Challenges of Human Behavior Understanding

Salah, Albert Ali; Gevers, Theo; Sebe, Nicu; Vinciarelli, Alessandro

doi:10.1007/978-3-642-14715-9_1

Cited by 29 publications

(21 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This Special Issue incorporates six papers, two of which extend work presented in the Third International Workshop on Human Behavior Understanding [1]. We briefly summarize their highlights here.…”

Section: Contribution To the Special Issuementioning

confidence: 98%

See 1 more Smart Citation

Guest Editorial Behavior Understanding and Developmental Robotics

Salah

Oudeyer²,

Meriçli³

et al. 2014

IEEE Trans. Auton. Mental Dev.

Self Cite

View full text Add to dashboard Cite

Abstract-The scientific, technological, and application challenges that arise from the mutual interaction of developmental robotics and computational human behavior understanding give rise to two different perspectives. Robots need to be capable to learn dynamically and incrementally how to interpret, and thus understand multimodal human behavior, which means behavior analysis can be performed for developmental robotics. On the other hand, behavior analysis can also be performed through developmental robotics, since developmental social robots can offer stimulating opportunities for improving scientific understanding of human behavior, and especially to allow a deeper analysis of the semantics and structure of human behavior. The contributions to the Special Issue explore these two perspectives.Index Terms-Activity recognition, affective computing, attention, developmental learning, human behavior understanding, learning by demonstration, nonverbal communication. I. THE SCOPE OF THIS SPECIAL ISSUEI N ORDER to act in a useful, relevant, and socially acceptable manner, robots will need to understand the behavior of humans at various levels of abstractions, at various time scales, and in the particular context of human-robot interactions. Robots need to be capable to learn dynamically and incrementally how to interpret, and thus understand multimodal human behavior. This includes for example learning the meaning of new linguistic constructs used by a human, learning to interpret the emotional state of particular users from paralinguistic or nonverbal behavior, characterizing properties of the interaction or learning to guess the intention, and potentially the structure of goals of a human based on its overt behavior Furthermore, robots need in particular to be capable of learning new tasks through interaction with humans, for example using imitation learning or learning by demonstration. This heavily involves the capacity for learning how to decode teaching behavior, including linguistic and nonlinguistic cues, feedback and guidance provided by humans, as well as inferring reusable primitives in human behavior.While some of the existing techniques of multimodal behavior analysis and modeling can be readily reused for robots, novel scientific and technological challenges arise when one aims to achieve human behavior understanding in the context of natural and life-long human-robot interaction. The first purpose of this Special Issue is to explore these challenges.Our second purpose is to understand how behavior analysis can be achieved through developmental robotics. DevelopDigital Object Identifier 10.1109/TAMD.2014.2328731 mental social robots can offer stimulating opportunities for improving scientific understanding of human behavior, and especially to allow a deeper analysis of the semantics and structure of human behavior. Humans tend to interpret the meaning and the structure of other's behaviors in terms of their own action repertoire, which acts as a strong helping prior for this complex inference problem. S...

show abstract

Section: Contribution To the Special Issuementioning

confidence: 98%

“…Recent work in computer analysis of human behavior focuses on complex and contextualized social interactions, as opposed to scenarios of a single person performing a single activity [5], [6]. One of the basic requirements of social interaction is the establishment of joint attention between the interacting parties.…”

Section: Contribution To the Special Issuementioning

confidence: 99%

Guest Editorial Behavior Understanding and Developmental Robotics

Salah

Oudeyer²,

Meriçli³

et al. 2014

IEEE Trans. Auton. Mental Dev.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recognizing and understanding the behaviour of humans is a key capability for these systems. Yet, building such capabilities entails diverse and difficult technical challenges [1], partly due to the fact that each human user and each task context has its own particularities, i.e. different humans often behave differently in similar contexts, and vice versa the behaviour of one human, for example its motions, can have different properties and structures in different contexts.…”

Section: Introductionmentioning

confidence: 99%

“…different humans often behave differently in similar contexts, and vice versa the behaviour of one human, for example its motions, can have different properties and structures in different contexts. Thus, there is a strong need for capabilities to adapt to users, which importantly can be achieved through learning [1].…”

Section: Introductionmentioning

confidence: 99%

Learning to recognize parallel combinations of human motion primitives with linguistic descriptions using non-negative matrix factorization

Mangin

Oudeyer

2012

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

To cite this version:Olivier Mangin, Pierre-Yves Oudeyer. Learning to recognize parallel combinations of human motion primitives with linguistic descriptions using non-negative matrix factorization. Proceedings of 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, 2012. Learning to recognize parallel combinations of human motion primitives with linguistic descriptions using non-negative matrix factorizationOlivier Mangin and Pierre-Yves OudeyerAbstract-We present an approach, based on non-negative matrix factorization, for learning to recognize parallel combinations of initially unknown human motion primitives, associated with ambiguous sets of linguistic labels during training. In the training phase, the learner observes a human producing complex motions which are parallel combinations of initially unknown motion primitives. Each time the human shows a complex motion, he also provides high-level linguistic descriptions, consisting of a set of labels giving the name of the primitives inside the complex motion. From the observation of multimodal combinations of high-level labels with high-dimensional continuous unsegmented values representing complex motions, the learner must later on be able to recognize, through the production of the adequate set of labels, which are the motion primitives in a novel complex motion produced by a human, even if those combinations were never observed during training. We explain how this problem, as well as natural extensions, can be addressed using non-negative matrix factorization. Then, we show in an experiment in which a learner has to recognize the primitive motions of complex human dance choreographies, that this technique allows the system to infer with good performance the combinatorial structure of parallel combinations of unknown primitives.

show abstract

“…A large body of work exists in the field of computational human-behavior understanding, and the International Workshop of Human Behavior Understanding, previously organized with a focus on pattern recognition and ambient intelligence, brings together scientific and technological responses to some of the challenges in this field [57,58]. While some of the proposed methods can be readily re-used for robots, novel scientific and technological challenges arise when one considers achieving human behavior understanding in the context of human-robot interaction:…”

Section: Introductionmentioning

confidence: 99%

Human Behavior Understanding for Robotics

Salah

Ruiz‐del‐Solar²,

Meriçli

et al. 2012

Human Behavior Understanding

Self Cite

View full text Add to dashboard Cite

Abstract. Human behavior is complex, but structured along individual and social lines. Robotic systems interacting with people in uncontrolled environments need capabilities to correctly interpret, predict and respond to human behaviors. This paper discusses the scientific, technological and application challenges that arise from the mutual interaction of robotics and computational human behavior understanding. We supply a short survey of the area to provide a contextual framework and describe the most recent research in this area.

show abstract

Challenges of Human Behavior Understanding

Cited by 29 publications

References 41 publications

Guest Editorial Behavior Understanding and Developmental Robotics

Guest Editorial Behavior Understanding and Developmental Robotics

Learning to recognize parallel combinations of human motion primitives with linguistic descriptions using non-negative matrix factorization

Human Behavior Understanding for Robotics

Contact Info

Product

Resources

About