HUMAINE: towards a sound foundation for emotion-oriented computing
Prof Roddy Cowie, coordinator of the EU-funded network of excellence project HUMAINE
9th of December, 12.00 - 13.00,
DSV, floor 7, C-elevator, Forum-building, Kista
Emotion pervades human experience and communication, but machines are blind to it. That constrains their communication, and specifically forces the humans to adapt to the machines’ style. Changing that imbalance is a challenge with far reaching implications for the information sciences, and the main outcome of early efforts has been to underline how difficult it is. The new network of excellence HUMAINE rests on the judgment that real progress depends on looking beyond natural preconceptions and short term goals; pooling expertise from very different disciplines, from signal processing to AI to experimental psychology to philosophy; and establishing a shared understanding of the nature and scale of the challenge.
Everybody is most welcome!
Please bring your lunch.
Professor at DSV
A new Kernel method for object recognition: Spin Glass-Markov random fields
Respondent: Barbara Caputo
Opponent: Prof Kalle Åström, LU
Huvudhandledare: Prof Stefan Arnborg
26 november, 14.15,
sal F2, Lindstedtsvägen 28
Recognizing objects through vision is an important part of our lives: we recognize people when we talk to them, we recognize our cup on the breakfast table, our car in a parking lot, and so on. While this task is performed with great accuracy and apparently little effort by humans, it is still unclear how this performance is achieved. Creating computer methods for automatic object recognition gives rise to challenging theoretical problems
such as how to model the visual appearance of the objects or categories we want to recognize, so that the resulting algorithm will perform robustly in realistic scenarios; to this end, how to use effectively multiple cues (such as shape, color, textural properties and many others), so that the algorithm uses the best subset of cues in the most effective manner; how to use specific features and/or specific strategies for different classes.
The present work is devoted to the above issues. We propose to model the visual appearance of objects and visual categories via probability density functions. The model is developed on the basis of concepts and results obtained in three different research areas:
computer vision, machine learning and statistical physics of spin glasses. It consists of a fully connected Markov random field with energy function derived from results of statistical physics of spin glasses. Markov random fields and spin glass energy functions are combined together via nonlinear kernel functions; we call the model Spin Glass\– Markov Random Fields. Full connectivity enables to take into account the global appearance of the object, and its specific local characteristics at the same time, resulting in robustness to noise, occlusions and cluttered background. Because of properties of some classes of spin glass\–like energy functions, our model allows to use easily and effectively multiple cues, and to employ class specific strategies. We show with theoretical analysis and experiments
that this new model is competitive with state\–of\–the\–art algorithms for object recognition.