SocialInteractionGAN: Multi-person Interaction Sequence Generation

by   Louis Airale, et al.

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.



There are no comments yet.


page 1

page 2

page 3

page 4


Human Motion Modeling using DVGANs

We present a novel generative model for human motion modeling using Gene...

Actions Generation from Captions

Sequence transduction models have been widely explored in many natural l...

Discriminator Rejection Sampling

We propose a rejection sampling scheme using the discriminator of a GAN ...

MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion

We introduce MUGL, a novel deep neural model for large-scale, diverse ge...

Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions

Human-motion generation is a long-standing challenging task due to the r...

Contextual RNN-GANs for Abstract Reasoning Diagram Generation

Understanding, predicting, and generating object motions and transformat...

Information Interaction Profile of Choice Adoption

Interactions between pieces of information (entities) play a substantial...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.