Comparison of Spatio-Temporal Models for Human Motion and Pose Forecasting in Face-to-Face Interaction Scenarios

03/07/2022
by   Germán Barquero, et al.
17

Human behavior forecasting during human-human interactions is of utmost importance to provide robotic or virtual agents with social intelligence. This problem is especially challenging for scenarios that are highly driven by interpersonal dynamics. In this work, we present the first systematic comparison of state-of-the-art approaches for behavior forecasting. To do so, we leverage whole-body annotations (face, body, and hands) from the very recently released UDIVA v0.5, which features face-to-face dyadic interactions. Our best attention-based approaches achieve state-of-the-art performance in UDIVA v0.5. We show that by autoregressively predicting the future with methods trained for the short-term future (<400ms), we outperform the baselines even for a considerably longer-term future (up to 2s). We also show that this finding holds when highly noisy annotations are used, which opens new horizons towards the use of weakly-supervised learning. Combined with large-scale datasets, this may help boost the advances in this field.

READ FULL TEXT
research
04/08/2023

StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation

Anticipation problem has been studied considering different aspects such...
research
03/06/2022

On the importance of stationarity, strong baselines and benchmarks in transport prediction problems

Over the last years, the transportation community has witnessed a tremen...
research
10/23/2018

Action-Agnostic Human Pose Forecasting

Predicting and forecasting human dynamics is a very interesting but chal...
research
12/12/2019

Human Motion Anticipation with Symbolic Label

Anticipating human motion depends on two factors: the past motion and th...
research
07/07/2020

Human Trajectory Forecasting in Crowds: A Deep Learning Perspective

Since the past few decades, human trajectory forecasting has been a fiel...
research
04/12/2023

Best Practices for 2-Body Pose Forecasting

The task of collaborative human pose forecasting stands for predicting t...
research
11/04/2019

Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision

We tackle the problem of Human Locomotion Forecasting, a task for jointl...

Please sign up or login with your details

Forgot password? Click here to reset