Social Process models, which treat each conversation group as a meta-learning task and condition forecasts on a short context of the same group, can interpolate to unseen synthetic group dynamics but do not extrapolate beyond training variety.
Forecasting Human Dynamics from Static Images
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper presents the first study on forecasting human dynamics from static images. The problem is to input a single RGB image and generate a sequence of upcoming human body poses in 3D. To address the problem, we propose the 3D Pose Forecasting Network (3D-PFNet). Our 3D-PFNet integrates recent advances on single-image human pose estimation and sequence prediction, and converts the 2D predictions into 3D space. We train our 3D-PFNet using a three-step training strategy to leverage a diverse source of training data, including image and video based human pose datasets and 3D motion capture (MoCap) data. We demonstrate competitive performance of our 3D-PFNet on 2D pose forecasting and 3D pose recovery through quantitative and qualitative results.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Social Processes: Probabilistic Meta-learning for Adaptive Multiparty Interaction Forecasting
Social Process models, which treat each conversation group as a meta-learning task and condition forecasts on a short context of the same group, can interpolate to unseen synthetic group dynamics but do not extrapolate beyond training variety.