Daniel Harari

Daniel Harari
Daniel
Harari
Research Affiliate
Massachusetts Institute of Technology (MIT), Weizmann Institute of Science
Department:  Department of Computer Science and Applied Mathematics
Lab Affiliation(s):  Poggio Lab Computer Vision Lab

Associated Research Thrust: 

Email:  hararid@mit.edu
Faculty Profile
Website: 
Advisor/s: 
Shimon Ullman, Tomaso Poggio, Gabriel Kreiman

Projects

Face Looking Behavior and Image Statistics in the Real World
Grounded language acquisition
Grounded question answering
Inferring "Theory of Mind" from Videos
Intentions and goals in human interactions
Multi-sentence event recognition
Objects and hands in context

CBMM Publications

D. Harari, Tenenbaum, J. B., and Ullman, S., “Discovery and usage of joint attention in images”, arXiv.org, 2018.
Y. Berzak, Barbu, A., Harari, D., Katz, B., and Ullman, S., “Language and Vision Ambiguities (LAVA) Corpus”. 2016.
S. Ullman, Assif, L., Fetaya, E., and Harari, D., “Atoms of recognition in human and computer vision”, PNAS , vol. 113, no. 10, pp. 2744–2749, 2016.
Y. Berzak, Barbu, A., Harari, D., Katz, B., and Ullman, S., “Do You See What I Mean? Visual Resolution of Linguistic Ambiguities”. 2016.
D. Harari, Gao, T., Kanwisher, N., Tenenbaum, J. B., and Ullman, S., “Measuring and modeling the perception of natural and unconstrained gaze in humans and machines”. 2016.
G. Ben-Yosef, Assif, L., Harari, D., and Ullman, S., “A model for full local image interpretation”, Cognitive Science Society . 2015.
Y. Berzak, Barbu, A., Harari, D., Katz, B., and Ullman, S., “Do You See What I Mean? Visual Resolution of Linguistic Ambiguities”, in Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal. , 2015.
T. Gao, Harari, D., Tenenbaum, J. B., and Ullman, S., “When Computer Vision Gazes at Cognition.”. 2014.