From simple innate biases to complex visual concepts
Open accessAbstract
Early in development, infants learn to solve visual problems that are highly challenging for current computational methods. We present a model that deals with two fundamental problems in which the gap between computational difficulty and infant learning is particularly striking: learning to recognize hands and learning to recognize gaze direction. The model is shown a stream of natural videos and learns without any supervision to detect human hands by appearance and by context, as well as direction of gaze, in complex natural scenes. The algorithm is guided by an empirically motivated innate mechanism--the detection of "mover" events in dynamic images, which are the events of a moving image region causing a stationary region to move or change after contact. Mover events provide an internal teaching signal, which is shown to be more effective than alternative cues and sufficient for the efficient acquisition of hand and gaze representations. The implications go beyond the specific tasks, by showing how domain-specific "proto concepts" can guide the system to acquire meaningful concepts, which are significant to the observer but statistically inconspicuous in the sensory input.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Pre-specification of mutual supervision signals can make learning the relevant features of the world far easier, by giving an otherwise unsupervised learner the right kinds of hints or heuristic biases at the right times.
“Their broader claim is that such pre-specification of mutual supervision signals can make learning the relevant features of the world far easier, by giving an otherwise unsupervised learner the right kinds of hints or heuristic biases at the right times.”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Ullman et al., 2012
Ullman's hand detector operates via a simple local optical flow calculation to detect 'mover' events.
“Ullman's hand detector, in fact, operates via a simple local optical flow calculation to detect “mover” events.”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Ullman et al., 2012
Special internally generated signals are needed for learning problems where standard unsupervised methods fail to discover properties of the world that are statistically weak but significant to the organism.
“Special, internally-generated signals are needed specifically for learning problems where standard unsupervised methods—based purely on matching the statistics of the world, or on optimizing simple mathematical objectives like temporal continuity or sparsity—will fail to discover properties of the world which are statistically weak in an objective sense but nevertheless have special significance”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Ullman et al., 2012
Hands are important because they allow us to learn about the set of actions that can be produced by agents.
“Hands are important because they allow us to learn about the set of actions that can be produced by agents (Ullman et al., 2012).”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Ullman et al., 2012
In Ullman et al. (2012), appearance, body context, and mover motion are all used to bootstrap off of one another, creating a detector that is better than any of its training heuristics.
“In Ullman et al. (2012), appearance, body context, and mover motion are all used to bootstrap off of one another, creating a detector that is better than any of its training heuristics.”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Ullman et al., 2012
The work of Ullman et al. (2012) illustrates that bootstrapping does not pose a chicken-and-egg problem because an innate detector can train a downstream detector based on different cues, and multiple detection pathways can improve each other.
“The work of Ullman et al. (2012) illustrates why this is not the case. First, the “innate detector” can be used to train a downstream detector that operates based on different cues: for example, based on the spatial and body context of the hand, rather than its motion. Second, once multiple such pathways of detection come into existence, they can be used to improve each other.”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Ullman et al., 2012
An internally supervised learning algorithm containing specialized, hard-coded biases to detect hands, on the basis of their typical motion properties, can be used to bootstrap the training of an image recognition module that learns to recognize hands based on their appearance.
“Indeed, an internally supervised learning algorithm containing specialized, hard-coded biases to detect hands, on the basis of their typical motion properties, can be used to bootstrap the training of an image recognition module that learns to recognize hands based on their appearance.”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Ullman et al., 2012
Generalizing previous ideas, the brain uses optimization with respect to internally generated heuristic detection signals to bootstrap learning of biologically relevant features which would otherwise be missed by an unsupervised learner.
“Thus, generalizing previous ideas (Ullman et al., 2012; Poggio, 2015), we suggest that the brain uses optimization with respect to internally generated heuristic39 detection signals to bootstrap learning of biologically relevant features which would otherwise be missed by an unsupervised learner.”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Ullman et al., 2012
Ullman et al. (2012) further exploits a combination of hand and face detection to bootstrap a predictor for gaze direction, based on the heuristic that faces tend to be looking toward hands.
