Sample Publications

  1. Books:

    S. Ullman. The Interpretation of Visual Motion. Cambridge, MA. The MIT Press, 1979. Russian Edition, 1984.

    S. Ullman and W. Richards (eds). Image Understanding 1984. New Jersey: Ablex Publishing Co. Includes an introduction by S. Ullman, 5-19, 1984.

    W. Richards and S. Ullman (eds). Image Understanding 1985-1986. New Jersey: Ablex Publishing Co., 1986.

    S. Ullman and W. Richards (eds). Image Understanding 1989. New Jersey: Ablex Publishing Co., 1990.

    S. Ullman. High-level Vision: Object Recognition and Visual Cognition. Cambridge, MA: The MIT Press, 1996.

    Ullman, S. and Epshtein, B. Visual classification by a hierarchy of extended fragments. Towards Category-Level Object Recognition Springer, 2006, pp. 321-344, J. Ponce, M. Hebert, C. Schmid and A. Zisserman (eds.)

    Ullman, S. Beyond Classification. Object Categorization: Computer and Human Vision Perspectives Cambridge University Press, 2009, Dickinson (ed.)

    Vidal-Naquet, M., Ullman, S., Tanifuji, M. Extracting MAX-pooling receptive fields with natural image fragments. Frontiers in Systems Neuroscience COSYNE meeting, 2009

    Ullman, S. Forward to David Marr: Vision MIT Press, 2010

  2. Sample Publications:

    Ullman, S. (1995). Sequence-seeking and counter streams: A computational model for bi-directional information flow in the visual cortex. Cerebral Cortex, 5(1) 1-11. link

    Bar, M. and Ullman, S. (1996). Spatial context in recognition. Perception, 25 343-352. pdf 205kb

    Moses, Y., Ullman, S. and Edelman, S. (1996). Generalization to novel images in upright and inverted faces. Perception, 25 443-461.pdf 395kb

    Adini, Y., Moses, Y. and Ullman, S. (1997). Face recognition: the problem of compensating for changes in illumination direction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19, 721-732. link

    Ullman, S. and Zeria, A. (1997). Object recognition using stochastic optimization. Proceedings of the Venice Meeting on Optimization in Computer Vision. Springer-Verlag.

    Ullman, S. (1998). Three-dimensional object recognition based on the combination of views. Cognition, 67(1) 21-44. pdf 298kb

    Moses, Y. and Ullman, S. (1998). Generalization to novel views: Universal, class-based and model-based processing. International Journal of Computer Vision, 29(3) 233-253. pdf 204kb

    Sali, E. and Ullman, S. (1998). Recognizing novel 3-D objects under new illumination and viewing position using a small number of example views or even a single view. Proceedings of the Sixth International Conference on Computer Vision, Bombay, India, 153-161.

    Ullman, S. & Solovieiv, S. (1999) Computation of pattern invariance in brain-like structures. Neural Networks, 12, 1021-1036. pdf 1,398kb

    Sali, E. & Ullman, S. (1999) Combining class-specific fragments for object classification. In Proc. 10th British Machine Vision Conference, volume 1, 203 - 213. pdf 2,070kb

    Sali, E. & Ullman, S.(1999) Detecting object classes by the detection of overlapping 2-D fragments. In: D. Chernikov & T. Szinanyi, (eds.) Proceedings of the Workshop on Fundamental Structural Properties in Image and Pattern Analysis, 123-132. Published by OCG, Austrian Computer Society.

    Ullman, S. & Sali, E.(2000) Object Classification Using a Fragment-Based Representatio. In: Seong-Whan Lee, Heinrich H. Bulthoff, Tomaso Poggio (eds.): Biologically Motivated Computer Vision, First IEEE International Workshop, BMVC 2000, Seoul, Korea, May 15-17, Proc. Lecture Notes in Computer Science 1811 Springer, 73-87. pdf 968kb

    Ullman, S., Sali, E. & Vidal-Naquet, M. (2001) A fragment-based approach to object representation and classification. In: A. Arcelli, L.P. Cordella & G. Sanniti di Baja (eds.), International Workshop on Visual Form, Berlin: Springer, 85-100. pdf 741kb

    Borenstein, E. & Ullman, S. (2001) Class specific top down-segmentation. Proceedings of the European Conference on Computer Vision, 110-122. pdf 1,248kb

    Gilaie-Dotan, S., Ullman, S., Kushnir, T., Malach, R. (2001) Shape-selective stereo processing in human object-related visual areas. Human Brain Mapping 15, 67-79. pdf 895kb

    Ullman, S., Vidal-Naquet, M. , and Sali, E. (2002) Visual features of intermediate complexity and their use in classification. Nature Neuroscience, 5(7), 1-6. pdf 640kb

    Zur, D., Ullman, S. (2003) Filling of Retinal scotomas. Vision Research, 43

    Ullman, S. (2003) Approaches to visual recognition. Attention and Performance XX, Oxford University Press. link

