Events & Talks

Optics and Sensing Laboratory Talk 29-07-2015 Novel optical sensing technologies Coherent light enables optical measurements of exquisite sensitivity, advancing technologies for improved sensing and autonomous systems. From my previous work on gravitational physics, I will present a brief overview on technologies for laser-interferometric gravitational-wave observatories, particularly within the scope of the European mission LISA Pathfinder, to be launched at the end 2015. In addition, I will talk about my current work in novel and highly compact optomechanical systems and photonic crystals, optical micro-resonators with sensitivities below femtometer levels, as ... Senya Polikovsky

Empirical Inference IS Colloquium 27-07-2015 New Foundations for Ockham’s Razor in Statistical Inductive Inference, with Applications to Causal Discovery from Non-experimental Data In machine learning, the standard explanation of Ockham's razor is to minimize predictive risk. But prediction is interpreted passively---one may not rely on predictions to change the probability distribution used for training. That limitation may be overcome by studying alternatively manipulated systems in randomized experimental trials, but experiments on multivariate systems or on human subjects are often infeasible or immoral. Happily, the past three decades have witnessed the development of a range of statistical techniques for discovering causal relations from non-experimental dat... Michel Besserve Kun Zhang

Symposium 24-07-2015 Günter Petzow Colloquium (interesting speakers and talks - mostly in German) Seit 2002 veranstaltet das Institut am Standort Stuttgart ein wissenschaftliches Kolloquium, das der Kontaktpflege mit den Alumni und Freunden des Instituts dient. Wir bitten um Anmeldung bis 30. Juni 2015, entweder per Post oder unter: www.is.mpg.de/gpk2015

Talk 16-07-2015 (Matter) Waves in disordered media The propagation of waves in inhomogeneous media is a vast subject, spanning many different research communities. The ability of waves to interfere leads to the celebrated phenomenon of Anderson localization. Constructive interference increases the probability of return and therefore it can reduce or even cancel the propagation in a disordered medium. Anderson localization was first predicted for electrons in 'dirty' condensed matter systems, very soon however, it was generalized to all kind of waves and has been studied since with light, microwaves, ultrasound, and ultra cold atoms. Here... Senya Polikovsky

Empirical Inference Conference 13-07-2015 - 24-07-2015 MLSS 2015 - Machine Learning Summer School 2015 in Tübingen MLSS's are a renowned venue for graduate students, researchers, and professionals. They offer an opportunity to learn about fundamental and advanced aspects of machine learning, data analysis and inference, from intellectual leaders of the field. In the summer of 2015 the MLSS will make its fourth appearance in Tübingen. Michael Hirsch Philipp Hennig Bernhard Schölkopf

Symposium 12-07-2015 Symposium on Intelligent Systems in Science and Industry (SISSI) Symposium on Intelligent Systems / Alumni Meeting of MPI-IS: Claudia Daefler Matthias Tröndle

Perceiving Systems Talk 10-07-2015 Reading and Writing the Neural Code: Challenges in Neuroengineering The external world is represented in the brain as spatiotemporal patterns of electrical activity. Sensory signals, such as light, sound, and touch, are transduced at the periphery and subsequently transformed by various stages of neural circuitry, resulting in increasingly abstract representations through the sensory pathways of the brain. It is these representations that ultimately give rise to sensory perception. Deciphering the messages conveyed in the representations is often referred to as “reading the neural code”. True understanding of the neural code requires knowledge of not on... Jonas Wulff

Autonomous Motion Talk 06-07-2015 Autonomous Systems At Moog The talk will briefly introduce Moog Inc. It will then describe Moog's view of its value proposition to robotics and autonomous systems. If robots and autonomous system are to achieve their enormous potential to positively impact the world economy, the technology has to achieve equivalent the levels of robustness, availability, reliability and safety that are expected from current solutions. The commercial aircraft industry has seen an order of magnitude increase in machine complexity in the last fifty years in order to reach the highest ever levels of cost per seat-mile and safety in it... Ludovic Righetti

