database with an audio segment taken from the input audio stream to keep track of the flow of the stream in the original content sources or to compare two differently edited ...
Index Terms
- Proceedings of the 1st International Workshop on Multimedia Analysis and Retrieval for Multimodal Interaction
Recommendations
Acceptance Rates
| Year | Submitted | Accepted | Rate |
|---|---|---|---|
| MARMI '16 | 7 | 6 | 86% |
| Overall | 7 | 6 | 86% |