Pith. sign in

REVIEW 1 cited by

Interaction Transformer for Human Reaction Generation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2207.01685 v2 pith:GRG234DN submitted 2022-07-04 cs.CV

classification cs.CV
keywords interactionattentionreactiongenerateinterformerspatialtemporaltransformer
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We address the challenging task of human reaction generation, which aims to generate a corresponding reaction based on an input action. Most of the existing works do not focus on generating and predicting the reaction and cannot generate the motion when only the action is given as input. To address this limitation, we propose a novel interaction Transformer (InterFormer) consisting of a Transformer network with both temporal and spatial attention. Specifically, temporal attention captures the temporal dependencies of the motion of both characters and of their interaction, while spatial attention learns the dependencies between the different body parts of each character and those which are part of the interaction. Moreover, we propose using graphs to increase the performance of spatial attention via an interaction distance module that helps focus on nearby joints from both characters. Extensive experiments on the SBU interaction, K3HI, and DuetDance datasets demonstrate the effectiveness of InterFormer. Our method is general and can be used to generate more complex and long-term interactions. We also provide videos of generated reactions and the code with pre-trained models at https://github.com/CRISTAL-3DSAM/InterFormer

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling

    cs.GR 2025-06 conditional novelty 6.0 of 10

    DuetGen is a two-stage masked-modeling system that converts music into synchronized, interactive two-person dance motion, and claims state-of-the-art results on the DD100 duet dataset.

Pith tools