Understanding physical phenomena is a key competence that enables humans and
animals to act and interact under uncertain perception in previously unseen
environments containing novel object and their configurations. Developmental
psychology has shown that such skills are acquired by infants from observations
at a very early stage.
In this paper, we contrast a more traditional approach of taking a
model-based route with explicit 3D representations and physical simulation by
an end-to-end approach that directly predicts stability and related quantities
from appearance. We ask the question if and to what extent and quality such a
skill can directly be acquired in a data-driven way bypassing the need for an
explicit simulation.
We present a learning-based approach based on simulated data that predicts
stability of towers comprised of wooden blocks under different conditions and
quantities related to the potential fall of the towers. The evaluation is
carried out on synthetic data and compared to human judgments on the same
stimuli.

本文挑战传统的基于模型的路线，采用直接从外观预测稳定性及其相关量的端到端方法，并提出了一种基于模拟数据的学习方法，用于预测由木质块组成的塔在不同条件下的稳定性以及与塔的潜在倒塌有关的量。

摔倒还是不摔倒：一种物理稳定性预测的视觉方法

To Fall Or Not To Fall: A Visual Approach to Physical Stability  Prediction

In this work we introduce a fully end-to-end approach for action detection in
videos that learns to directly predict the temporal bounds of actions. Our
intuition is that the process of detecting actions is naturally one of
observation and refinement: observing moments in video, and refining hypotheses
about when an action is occurring. Based on this insight, we formulate our
model as a recurrent neural network-based agent that interacts with a video
over time. The agent observes video frames and decides both where to look next
and when to emit a prediction. Since backpropagation is not adequate in this
non-differentiable setting, we use REINFORCE to learn the agent's decision
policy. Our model achieves state-of-the-art results on the THUMOS'14 and
ActivityNet datasets while observing only a fraction (2% or less) of the video
frames.

该研究提出了一种直接预测动作时间边界的完全端到端的方法，其中模型作为一个基于循环神经网络的智能体与视频交互，并使用 REINFORCE 来学习决策策略，取得了 THUMOS'14 和 ActivityNet 数据集的最先进结果。