Perceiving Systems Talk 26-06-2015 Perceptual representation learning across diverse modalities and domains Learning of layered or "deep" representations has provided significant advances in computer vision in recent years, but has traditionally been limited to fully supervised settings with very large amounts of training data. New results show that such methods can also excel when learning in sparse/weakly labeled settings across modalities and domains. I'll present our recent long-term recurrent network model which can learn cross-modal translation and can provide open-domain video to text transcription. I'll also describe state-of-the-art models for fully convolutional pixel-dense segmentati... Jonas Wulff

Autonomous Motion Talk 16-06-2015 Biomechanics of legged locomotion - experiments, models, robots and assistive devices In this presentation a series of conceptual models for describing human and animal locomotion will be presented ranging from standing to walking and running. By subsequently increasing the complexity of the models we show that basic properties of the underlying spring-mass model can be inherited by the more detailed models. Model extensions include the consideration of a rigid trunk (instead of a point mass), non-elastic leg properties (instead of a mass-less leg spring), additional legs (two and four legs), leg masses, leg segments (e.g. a compliantly attached foot) and energy mana...

Autonomous Motion Talk 16-06-2015 Biomechanics of legged locomotion - experiments, models, robots and assistive devices In this presentation a series of conceptual models for describing human and animal locomotion will be presented ranging from standing to walking and running. By subsequently increasing the complexity of the models we show that basic properties of the underlying spring-mass model can be inherited by the more detailed models. Model extensions include the consideration of a rigid trunk (instead of a point mass), non-elastic leg properties (instead of a mass-less leg spring), additional legs (two and four legs), leg masses, leg segments (e.g. a compliantly attached foot) and energy mana... Ludovic Righetti

Perceiving Systems Talk 10-06-2015 Learning Rich and Fair Representations from Images and Text I will talk about two types of machine learning problems, which are important but have received little attention. The first are problems naturally formulated as learning a one-to-many mapping, which can handle the inherent ambiguity in tasks such as generating segmentations or captions for images. A second problem involves learning representations that are invariant to certain nuisance or sensitive factors of variation in the data while retaining as much of the remaining information as possible. The primary approach we formulate for both problems is a constrained form of joint emb... Gerard Pons-Moll

Max Planck Lecture 20-05-2015 Ultracold atoms as quantum simulators for new materials – synthetic magnetic fields and topological phases When atoms are cooled to nanokelvin temperatures, they can easily be confined and manipulated with laser beams. Their interactions can be tuned with the help of magnetic fields, making them strongly or weakly interacting, repulsive or attractive.

Perceiving Systems Talk 18-05-2015 3D Image Analysis and Synthesis -- The World inside the Computer During the last three decades computer graphics established itself as a core discipline within computer science and information technology. Two decades ago, most digital content was textual. Today it has expanded to include audio, images, video, and a variety of graphical representations. New and emerging technologies such as multimedia, social networks, digital television, digital photography and the rapid development of new sensing devices, telecommunication and telepresence, virtual reality, or 3D-internet further indicate the potential of computer graphics...

Perceiving Systems Talk 04-05-2015 Learning and understanding visual representations Learnable representations, and deep convolutional neural networks (CNNs) in particular, have become the preferred way of extracting visual features for image understanding tasks, from object recognition to semantic segmentation. In this talk I will discuss several recent advances in deep representations for computer vision. After reviewing modern CNN architectures, I will give an example of a state-of-the-art network in text spotting; in particular, I will show that, by using only synthetic data and a sufficiently large deep model, it is possible directly map image regions to Englis...

Event 10-04-2015 - 12-03-2015 DALI 2015 – Data, Learning and Inference The idea of DALI is to combine the special qualities of the former Snowbird meetings (intimate atmosphere, very good people, plenty of time to interact) with positive aspects of larger conferences that rarely take place in Europe. We decided for a three day format with two days of workshops, and one day of plenary talks in the middle, including a poster session. We chose an attractive location in a nearby time zone, which limits travel times for many of us who normally travel to meetings in the US. We have initially circulated this link only to a small list of people with the hope that we c...

