Deep Reinforcement Learning for Active Human Pose Estimation

2020-01-07 · Erik Gärtner, Aleksis Pirinen, Cristian Sminchisescu

Most 3d human pose estimation methods assume that input -- be it images of a scene collected from one or several viewpoints, or from a video -- is given. Consequently, they focus on estimates leveraging prior knowledge and measurement by fusing information spatially and/or temporally, whenever available. In this paper we address the problem of an active observer with freedom to move and explore the scene spatially -- in `time-freeze' mode -- and/or temporally, by selecting informative viewpoints that improve its estimation accuracy. Towards this end, we introduce Pose-DRL, a fully trainable deep reinforcement learning-based active pose estimation architecture which learns to select appropriate views, in space and time, to feed an underlying monocular pose estimator. We evaluate our model using single- and multi-target estimators with strong result in both settings. Our system further learns automatic stopping conditions in time and transition functions to the next temporal processing step in videos. In extensive experiments with the Panoptic multi-view setup, and for complex scenes containing multiple people, we show that our model learns to select viewpoints that yield significantly more accurate pose estimates compared to strong multi-view baselines.

📄 PDF Abstract BibTeX arXiv:2001.02024

Code (1)

aleksispi/pose-drl 공식 구현

Tasks

3D Human Pose EstimationDeep Reinforcement LearningPose Estimation reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Proactive Multi-Camera Collaboration For 3D Human Pose Estimation

2023-03-07 · Hai Ci, Mickel Liu, Xuehai Pan, Fangwei Zhong 외

This paper presents a multi-agent reinforcement learning (MARL) scheme for proactive Multi-Camera Collaboration in 3D Human Pose Estimation in dynamic human crowds. Traditional fixed-viewpoint multi-camera solutions for …

3D Human Pose Estimation 3D Reconstruction Multi-agent Reinforcement Learning Pose Estimation

Model-Free Reinforcement Learning with the Decision-Estimation Coefficient

2022-11-25 · NeurIPS 2023 11

We consider the problem of interactive decision making, encompassing structured bandits and reinforcement learning with general function approximation. Recently, Foster et al. (2021) introduced the Decision-Estimation Co…

Decision Making reinforcement-learning Reinforcement Learning

Multi-modal Active Learning From Human Data: A Deep Reinforcement Learning Approach

2019-06-07 · Ognjen Rudovic, Meiru Zhang, Bjorn Schuller, Rosalind W. Picard

Human behavior expression and experience are inherently multi-modal, and characterized by vast individual and contextual heterogeneity. To achieve meaningful human-computer and human-robot interactions, multi-modal model…

Active Learning Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Deep Reinforcement Learning with Interactive Feedback in a Human-Robot Environment

2020-07-07 · Ithan Moreira, Javier Rivas, Francisco Cruz, Richard Dazeley 외

Robots are extending their presence in domestic environments every day, being more common to see them carrying out tasks in home scenarios. In the future, robots are expected to increasingly perform more complex tasks an…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning

2019-09-09 · IJCNLP 2019 11 · Peng Xu, Chien-Sheng Wu, Andrea Madotto, Pascale Fung

Sensational headlines are headlines that capture people's attention and generate reader interest. Conventional abstractive headline generation methods, unlike human writers, do not optimize for maximal reader attention. …

Headline Generation reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)