“Ullman et al. (2012) then further exploits a combination of hand and face detection to bootstrap a predictor for gaze direction, based on the heuristic that faces tend to be looking toward hands.”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Ullman et al., 2012
Internally generated signals may allow a learning system to go beyond standard unsupervised methods by guiding or steering it to learn specific features or computations.
“These internally generated signals may allow a learning system to go beyond what can be learned via standard unsupervised methods, effectively guiding or steering the system to learn specific features or computations (Ullman et al., 2012).”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Ullman et al., 2012
Visual data streams can be segmented into elements such as foreground versus background and objects that can move of their own accord versus those that cannot, using diverse unsupervised criteria.
“For example, visual data streams can be segmented into elements like foreground vs. background, objects that can move of their own accord vs. those that cannot, all using diverse unsupervised criteria (Ullman et al., 2012; Poggio, 2015).”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Ullman et al., 2012
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · see citing works
The origins of intelligence in children.
Piaget, J. (1952) · doi:10.1037/11494-000 · Cited by 10,687 · see citing works
Information theory, inference, and learning algorithms
(2004) · Choice Reviews Online · doi:10.5860/choice.41-5949 · Cited by 6,535 · see citing works
The Cultural Origins of Human Cognition
Tomasello, M. (2009) · doi:10.2307/j.ctvjsf4jc · Cited by 6,368 · see citing works
Bradski, G. R. (2000) · Medical Entomology and Zoology · Cited by 5,994 · see citing works
Information Theory, Inference, and Learning Algorithms
(2004) · Kybernetes · doi:10.1108/03684920410534506 · Cited by 4,937 · see citing works
PINKER, S. (1999) · Annals of the New York Academy of Sciences · doi:10.1111/j.1749-6632.1999.tb08538.x · Cited by 3,738 · see citing works
Jordan, M. I. (1998) · Springer eBooks · doi:10.1007/978-94-011-5014-9 · Cited by 2,449 · see citing works
Carey, S. E. (2000) · Oxford University Press eBooks · doi:10.1037/e513702014-002 · Cited by 2,324 · see citing works
Infants selectively encode the goal object of an actor's reach
Woodward, A. L. (1998) · Cognition · doi:10.1016/s0010-0277(98)00058-4 · Cited by 1,977 · see citing works
How to grow a mind: Statistics, structure, and abstraction
Tenenbaum, J. B., Kemp, C., Griffiths, T. L., & Goodman, N. D. (2011) · Science · doi:10.1126/science.1192788 · Cited by 1,815 · see citing works
The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields
Black, M. J., & Anandan, P. (1996) · Computer Vision and Image Understanding · doi:10.1006/cviu.1996.0006 · Cited by 1,571 · see citing works
Rational imitation in preverbal infants
Gergely, G., Bekkering, H., & Király, I. (2002) · Nature · doi:10.1038/415755a · Cited by 1,391 · see citing works
Michotte, A. (2017) · Routledge eBooks · doi:10.4324/9781315519050 · Cited by 1,311 · see citing works
Head Pose Estimation in Computer Vision: A Survey
Murphy-Chutorian, E., & Trivedi, M. M. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.106 · Cited by 1,304 · see citing works
Modeling attention to salient proto-objects
Walther, D. B., & Christof Koch, A. (2006) · Neural Networks · doi:10.1016/j.neunet.2006.10.001 · Cited by 1,235 · see citing works