Perceiving Systems IS Colloquium 24-03-2015 From Perceptual Evidence to Large-Scale Visual Recognition Models Recent progress in computer-based visual recognition heavily relies on machine learning methods trained using large scale annotated datasets. While such data has made advances in model design and evaluation possible, it does not necessarily provide insights or constraints into those intermediate levels of computation, or deep structure, perceived as ultimately necessary in order to design reliable computer vision systems. This is noticeable in the accuracy of state of the art systems trained with such annotations, which still lag behind human performance in similar tasks. Nor does the exist...

Autonomous Motion Talk 20-03-2015 Bio-inspired robotics and the use of robotics to validate neuro-mechanical models of animal locomotion Ludovic Righetti

Talk 18-03-2015 Modelling in the Context of Massively Missing Data In the age of large streaming data it seems appropriate to revisit the foundations of what we think of as data modelling. In this talk I'll argue that traditional statistical approaches based on parametric models and i.i.d. assumptions are inappropriate for the type of large scale machine learning we need to do in the age of massive streaming data sets. Particularly when we realise that regardless of the size of data we have, it pales in comparison to the data we could have. This is the domain of massively missing data. I'll be arguing for flexible non-parametric models as the answer. T... Jane Walters

Perceiving Systems Talk 11-03-2015 Of Breasts and Symbols: A Visual Journey through Twenty-Five Centuries of Western Art and Culture The breast is not just a protruding gland situated on the front of the thorax in female bodies: behind biology lies an intricate symbolism that has taken various and often contradictory meanings.  We begin our journey looking at pre-historic artifacts that revered the breast as the ultimate symbol of life; we then transition to the rich iconographical tradition centering on the so-called Virgo Lactans when the breast became a metaphor of nourishment for the entire Christian community. Next, we look at how artists have eroticized the breast in portraits of fifteenth-century French court...

Max Planck Lecture 09-03-2015 Aerial Robot Swarms Autonomous micro aerial robots can operate in three-dimensional, indoor and outdoor environments, and have applications to search and rescue, first response and precision farming. I will describe the challenges in developing small, agile robots and the algorithmic challenges in the areas of (a) control and planning, (b) state estimation and mapping, and (c) coordinating large teams of robots.

Autonomous Motion Talk 09-03-2015 Quadrupedal locomotion: a planning & control framework for HyQ It is a great pleasure to invite you to the talk of Ioannis Havoutis (cf. info below) on Monday March 9th at 11h in the AMD seminar room (TTR building, first floor). have a nice week-end, ludovic Quadrupedal animals move with skill, grace and agility. Quadrupedal robots have made tremendous progress in the last few years. In this talk I will give an overview of our work with the Hydraulic Quadruped -HyQ- and present our latest framework for perception, planning and control of quadrupedal locomotion in challenging environments. In addition, I will give a short preview of our ... Ludovic Righetti

Perceiving Systems Talk 26-02-2015 "Real stupidity beats artificial intelligence every time" (Terry Pratchett) How is it that biological systems can be so imprecise, so ad hoc, and so inefficient, yet accomplish (seemingly) simple tasks that still elude state-of-the-art artificial systems? In this context, I will introduce some of the themes central to CMU's new BrainHub Initiative by discussing: (1) The complexity and challenges of studying the mind and brain; (2) How the study of the mind and brain may benefit from considering contemporary artificial systems; (3) Why studying the mind and brain might be interesting (and possibly useful) to computer scientists.

Perceiving Systems Talk 24-02-2015 Balancing Speed and Fidelity in Physics Based Animation and Control In this talk I will give an overview of work I have done over the years exploring physically based simulation of contact, deformation, and articulated structures where there are trade-offs between computational speed and physical fidelity that can be made.  I will also discuss examples that mix data-driven and physically based approaches in animation and control. Paul Kry is an associate professor in the School of Computer Science at McGill University.  He has a BMath from University of Waterloo, and MSc and PhD from University of British Columbia.  His res...

Perceiving Systems Talk 18-02-2015 What is biological motion? Everyone in visual psychology seems to know what Biological Motion is. Yet, it is not easy to come up with a definition that is specific enough to justify a distinct label, but is also general enough to include the many different experiments to which the term has been applied in the past. I will present a number of tasks, stimuli, and experiments, including some of my own work, to demonstrate the diversity and the appeal of the field of biological motion perception. In trying to come up with a definition of the term, I will particularly focus on a type of motion that has been consider...

