HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

SocialInteractionGAN: Multi-person Interaction Sequence Generation

Louis Airale 1, 2 Dominique Vaufreydaz 1 Xavier Alameda-Pineda 2
1 M-PSI - Multimodal Perception and Sociable Interaction
LIG - Laboratoire d'Informatique de Grenoble
2 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : Prediction of human actions in social interactions has important applications in the design of social robots or artificial avatars. In this paper, we model human interaction generation as a discrete multi-sequence generation problem and present SocialInteractionGAN, a novel adversarial architecture for conditional interaction generation. Our model builds on a recurrent encoder-decoder generator network and a dual-stream discriminator. This architecture allows the discriminator to jointly assess the realism of interactions and that of individual action sequences. Within each stream a recurrent network operating on short subsequences endows the output signal with local assessments, better guiding the forthcoming generation. Crucially, contextual information on interacting participants is shared among agents and reinjected in both the generation and the discriminator evaluation processes. We show that the proposed SocialInteractionGAN succeeds in producing high realism action sequences of interacting people, comparing favorably to a diversity of recurrent and convolutional discriminator baselines. Evaluations are conducted using modified Inception Score and Fréchet Inception Distance metrics, that we specifically design for discrete sequential generated data. The distribution of generated sequences is shown to approach closely that of real data. In particular our model properly learns the dynamics of interaction sequences, while exploiting the full range of actions.
Complete list of metadata

Contributor : Dominique Vaufreydaz Connect in order to contact the contributor
Submitted on : Tuesday, March 9, 2021 - 11:42:48 AM
Last modification on : Wednesday, April 13, 2022 - 9:32:12 AM
Long-term archiving on: : Thursday, June 10, 2021 - 6:56:13 PM


Files produced by the author(s)


  • HAL Id : hal-03163467, version 1
  • ARXIV : 2103.05916


Louis Airale, Dominique Vaufreydaz, Xavier Alameda-Pineda. SocialInteractionGAN: Multi-person Interaction Sequence Generation. 2021. ⟨hal-03163467⟩



Record views


Files downloads