Measuring the Objectness of Image Windows
Alexe, B., Deselaers, T., & Ferrari, V. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.28 · Cited by 1,182 · see citing works
The capacity for joint visual attention in the infant
Scaife, M., & Bruner, J. S. (1975) · Nature · doi:10.1038/253265a0 · Cited by 1,158 · see citing works
Spelke, E. S., & Kinzler, K. D. (2007) · Developmental Science · doi:10.1111/j.1467-7687.2007.00569.x · Cited by 1,089 · see citing works
Learning multiple layers of representation
Hinton, G. E. (2007) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2007.09.004 · Cited by 1,016 · see citing works
Mirrors in the Brain—How Our Minds Share Actions and Emotions
Rizzolatti, G., Sinigaglia, C., & Anderson, F. S. (2007) · doi:10.1093/oso/9780199217984.001.0001 · Cited by 1,001 · see citing works
Biology and cognitive development: the case of face recognition
(1992) · Choice Reviews Online · doi:10.5860/choice.30-0600 · Cited by 892 · see citing works
Action experience alters 3-month-old infants' perception of others' actions
Sommerville, J. A., Woodward, A. L., & Needham, A. (2005) · Cognition · doi:10.1016/j.cognition.2004.07.004 · Cited by 817 · see citing works
Alexe, B., Deselaers, T., & Ferrari, V. (2010) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2010.5540226 · Cited by 778 · see citing works
Visual Perception and the Statistical Properties of Natural Scenes
Geisler, W. S. (2007) · Annual Review of Psychology · doi:10.1146/annurev.psych.58.110405.085632 · Cited by 732 · see citing works
Foundations for a new science of learning
Meltzoff, A. N., Kuhl, P. K., Movellan, J., & Sejnowski, T. J. (2009) · Science · doi:10.1126/science.1175626 · Cited by 723 · see citing works
The infant's theory of self-propelled objects
Premack, D. (1990) · Cognition · doi:10.1016/0010-0277(90)90051-k · Cited by 658 · see citing works
Visual features of intermediate complexity and their use in classification
Ullman, S., Vidal-Naquet, M., & Sali, E. (2002) · Nature Neuroscience · doi:10.1038/nn870 · Cited by 600 · see citing works
Self-citationInfants predict other people's action goals
Falck‐Ytter, T., Gredebäck, G., & von Hofsten, C. (2006) · Nature Neuroscience · doi:10.1038/nn1729 · Cited by 563 · see citing works
Recovering human body con .gurations:combining segmentation and recognition
Mori, G., Ren, X., Efros, A. A., & Malik, J. (2004) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2004.1315182 · Cited by 510 · see citing works
Face perception in monkeys reared with no exposure to faces
Sugita, Y. (2008) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0706079105 · Cited by 465 · see citing works
Letting structure emerge: connectionist and dynamical systems approaches to cognition
McClelland, J. L., Botvinick, M., Noelle, D. C., Plaut, D. C., Rogers, T. T., Seidenberg, M. S., & Smith, L. B. (2010) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2010.06.002 · Cited by 457 · see citing works
Can a Self-Propelled Box Have a Goal?: Psychological Reasoning in 5-Month-Old Infants
Luo, Y., & Baillargeon, R. (2005) · Psychological Science · doi:10.1111/j.1467-9280.2005.01582.x · Cited by 406 · see citing works
A demonstration of gaze following in 3- to 6-month-olds
D’Entremont, B., Hains, S. M. J., & Muir, D. W. (1997) · Infant Behavior and Development · doi:10.1016/s0163-6383(97)90048-5 · Cited by 389 · see citing works
Spatial Priors for Part-Based Recognition Using Statistical Models
