対面インタラクションにおける人間の動作・姿勢予測のための時空間モデル比較
Comparison of Spatio-Temporal Models for Human Motion and Pose Forecasting in Face-to-Face Interaction Scenarios
対面会話データセットUDIVA v0.5を用い、全身(顔・体・手)の動作予測手法を初めて体系的に比較し、短期的に学習した注意ベースモデルが長期的予測でも高精度であることを示した。
著者: German Barquero, Johnny Núñez, Zhen Xu, Sergio Escalera, Wei-Wei Tu, Isabelle Guyon, Cristina Palmero
分類: cs.CV, cs.RO
原文アブストラクト
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.
