Publication
One- to Four-year-olds’ Ability to Connect Diverse Positive Emotional Expressions to Their Probable Causes . Society for Research in Child Development (2017).
Learning Scene Gist with Convolutional Neural Networks to Improve Object Recognition. arXiv | Cornell University arXiv:1803.01967, (2018).
A fine-grained understanding of emotions: Young children match within-valence emotional expressions to their causes. Cognitive Science Conference (CogSci) 2685-2690 (2015).
Cogsci Emotion pairings 2-4-15 Final version.pdf (729.07 KB)
MarrNet: 3D Shape Reconstruction via 2.5D Sketches. Advances in Neural Information Processing Systems 30 540–550 (2017). at <http://papers.nips.cc/paper/6657-marrnet-3d-shape-reconstruction-via-25d-sketches.pdf>
MarrNet: 3D Shape Reconstruction via 2.5D Sketches (6.25 MB)
Infants and toddlers leverage their understanding of action goals to evaluate agents who help others. Child Development (2023). doi:10.1111/cdev.13895
Eight-Month-Old Infants’ Social Evaluations of Agents Who Act on False Beliefs. Proceedings of the Annual Meeting of the Cognitive Science Society 44, (2022).
One Shot Learning via Compositions of Meaningful Patches. International Conference on Computer Vision (ICCV) (2015).
AlexWongOneShotCVPR2015.pdf (1.83 MB)
One Shot Learning by Composition of Meaningful Patches. International Conference on Computer Vision (ICCV) (2015).
AlexWongOneShotCVPR2015.pdf (1.83 MB)
Artificial intelligence insights into hippocampal processing. Frontiers in Computational Neuroscience 16, (2022).
Character-building stories. Advances in Cognitive Systems (2017).
. Marvin L. Minsky (1927–2016) Scientist and inventor was a visionary founder of AI. (2016).
Marvin L. Minsky (1927–2016) Scientist and inventor was a visionary founder of AI.pdf (559.42 KB)
. The Genesis Story Understanding and Story Telling System A 21st Century Step toward Artificial Intelligence. (2014).
CBMM-Memo-019_StoryWhitePaper.pdf (894.38 KB)
. Model-based Story Summary. 6th Workshop on Computational Models of Narrative (2015). doi:10.4230/OASIcs.CMN.2015.157
Localized task-invariant emotional valence encoding revealed by intracranial recordingsAbstract. Social Cognitive and Affective Neuroscience (2021). doi:10.1093/scan/nsab134
BrainBERT: Self-supervised representation learning for Intracranial Electrodes. International Conference on Learning Representations (2023). at <https://openreview.net/forum?id=xmcYx_reUn6>
985_brainbert_self_supervised_repr.pdf (9.71 MB)
Semantic Part Segmentation using Compositional Model combing Shape and Appearance. CVPR (2015).
JianyuWangSemanticCVPR2015 (1).pdf (6.15 MB)
Learning a natural-language to LTL executable semantic parser for grounded robotics. (2020). doi:https://doi.org/10.48550/arXiv.2008.03277
CBMM-Memo-122.pdf (1.03 MB)
Detecting Semantic Parts on Partially Occluded Objects. British Machine Vision Conference (BMVC) (2017). at <https://bmvc2017.london/proceedings/>
Learning a Natural-language to LTL Executable Semantic Parser for Grounded Robotics. (Proceedings of Conference on Robot Learning (CoRL-2020), 2020). at <https://corlconf.github.io/paper_385/>
A Geometric Analysis of Deep Generative Image Models and Its Applications. Proc. International Conference on Learning Representations, 2021 (2021).
Visual concepts and compositional voting. (2018).
CBMM-Memo-087.pdf (3.37 MB)
DOC: Deep OCclusion Recovering From A Single Image. ECCV (2016).
Visual Concepts and Compositional Voting. Annals of Mathematical Sciences and Applications (AMSA) 3, 151–188 (2018).
Mesoscopic physiological interactions in the human brain reveal small-world properties. Cell Reports 36, 109585 (2021).
]