Crandall, D., Felzenszwalb, P. F., & Huttenlocher, D. P. (2005) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2005.329 · Cited by 279 · see citing works
Spatiotemporal Continuity and the Perception of Causality in Infants
Leslie, A. M. (1984) · Perception · doi:10.1068/p130287 · Cited by 258 · see citing works
View-Based Encoding of Actions in Mirror Neurons of Area F5 in Macaque Premotor Cortex
Caggiano, V., Fogassi, L., Rizzolatti, G., Pomper, J. K., Thier, P., Giese, M. A., & Casile, A. (2011) · Current Biology · doi:10.1016/j.cub.2010.12.022 · Cited by 223 · see citing works
What's in View for Toddlers? Using a Head Camera to Study Visual Experience
Yoshida, H., & Smith, L. B. (2008) · Infancy · doi:10.1080/15250000802004437 · Cited by 216 · see citing works
Secret Agents: Inferences About Hidden Causes by 10- and 12-Month-Old Infants
Saxe, R., Tenenbaum, J. B., & Carey, S. (2005) · Psychological Science · doi:10.1111/j.1467-9280.2005.01649.x · Cited by 210 · see citing works
Measuring the Development of Social Attention Using Free‐Viewing
Frank, M. C., Vul, E., & Saxe, R. R. (2011) · Infancy · doi:10.1111/j.1532-7078.2011.00086.x · Cited by 192 · see citing works
Gaze-following: its development and significance
(2007) · Choice Reviews Online · doi:10.5860/choice.44-4733 · Cited by 160 · see citing works
A parallel algorithm for real-time computation of optical flow
Bülthoff, H., Little, J., & Poggio, T. (1989) · Nature · doi:10.1038/337549a0 · Cited by 158 · see citing works
The Development of Infant Sensitivity to Biomechanical Motions
Bertenthal, B. I., Proffítt, D. R., Spetner, N. B., & Thomas, M. A. (1985) · Child Development · doi:10.2307/1129742 · Cited by 147 · see citing works
Smooth-Pursuit Eye Movements in the Newborn Infant
Kremenitzer, J. P., Vaughan, H. G., Kurtzberg, D., & Dowling, K. (1979) · Child Development · doi:10.1111/j.1467-8624.1979.tb04127.x · Cited by 124 · see citing works
Detector adaptation by maximising agreement between independent data sources
Conaire, C. Ó., O'Connor, N. E., & Smeaton, A. F. (2007) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2007.383448 · Cited by 105 · see citing works
Smooth-Pursuit Eye Movements in the Newborn Infant
Kremenitzer, J. P., Vaughan, H. G., Kurtzberg, D., et al. (1979) · Child Development · doi:10.2307/1129421 · Cited by 101 · see citing works
The chains model for detecting parts by their context
Karlinsky, L., Dinerstein, M., Harari, D., & Ullman, S. (2010) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2010.5540232 · Cited by 78 · see citing works
Self-citationHow Infants View Natural Scenes Gathered From a Head‐Mounted Camera
Aslin, R. Ν. (2009) · Optometry and Vision Science · doi:10.1097/opx.0b013e3181a76e96 · Cited by 71 · see citing works
(2017) · Psychology Press eBooks · doi:10.4324/9781315093741 · Cited by 61 · see citing works
Infant shifting attention from an adult’s face to an adult’s hand: a precursor of joint attention
Amano, S., Kezuka, E., & Yamamoto, A. (2003) · Infant Behavior and Development · doi:10.1016/j.infbeh.2003.06.005 · Cited by 61 · see citing works
Neural theory for the perception of causal actions
Fleischer, F., Christensen, A., Caggiano, V., Thier, P., & Giese, M. A. (2012) · Psychological Research · doi:10.1007/s00426-012-0437-9 · Cited by 22 · see citing works
When do infants expect hands to be connected to a person?
Slaughter, V. P., & Heron‐Delaney, M. (2010) · Journal of Experimental Child Psychology · doi:10.1016/j.jecp.2010.08.005 · Cited by 8 · see citing works
Do young infants respond socially to human hands?
