Infants' Physical World

By R. Baillargeon. 2004

240 citations recorded by the source corpus.

Subfields: Developmental and Educational Psychology, Social Psychology, Cognitive Science & Psychology

How researchers see this paper

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

In Developmental and Educational Psychology

In Social Psychology

In Cognitive Science & Psychology

Citations in the corpus

What can the brain teach us about building artificial intelligence? (2016, background): “By their first birthday, infants have gone through several transitions of comprehending basic physical concepts such as inertia, support, containment and collisions (Baillargeon, 2004; Baillargeon, Li, Ng, & Yuan, 2009; Hespos & Baillargeon, 2008).”
Unmasking Clever Hans predictors and assessing what machines really learn (2019, background): “A major difference between machine and human learning is that humans (even infants) are equipped with a “start-up” software [62, 63] consisting of a priori representation about objects and physics [64,65] and about other agents [66,67].”
Physics 101: Learning Physical Object Properties from Unlabeled Videos (2016, background): “objects sliding down on an inclined surface and possibly hitting other objects, are similar to classic experiments conducted by Galileo Galilei hundreds of years ago [10], and to experimental conditions in modern developmental psychology [2].”
SE3-nets: Learning rigid body motion using deep neural networks (2016, background): “Research has shown that humans learn these mental models from a young age, potentially by observing the effect of actions on the physical world [6].”
Spatio-temporal video autoencoder with differentiable memory (2015, background): “Moreover, the fact that infants are able to handle occlusion, containment, and covering events by the age of 2.5 months Baillargeon (2004) could suggest that the primary skills acquired by VSTM are related to extracting features useful for motion understanding.”
SCAN: Learning Hierarchical Compositional Visual Concepts (2017, background): “Intelligent agents are able to discover and learn abstract compositional concepts using little supervision (Baillargeon, 1987; Spelke, 1990; Baillargeon, 2004; Smith & Vul, 2013).”
Holistic++ Scene Understanding: Single-View 3D Holistic Scene Parsing and Human Pose Estimation With Human-Object Interaction and Physical Commonsense (2019, background): “ing occlusions [43, 20], tracking small objects even if contained by other objects [10], realizing object permanence [2], recognizing rational HOI [46, 37], understanding intuitive physic [11, 29, 1], and using exploratory play to understand the environment [42].”
Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning (2015, background): “Young babies are sensitive to physics of objects mainly from the motion of foreground objects from background [1]; in other words, they learn by watching videos of moving objects.”
Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery (2021, background): “Studies from cognitive science indicate observing the consequences of one’s actions plays a crucial role [17, 38, 3].”
Occlusion is hard: Comparing predictive reaching for visible and hidden objects in infants and adults (2009, background): “One limit stems from effects of memory on representations: when an object ceases to be visible, its existence and location must be remembered, and the precision of this memory may decline as the length of occlusion increases.”
Long-Term Image Boundary Prediction (2016, background): “Although some recent approaches such as (Battaglia et al. 2016; Watters et al. 2017) are capable of long-term predictions, they are modeling either state-to-state or images-to-state transitions.”
A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding (2016, background): “Precursors to them can be found in infants as young as 3-5 months old, even before children acquire their ﬁrst words labeling kinds of objects (Carey, 2009; Baillargeon, 2004).”
Building Machines that Learn and Think Like People (2018, background): “By their first birthday, infants have gone through several transitions of comprehending basic physical concepts such as inertia, support, containment and collisions (Baillargeon, 2004; Baillargeon, Li, Ng, & Yuan, 2009; Hespos & Baillargeon, 2008).”
Intuitive Theories (2020, background): “Over the course of childhood, our intuitive understanding of physics grows to become more and more sophisticated (for reviews, see Baillargeon, 2004; Spelke, Breinlinger, Macomber, & Jacobson, 1992).”
SCAN: Learning Abstract Hierarchical Compositional Visual Concepts (2017, background): “A more formal deﬁnition of concepts is provided in Sec. 3. Intelligent agents are able to discover and learn abstract compositional concepts using little supervision (Baillargeon, 1987; Spelke, 1990; Baillargeon, 2004; Smith & Vul, 2013). Think of human word learning – we acquire the meaning of ”
Investigating Human Priors for Playing Video Games (2018, background): “In addition to prior knowledge about objects, humans also bring in rich prior knowledge about intuitive physics and strong motor control priors when they approach a new task (Baillargeon, 1994; 2004; Hespos et al., 2009; Wolpert & Ghahramani, 2000).”
Developing Object Concepts in Infancy: An Associative Learning Perspective (2008, background): “Although the latter view is more often connected to the literature on language learning (for a review, see Markman, 1989), it is inherent in a number of theories relating to the development of concepts for animates and inanimates (e.g., Mandler, 1992; Spelke, 1994; Baillargeon, 2004).”
On the nature and origin of intuitive theories : learning, physics and psychology (2015, background): “A functional language of this sort would allow us to explore rich theories described in children, such as basic notions about objects and their interactions [169], and the intuitive physics of object behavior [5].”