Affect-expressive movement generation with factored conditional Restricted Boltzmann Machines

Alemi, Omid; Pasquier, Philippe

doi:10.1109/acii.2015.7344608

Cited by 17 publications

(25 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The final set of methods seeks to learn both the relevant features and the mapping from a (large) corpus of labeled exemplar data. Several different techniques have been proposed, including dimensionality reduction techniques, such as principal component analysis (PCA) [95] or functional PCA [81], and spatio-temporal models such as factored conditional restricted Boltzmann machines (FCRBMs) [3], the Bayesian dynamic network (BDN) [53], factored Gaussian process dynamical models (GPDM) [100], and structured recurrent neural networks (S-RNN) [39]. Although the preceding works aim to automatically extract both the features and the mapping for generating expressive trajectories, and the learning approaches rely on large corpora of human motion data, the majority of works remain focused on a single task (e.g., walking) and a specific robot structure, most commonly humanoid.…”

Section: Learned Featuresmentioning

confidence: 99%

“…The algorithm produces gaits and movements of the system, and a user can "encourage an added level of humor and expressivity" by selecting some preferred gaits to pass on the future evolving generations. More recent examples include spatio-temporal models such as Factored Conditional RestricteFCRBMs [3], the BDN [53], GPDMs [100], and S-RNNs [39], which simultaneously learn both the features and the mapping.…”

Section: Formulatedmentioning

confidence: 99%

See 1 more Smart Citation

Robot Expressive Motions

Venture

Kulić

2019

J. Hum.-Robot Interact.

View full text Add to dashboard Cite

Robots that have different forms and capabilities are used in a wide variety of situations; however, one common point to all robots interacting with humans is their ability to communicate with them. In addition to verbal communication or purely communicative movements, robots can also use their embodiment to generate expressive movements while achieving a task, to convey additional information to its human partner. This article surveys state-of-the-art techniques that generate whole-body expressive movements in robots and robot avatars. We consider different embodiments such as wheeled, legged, or flying systems and the different metrics used to evaluate the generated movements. Finally, we discuss future areas of improvement and the difficulties to overcome to develop truly expressive motions in artificial agents.

show abstract

Section: Learned Featuresmentioning

confidence: 99%

Section: Formulatedmentioning

confidence: 99%

Robot Expressive Motions

Venture

Kulić

2019

J. Hum.-Robot Interact.

View full text Add to dashboard Cite

show abstract

“…Importantly, they explicitly address the search for robust computational models that are able to harness the strengths of these systems, most importantly their speed and energy efficiency. The proposed architecture scales naturally to substrates with more neuronal real-estate and can be used for a wide array of tasks that can be mapped to a Bayesian formulation, such as constraint satisfaction problems (Jonke et al, 2016; Fonseca Guerra and Furber, 2017), prediction of temporal sequences (Sutskever and Hinton, 2007), movement planning (Taylor and Hinton, 2009; Alemi et al, 2015), simulation of solid-state systems (Edwards and Anderson, 1975), and quantum many-body problems (Carleo and Troyer, 2017; Czischek et al, 2018).…”

Section: Discussionmentioning

confidence: 99%

Accelerated Physical Emulation of Bayesian Inference in Spiking Neural Networks

et al. 2019

View full text Add to dashboard Cite

The massively parallel nature of biological information processing plays an important role due to its superiority in comparison to human-engineered computing devices. In particular, it may hold the key to overcoming the von Neumann bottleneck that limits contemporary computer architectures. Physical-model neuromorphic devices seek to replicate not only this inherent parallelism, but also aspects of its microscopic dynamics in analog circuits emulating neurons and synapses. However, these machines require network models that are not only adept at solving particular tasks, but that can also cope with the inherent imperfections of analog substrates. We present a spiking network model that performs Bayesian inference through sampling on the BrainScaleS neuromorphic platform, where we use it for generative and discriminative computations on visual data. By illustrating its functionality on this platform, we implicitly demonstrate its robustness to various substrate-specific distortive effects, as well as its accelerated capability for computation. These results showcase the advantages of brain-inspired physical computation and provide important building blocks for large-scale neuromorphic applications.

show abstract

“…Transitions between motion styles can be introduced at will by appropriate settings of the motion style labels over the sequence. Alemi et al [ALP15] applied the FCRBM model to the generation of controlled affective variations of walking motion, based on timevarying valence and arousal labels. Hierarchical FCRBMs.…”

Section: Figure 7: In a Variational Autoencoder (Vae) A Motion Sequen...mentioning

confidence: 99%

A Survey on Deep Learning for Skeleton‐Based Human Animation

Mourot

Hoyet

Clerc³

et al. 2021

Computer Graphics Forum

View full text Add to dashboard Cite

Human character animation is often critical in entertainment content production, including video games, virtual reality or fiction films. To this end, deep neural networks drive most recent advances through deep learning (DL) and deep reinforcement learning (DRL). In this article, we propose a comprehensive survey on the state‐of‐the‐art approaches based on either DL or DRL in skeleton‐based human character animation. First, we introduce motion data representations, most common human motion datasets and how basic deep models can be enhanced to foster learning of spatial and temporal patterns in motion data. Second, we cover state‐of‐the‐art approaches divided into three large families of applications in human animation pipelines: motion synthesis, character control and motion editing. Finally, we discuss the limitations of the current state‐of‐the‐art methods based on DL and/or DRL in skeletal human character animation and possible directions of future research to alleviate current limitations and meet animators' needs.

show abstract

Affect-expressive movement generation with factored conditional Restricted Boltzmann Machines

Cited by 17 publications

References 19 publications

Robot Expressive Motions

Robot Expressive Motions

Accelerated Physical Emulation of Bayesian Inference in Spiking Neural Networks

A Survey on Deep Learning for Skeleton‐Based Human Animation

Contact Info

Product

Resources

About