Slaughter, V. P., & Neary, P. (2011) · Infant Behavior and Development · doi:10.1016/j.infbeh.2011.01.004 · Cited by 4 · see citing works
Aspects of Motion Perception in Infancy
Kaufmann, F. (1987) · Advances in psychology · doi:10.1016/s0166-4115(08)60347-7 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Building machines that learn and think like people
Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2017) · Behavioral and Brain Sciences · doi:10.1017/s0140525x16001837 · Cited by 2,550 · see citing works
Yu, C., & Smith, L. B. (2013) · PLoS ONE · doi:10.1371/journal.pone.0079659 · Cited by 434 · see citing works
Traversing psychological distance
Liberman, N., & Yaacov Trope, B. (2014) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2014.03.001 · Cited by 411 · see citing works
From faces to hands: Changing visual input in the first two years
Fausey, C. M., Jayaraman, S., & Smith, L. B. (2016) · Cognition · doi:10.1016/j.cognition.2016.03.005 · Cited by 278 · see citing works
Using neuroscience to develop artificial intelligence
Ullman, S. (2019) · Science · doi:10.1126/science.aau6595 · Cited by 231 · see citing works
Self-citationHand–Eye Coordination Predicts Joint Attention
Yu, C., & Smith, L. B. (2017) · Child Development · doi:10.1111/cdev.12730 · Cited by 187 · see citing works
Multiple Sensory‐Motor Pathways Lead to Coordinated Visual Attention
Yu, C., & Smith, L. B. (2016) · Cognitive Science · doi:10.1111/cogs.12366 · Cited by 160 · see citing works
Toward an integration of deep learning and neuroscience
Marblestone, A. H., Wayne, G., & Kording, K. P. (2016) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2016.00094 · Cited by 119 · see citing works
McMahon, E., & Işık, L. (2023) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2023.09.001 · Cited by 114 · see citing works
Origins of the concepts cause, cost, and goal in prereaching infants
Liu, S., Brooks, N. B., & Spelke, E. S. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1904410116 · Cited by 85 · see citing works
The functional neuroanatomy of face perception: from brain measurements to deep neural networks
Kalanit Grill-spector, A., Weiner, K. S., Gomez, J., Anthony Stigliani, A., & Natu, V. S. (2018) · Interface Focus · doi:10.1098/rsfs.2018.0013 · Cited by 78 · see citing works
Face detection in untrained deep neural networks
Baek, S., Song, M. J., Jang, J., Kim, G., & Paik, S. (2021) · Nature Communications · doi:10.1038/s41467-021-27606-9 · Cited by 74 · see citing works
Visual number sense in untrained deep neural networks
Kim, G., Jang, J., Baek, S., Song, M. J., & Paik, S. (2021) · Science Advances · doi:10.1126/sciadv.abd6127 · Cited by 70 · see citing works
Where and Why are They Looking? Jointly Inferring Human Attention and Intentions in Complex Tasks
Wei, P., Liu, Y., Shu, T., Zheng, N., & Zhu, S. C. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00711 · Cited by 67 · see citing works
Lessons from infant learning for unsupervised machine learning
Zaadnoordijk, L., Besold, T. R., & Cusack, R. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00488-2 · Cited by 65 · see citing works
Coupling perception to action through incidental sensory consequences of motor behaviour
Rolfs, M., & Schweitzer, R. (2022) · Nature Reviews Psychology · doi:10.1038/s44159-021-00015-x · Cited by 65 · see citing works
Caggiano, V., Fleischer, F., Pomper, J. K., Giese, M. A., & Thier, P. (2016) · Current Biology · doi:10.1016/j.cub.2016.10.007 · Cited by 57 · see citing works
Learning as the Unsupervised Alignment of Conceptual SystemsPreprint
Roads, B. D., & Love, B. (2019) · doi:10.17605/osf.io/ndrmg · Cited by 42 · see citing works
The Unbearable Shallow Understanding of Deep Learning
Plebe, A., & Grasso, G. M. (2019) · Minds and Machines · doi:10.1007/s11023-019-09512-8 · Cited by 37 · see citing works
Mind the gap: challenges of deep learning approaches to Theory of Mind
Aru, J., Labash, A., Corcoll, O., & Vicente, R. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10401-x · Cited by 37 · see citing works
Relational visual representations underlie human social interaction recognition
Malik, M., & Işık, L. (2023) · Nature Communications · doi:10.1038/s41467-023-43156-8 · Cited by 32 · see citing works
Learning as the unsupervised alignment of conceptual systems
Roads, B. D., & Love, B. C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0132-2 · Cited by 51 · see citing works
Animacy and the prediction of behaviour
Schultz, J., & Frith, C. (2022) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2022.104766 · Cited by 32 · see citing works
Vision: are models of object recognition catching up with the brain?
