Using Causal Induction in Humans to Learn and Infer Causality from Video

24 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Discovering Causal Signals in Images (2016, methodology): “Fire and Zhu [5, 6] use video data annotated with object status and actions to infer perceptual causality.”
Joint Video and Text Parsing for Understanding Events and Answering Queries (2013, methodology): “It has been employed in computer vision to model objects [6], scenes [7], [8] and events [9], [10].”
Visual Causal Feature Learning (2014, background): “ from image or video data does not generally consider the aggregation from pixel variables into causal macro-variables, but instead starts from annotated or pre-deﬁned features of the image (see e.g. Fire and Zhu (2013a,b)). 1.2CAUSAL FEATURE LEARNING: AN EXAMPLE Fig. 1 presents a paradigmatic case ”
Learning Perceptual Causality from Video (2013, methodology): “In this section we develop the theoretical framework for the learning theory, formulas of which were provided in [Fire and Zhu 2013b].”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, methodology): “14 [157]; in this study, systems learn how the status of a door, light, and screen relate to human actions.”
Exploring Causal Relationships in Visual Object Tracking (2015, methodology): “An example is Fire and Zhu [10], who use Causal AndOr Graphs and Bayesian grammar models for inference about hidden effects, otherwise undetected, or Sumioka et al. [34], using causality to learn joint attention for robots.”