paper-with-me

Papers

Towards Causal Physical Error Discovery in Video Analytics Systems

2024-05-27 · Jinjin Zhao, Ted Shaowang, Stavos Sintos, Sanjay Krishnan

Video analytics systems based on deep learning models are often opaque and brittle and require explanation systems to help users debug. Current model explanation system are very good at giving literal explanations of behavior in terms of pixel contributions but cannot integrate information about the physical or systems processes that might influence a prediction. This paper introduces the idea that a simple form of causal reasoning, called a regression discontinuity design, can be used to associate changes in multiple key performance indicators to physical real world phenomena to give users a more actionable set of video analytics explanations. We overview the system architecture and describe a vision of the impact that such a system might have.

📄 PDF Abstract BibTeX arXiv:2405.17686

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

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

2021-09-29 · Yuke Li, Kenneth Li, Pin Wang, Donglai Wei 외

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 th…

Causal DiscoverycounterfactualCounterfactual Reasoning

GRID: Graph-based Reasoning for Intervention and Discovery in Built Environments

2025-09-19 · Taqiya Ehsan, Shuren Xia, Jorge Ortiz arxiv

Manual HVAC fault diagnosis in commercial buildings takes 8-12 hours per incident and achieves only 60 percent diagnostic accuracy, reflecting analytics that stop at correlation instead of causation. To close this gap, w…

Fault Diagnosis

DOMINO: Visual Causal Reasoning with Time-Dependent Phenomena

2023-03-12 · Jun Wang, Klaus Mueller

Current work on using visual analytics to determine causal relations among variables has mostly been based on the concept of counterfactuals. As such the derived static causal networks do not take into account the effect…

Time Series Analysis

Common Action Discovery and Localization in Unconstrained Videos

2017-10-01 · ICCV 2017 10 · Jiong Yang, Junsong Yuan

Similar to common object discovery in images or videos, it is of great interests to discover and locate common actions in videos, which can benefit many video analytics applications such as video summarization, search, a…

Object DiscoveryVideo Summarization

Rethinking Chronological Causal Discovery with Signal Processing

2026-02-23 · Kurt Butler, Damian Machlanski, Panagiotis Dimitrakopoulos, Sotirios A. Tsaftaris arxiv

Causal discovery problems use a set of observations to deduce causality between variables in the real world, typically to answer questions about biological or physical systems. These observations are often recorded at re…