Poggio, T., & Ullman, S. (2013) · Annals of the New York Academy of Sciences · doi:10.1111/nyas.12148 · Cited by 29 · see citing works
Self-citationThe development of Bayesian integration in sensorimotor estimation
Chambers, C., Sokhey, T., Gaebler-Spira, D. J., & Kording, K. P. (2018) · Journal of Vision · doi:10.1167/18.12.8 · Cited by 28 · see citing works
Objects in the center: How the infant's body constrains infant scenes
Bambach, S., Smith, L. B., Crandall, D., & Yu, C. (2016) · IEEE International Conference on Development and Learning (ICDL) · doi:10.1109/devlrn.2016.7846804 · Cited by 27 · see citing works
Face identity coding in the deep neural network and primate brain
Wang, J., Cao, R., Brandmeir, N. J., Li, X., & Wang, S. (2022) · Communications Biology · doi:10.1038/s42003-022-03557-9 · Cited by 24 · see citing works
The Predictive Processing Model of EMDR
Chamberlin, D. E. (2019) · Frontiers in Psychology · doi:10.3389/fpsyg.2019.02267 · Cited by 22 · see citing works
Tian, M., & Kalanit Grill-spector, A. (2015) · Journal of Vision · doi:10.1167/15.6.7 · Cited by 18 · see citing works
Unsupervised Segmentation in Real-World Images via Spelke Object Inference
Chen, H., Venkatesh, R., Friedman, Y., Wu, J., Tenenbaum, J. B., Yamins, D. L. K., & Bear, D. M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19818-2_41 · Cited by 18 · see citing works
Infants’ Attributions of Insides and Animacy in Causal Interactions
Kominsky, J. F., Li, Y., & Carey, S. E. (2022) · Cognitive Science · doi:10.1111/cogs.13087 · Cited by 17 · see citing works
Learning what you can do before doing anythingPreprint
Rybkin, O., Pertsch, K., Derpanis, K. G., Daniilidis, K., & Jaegle, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.09655 · Cited by 17 · see citing works
Gaze following requires early visual experience
Zohary, E., Harari, D., Ullman, S., Ben-Zion, I., Doron, R., Attias, S., Porat, Y., Sklar, A. Y., & McKyton, A. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2117184119 · Cited by 16 · see citing works
Self-citationQuantum computing and neuroscience for 6G/7G networks: Survey
Glisic, S., & Lorenzo, B. (2024) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2024.200346 · Cited by 15 · see citing works
Outline of a Theory of Delusion: Irrationality and Pathological Belief
Gold, I. (2017) · Elsevier eBooks · doi:10.1016/b978-0-12-804600-5.00006-4 · Cited by 14 · see citing works
Brain-inspired automated visual object discovery and detection
Chen, L.-C., Singh, S. K., Kailath, T., & Roychowdhury, V. (2018) · Proceedings of the National Academy of Sciences of the United States of America · doi:10.1073/pnas.1802103115 · Cited by 15 · see citing works
Bambach, S., Franchak, J. M., Crandall, D., & Yu, C. (2014) · eScholarship (California Digital Library) · Cited by 13 · see citing works
A model for discovering ‘containment’ relations
Ullman, S., Dorfman, N., & Harari, D. (2018) · Cognition · doi:10.1016/j.cognition.2018.11.001 · Cited by 13 · see citing works
Self-citationBalaskas, S., & Rigou, M. (2023) · Pan-Hellenic Conference on Progress in Computing and Informatics (PCI) · doi:10.1145/3635059.3635081 · Cited by 12 · see citing works
Yu, C., & Smith, L. B. (2015) · PubMed · Cited by 12 · see citing works
Emergent Goal‐Anticipatory Gaze in Infants via Event‐Predictive Learning and Inference
