paper-with-me

Papers

Intervention-based Recurrent Casual Model for Non-stationary Video Causal Discovery

2021-09-29 · Yuke Li, Kenneth Li, Pin Wang, Donglai Wei, Hanspeter Pfister, Ching-Yao Chan

Non-stationary casual structures are prevalent in real-world physical systems. For example, the stacked blocks interacted with one another until they fall apart, while the billiard balls are moving independently until they collide. However, most video causal discovery methods can not discover such non-stationary casual structures due to the lack of modeling for the instantaneous change and the dynamics of the casual structure. In this work, we propose the Intervention-based Recurrent Casual Model (IRCM) for non-stationary video casual discovery. First, we extend the existing intervention-based casual discovery framework for videos to formulate the instantaneous change of the casual structure in a principled manner. Then, we use a recurrent model to sequentially predict the causal structure model based on previous observations to capture the non-stationary dynamic of the casual structure. We evaluate our method on two popular physical system simulation datasets with various types of multi-body interactions. Experimental results show that the proposed IRCM achieves the state-of-the-art performance on both the counterfactual reasoning and future forecasting tasks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Causal DiscoverycounterfactualCounterfactual Reasoning

Similar Papers 제목 키워드 기반

Inferring physical laws by artificial intelligence based causal models

2023-09-08 · Jorawar Singh, Kishor Bharti, Arvind

The advances in Artificial Intelligence (AI) and Machine Learning (ML) have opened up many avenues for scientific research, and are adding new dimensions to the process of knowledge creation. However, even the most power…

Causal Inferencescientific discovery

VidPanos: Generative Panoramic Videos from Casual Panning Videos

2024-10-17 · Jingwei Ma, Erika Lu, Roni Paiss, Shiran Zada 외

Panoramic image stitching provides a unified, wide-angle view of a scene that extends beyond the camera's field of view. Stitching frames of a panning video into a panoramic photograph is a well-understood problem for st…

Image StitchingVideo Generation

Causal Modeling with Stationary Diffusions

2023-10-26 · Lars Lorch, Andreas Krause, Bernhard Schölkopf

We develop a novel approach towards causal inference. Rather than structural equations over a causal graph, we learn stochastic differential equations (SDEs) whose stationary densities model a system's behavior under int…

Causal Inference

Asymmetric Graph Error Control with Low Complexity in Causal Bandits

2024-08-20 · Chen Peng, Di Zhang, Urbashi Mitra

In this paper, the causal bandit problem is investigated, in which the objective is to select an optimal sequence of interventions on nodes in a causal graph. It is assumed that the graph is governed by linear structural…

Change DetectionGraph Learning

Observational and Interventional Causal Learning for Regret-Minimizing Control

2022-12-05 · Christian Reiser

We explore how observational and interventional causal discovery methods can be combined. A state-of-the-art observational causal discovery algorithm for time series capable of handling latent confounders and contemporan…

Causal DiscoveryTime Series Analysis