    Bart, E., Byvatov, E., Ullman, S. (2004) View-invariant recognition using corresponding object fragments. ECCV, LNCS 3023, 152-165, Prague link

    E. Borenstein and S. Ullman (2004) Learning to segment. ECCV, LNCS 3023, 315-328, Prague link

    E. Borenstein and S. Ullman (2004) Combining bottom-up and top-down segmentation. CVPR workshop on Perceptual Organization in Computer Vision link

    E. Bart and S. Ullman (2004) Class-based matching of object parts. CVPR Workshop on Image and Video Registration link

    E. Bart and S. Ullman (2004) Image normalization by mutual information. BMVC link

    E. Bart and S. Ullman (2005) Learning a novel class from a single example by cross-generalization. CVPR, pp. 1063-1069 link

    Vidal Naquet, M. Miyakawa, N., Sato, T., Nakahara, H., Ullman, S. and Tanifuji, M. (2005) A fragment based approach for the characterization of V1 receptive fields. SFN Abstract link

    Ecker, A. and Ullman, S. (2005) A hierarchical non-parametric method for capturing non-rigid transformation. Canadian Robotics and Vision Conference, pp. 50-56 link

    Bart, E. and Ullman, S. (2005) Single-example learning of novel classes using representation by similarity. BMVC, Oxford, England link

    Epshtein, B. and Ullman, S. (2005) Identifying semantically equivalent object parts. CVPR, pp. 2-9 link

    Epshtein, B. and Ullman, S. (2005) Hierarchical features for object classification. ICCV, pp. 220-227 link

    Fink, M., Shalev-Shwartz, S., Singer, Y. and Ullman, S. (2006) Online Multiclass Learning by Interclass Hypothesis Sharing. ICML, pp. 313-320 link

    Levi, D. and Ullman. (2006) Learning to classify by ongoing feature selection. CRV, Recipient of Best CRV Paper Award. link

    Epstein, B. and Ullman, S. (2006) Satellite Features for the Classification of Visually Similar Classes. CVPR, pp. 2079-2086. link

    Bart, E. and Ullman, S. (2006) Object recognition by eliminating distracting information. ICCVG, Warsaw, Poland. link

    Epshtein, B. and Ullman, S. (2007) Semantic Hierarchies for recognizing objects and parts. CVPR, pp. 1-8. link

    Amit, Y., Srebro, N., Ullman, S. and Fink, M. (2007) Uncovering Shared Structures in Multiclass Classification. ICML, 227, pp. 17-24. link

    Karlinsky, L. Dinershtein, M. Levi, D. Ullman, S. (2008) Unsupervised Classification and Part Localization by Consistency Amplification. ECCV, vol. 2, pp. 321-335. link

    Karlinsky, L. Dinershtein, M. Levi, D. Ullman, S. (2008) Combined model for detecting, localizing and recognizing faces. ECCV Workshop on Faces in Real-life Images, pp. 1-14. link

    Karlinsky, L. Dinershtein, D. Ullman, S. (2009) Unsupervised feature optimization (UFO): Simultaneous selection of multiple features with their detection parameters. CVPR, pp. 1263-1270. link

    Levi, D. and Ullman, S. (2009) Learning model complexity in an online environment. CRV, pp. 260-267, IAPR Best Paper Award for 2009. link

    Karlinsky L., Dinerstein M., Harari D., and Ullman S. (2010) The chains model for detecting parts by their context. CVPR, 2010. pdf 3636kb

    Karlinsky, L. Dinershtein, D. Ullman, S. (2010) Using body-anchored priors for identifying actions in single images. Neural Information Processing, 1-9, 2010. link

    • Harel, A., Ullman, S., Harari, D., Bentin, S.: Basic-level categorization of intermediate complexity fragments reveals top-down effects of expertise in visual perception. Journal of Vision, 11(8), 1-13, 2011.

    • Ullman, S., Harari, D. and Dorfman, N. (2012). From simple innate biases to complex visual concepts. Proceeding of the National Academy of Sciences - PNAS 109(44): 18215-18220. PDF Project

    • Poggio, T. & Ullman, S.: Vision are models of object recognition catching up with the brain? Ann. N.Y. Acad. Sci. nyas.12148 1-11, 2013.

    • Dorfman, N., Harari, D. and Ullman, S. (2013): Learning to Perceive Coherent Objects. Proceedings of the Annual Meeting of the Cognitive Science Society - CogSci, pp 394-399. PDF Slides Winner of the 2013 Marr Prize

    • Ben-Yosef, G., Assif, L., Harari, D., Ullman, S. (2015). A Model for Full Local Image Interpretation. The Annual Conference of the Cognitive Science Society - CogSci PDF

    • Berzak, Y., Barbu, A., Harari, D., Katz, B., Ullman, S.: Do You See What I Mean? Visual Resolution of Linguistic Proc. Empirical Methods on Natural Language Processing, 2015

    • Ullman, S., Assif, L., Fetaya, E., Harari, D. (2016): Atoms of Recognition in Human and Computer Vision. Proceedings of the National Academy of Sciences - PNAS (in press) PDF Project