Gumbsch, C., Adam, M., Elsner, B., & Butz, M. V. (2021) · Cognitive Science · doi:10.1111/cogs.13016 · Cited by 10 · see citing works
Emulating human-like adaptive vision for efficient and flexible machine visual perception
Wang, Y., Yang, Y., Yue, Y., Wang, H., Jiang, H., Han, Y., Ni, Z., Pu, Y., Shi, M., Lu, R., et al. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01130-7 · Cited by 9 · see citing works
When Computer Vision Gazes at CognitionPreprint
Gao, T., Harari, D., Tenenbaum, J. B., & Ullman, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.2672 · Cited by 7 · see citing works
Self-citationLearning What to Learn Across the Life Span: From Objects to Real-World Skills
Wu, R. (2019) · Current Directions in Psychological Science · doi:10.1177/0963721419847994 · Cited by 6 · see citing works
Visual Neuroscience: Seeing Causality with the Motor System?
Rolfs, M. (2016) · Current Biology · doi:10.1016/j.cub.2016.09.046 · Cited by 6 · see citing works
Leshinskaya, A., & Thompson‐Schill, S. L. (2019) · Journal of Experimental Psychology General · doi:10.1037/xge0000594 · Cited by 6 · see citing works
Dramatic action: A theater-based paradigm for analyzing human interactions
Liron, Y., Raindel, N., & Alon, U. S. (2018) · PLoS ONE · doi:10.1371/journal.pone.0193404 · Cited by 5 · see citing works
What deep learning can tell us about higher cognitive functions like mindreading?Preprint
Aru, J., & Vicente, R. (2018) · doi:10.31234/osf.io/9skeq · Cited by 5 · see citing works
Rubio‐Fernández, P., Shukla, V., Bhatia, V., Ben-Ami, S., & Sinha, P. (2022) · Neuropsychologia · doi:10.1016/j.neuropsychologia.2022.108330 · Cited by 4 · see citing works
Yoshimi, R., Takeno, M., Toyota, Y., Tsuchida, N., Sugiyama, Y., Kunishita, Y., Kishimoto, D., Kamiyama, R., Minegishi, K., Hama, M., et al. (2016) · Modern Rheumatology · doi:10.1080/14397595.2016.1206173 · Cited by 4 · see citing works
Learning to perceive coherent objects
Dorfman, N., Harari, D., & Ullman, S. (2013) · eScholarship (California Digital Library) · Cited by 4 · see citing works
Self-citationMaouene, J., Sethuraman, N., Maouene, M., & Otieno, S. (2015) · Language and Cognition · doi:10.1017/langcog.2014.48 · Cited by 3 · see citing works
Psychologie cognitive expérimentale
Dehaene, S. (2014) · L’annuaire du Collège de France · doi:10.4000/annuaire-cdf.2464 · Cited by 3 · see citing works
Unsupervised Learning of Sensorimotor Affordances by Stochastic Future Prediction.Preprint
Rybkin, O., Pertsch, K., Jaegle, A., Derpanis, K. G., & Daniilidis, K. (2018) · arXiv (Cornell University) · Cited by 3 · see citing works
Kominsky, J. F., & Wenig, K. (2025) · Cognitive Science · doi:10.1111/cogs.70107 · Cited by 2 · see citing works
Human concerned object detecting in video
Li, J., Guo, J., & Fan, H. (2015) · Journal of Advanced Mechanical Design Systems and Manufacturing · doi:10.1299/jamdsm.2015jamdsm0072 · Cited by 2 · see citing works
Toddlers Working Memory Development via Visual Attention and Visual Sequential-Memory
Raihan, M. E., Akther, U. R., Afrin, S., Chowdhury, F. M., & Sarker, M. R. (2019) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit48885.2019.9038580 · Cited by 2 · see citing works
A Schema-Based Robot Controller Complying With the Constraints of Biological Systems
Lagriffoul, F. (2022) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2022.836767 · Cited by 2 · see citing works
