Learning Object Permanence from Video

  title={Learning Object Permanence from Video},
  author={Aviv Shamsian and Ofri Kleinfeld and A. Globerson and Gal Chechik},
  • Aviv Shamsian, Ofri Kleinfeld, +1 author Gal Chechik
  • Published in ECCV 2020
  • Computer Science
  • Object Permanence allows people to reason about the location of non-visible objects, by understanding that they continue to exist even when not perceived directly. Object Permanence is critical for building a model of the world, since objects in natural visual scenes dynamically occlude and contain each-other. Intensive studies in developmental psychology suggest that object permanence is a challenging task that is learned through extensive experience. Here we introduce the setup of learning… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper


    Publications referenced by this paper.
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 18,935
    • PDF
    Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
    • 1,474
    • PDF
    The construction of reality in the child
    • 5,284
    • PDF
    Two-Stream Convolutional Networks for Action Recognition in Videos
    • 4,012
    • PDF
    Long Short-Term Memory
    • 31,867
    • PDF
    Attention is All you Need
    • 12,281
    • PDF
    Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
    • 1,856
    • PDF
    Distractor-aware Siamese Networks for Visual Object Tracking
    • 281
    • PDF
    Spatiotemporal Residual Networks for Video Action Recognition
    • 426
    • PDF
    Object permanence in young infants: further evidence.
    • 288
    • PDF