Leshinskaya, A., Bajaj, M. A., & Thompson‐Schill, S. L. (2022) · Cerebral Cortex · doi:10.1093/cercor/bhac442 · Cited by 2 · see citing works
Action as an innate bias for visual learning
Yuille, A., & Bülthoff, H. (2012) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1215851109 · Cited by 2 · see citing works
High-Level Perceptual Similarity is Enabled by Learning Diverse TasksPreprint
Rosenfeld, A., Zemel, R., & Tsotsos, J. K. (2019) · arXiv (Cornell University) · doi:10.13140/rg.2.2.13104.20483 · Cited by 2 · see citing works
Le révérend Bayes, la phénoménologie et les bébés
Chesnel, J., & Hendrickx, M. (2021) · La psychiatrie de l enfant · doi:10.3917/psye.642.0037 · Cited by 1 · see citing works
Animacy and the prediction of behaviourPreprint
Schultz, J., & Frith, C. (2020) · doi:10.31234/osf.io/2k4mj · Cited by 1 · see citing works
A study in human attention to guide computational action recognition
Sinai, S. (2014) · DSpace@MIT (Massachusetts Institute of Technology)
Minimal Nativism: How does cognitive development get off the ground?
Ullman, T. D., Tenenbaum, J. B., Goodman, N. D., Ullman, S., & Spelke, E. S. (2013) · eScholarship (California Digital Library)
Self-citationChallenging Images For Minds and MachinesPreprint
Rosenfeld, A., & Tsotsos, J. K. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.04834
Discussion: Biological Plausibility of the Model
Jang, J., & Paik, S. (2022) · KAIST research series · doi:10.1007/978-981-19-0031-0_5
Liron, Y., Raindel, N., & Alon, U. (2018) · doi:10.31234/osf.io/qzked
Eleanor Jack Gibson: A Life in Science
Spelke, E. S. (2024) · Annual Review of Developmental Psychology · doi:10.1146/annurev-devpsych-080823-010040
Expert-level understanding of social scenes requires early visual experience
Naveh, I., Attias, S., Sklar, A. Y., Ben-Zion, I., & Zohary, E. (2025) · iScience · doi:10.1016/j.isci.2025.112454
An attentional-bias account of language emergence
Reynolds, B. (2026) · Evolutionary Linguistic Theory · doi:10.1075/elt.26001.rey
Selection-for-prediction: rethinking early cognitive development
Lourenco, S. F. (2026) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2026.09.013
- Authors
- Ullman, S., Harari, D., & Dorfman, N.
- Affiliations
- Weizmann Institute of Science (IL)
- Venue
- Proceedings of the National Academy of Sciences
- Publisher
- National Academy of Sciences
- Published
- 2012-09-24
- Volume
- 109
- Issue
- 44
- Pages
- 18215-18220
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- PMC
- PMC3497814
- OpenAlex
- W2023906772
- Cited by
- 77
- References
- 53
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 2 · 2023: 4 · 2022: 13 · 2021: 6 · 2020: 3 · 2019: 9 · 2018: 10 · 2017: 2 · 2016: 9 · 2015: 4 · 2014: 5 · 2013: 4 · 2012: 1
- FWCI
- 4.61
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Proceedings of the National Academy of Sciences (publishedVersion)
- Europe PMC (PubMed Central) (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Life Sciences › Neuroscience › Cognitive Neuroscience › Visual perception and processing mechanisms
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- hand detection, unsupervised learning, dynamic scene analysis
- MeSH terms
- Hand, Humans, Task Performance and Analysis, Visual Perception
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