Perceiving Systems Talk 17-02-2015 Reconstructing Complete 3D Models from Single Images We present an approach to creating 3D models of objects depicted in Web images, even when each object may only be shown in a single image. Our approach uses a comparatively small collection of existing 3D models to guide the reconstruction process. These existing shapes are used to derive information about shape structure. Our guiding idea is to jointly analyze the images and the available 3D models. Joint analysis of all images along with the available shapes regularizes the formulated optimization problems, stabilizes estimation of camera parameters and construction of dense pixel-level c...

Perceiving Systems IS Colloquium 16-02-2015 Reflecting in and on the Gradient Domain Image-based rendering has been introduced in the 1990s as an alternative approach to photorealistic rendering. Its key idea is to novel renderings by re-projecting pixels from nearby views. The basic approach works well for many scenes but breaks down if the scene contains “non-standard” elements such as reflective surfaces. In this talk, I will first show how we can extend image-based rendering to handle scenes with reflections. I will then discuss a novel gradient-based technique for image-based rendering that can intrinsically handle scenes with reflections.</pre>

Talk 26-01-2015 Haptics: The Technology of Touch When you touch objects in your surroundings, you can discern each item’ s physical properties from the rich array of haptic cues you experience, including both the tactile sensations arising in your skin and the kinesthetic cues originating in your muscles and joints. Although physical interaction with the world is at the core of human experience, few computer and machine interfaces provide the operator with high-fidelity touch feedback, limiting their usability . Similarly , autonomous robots rarely take advantag... Jane Walters

Autonomous Motion IS Colloquium 19-01-2015 Introduction to the Scenario Approach The scenario approach is a broad methodology to deal with decision-making in an uncertain environment. By resorting to observations, or by sampling uncertainty from a given model, one obtains an optimization problem (the scenario problem), whose solution bears precise probabilistic guarantees in relation to new, unseen, situations. The scenario approach opens up new avenues to address data-based problems in learning, identification, finance, and other fields. Sebastian Trimpe

Perceiving Systems Symposium 10-12-2014 - 13-12-2014 Scenes from Videos Workshop This invitation-only workshop will bring together experts in the field to focus on the problem of estimating Scenes from Video. In so doing, we hope to draw several lines of research together to address the problem of extracting physical and semantic information from video.

Event 23-11-2014 - 25-11-2014 Computer Vision Workshop As a follow up meeting on the RNLS (Research Network on Learning Systems) at the ETH Zürich in June 2014, we will organise the Computer Vision Breakout Meeting on the MPI IS Campus in Tuebingen. This meeting is to bring together researchers from both institutions, MPI IS and ETH Zürich, to exchange ideas, knowledge and experiences and learn from each other.

Perceiving Systems Talk 28-10-2014 Capturing and simulating the interaction of light with the world around us Driven by the increasing demand for photorealistic computer-generated images, graphics is currently undergoing a substantial transformation to physics-based approaches which accurately reproduce the interaction of light and matter. Progress on both sides of this transformation -- physical models and simulation techniques -- has been steady but mostly independent from another. When combined, the resulting methods are in many cases impracticably slow and require unrealistic workarounds to process even simple everyday scenes. My research lies at the interface of these two research fields; my g...

Perceiving Systems IS Colloquium 15-10-2014 Images everywhere - computer vision with vehicle-mounted, airborne and tourist cameras I will present selected research projects of the Photogrammetry and Remote Sensing Group at ETH, including (i) 3D scene flow estimation for stereo video captured from a car; (ii) extraction of road networks from aerial images; and (iii) 3D reconstruction from large, unstructured (e.g. crowd-sourced) image collections.

Perceiving Systems Talk 15-09-2014 Weak-supervision for Objects Detection and Image/Video Set Summarization The growing scale of image and video datasets in vision makes labeling and annotation of such datasets, for training of recognition models, difficult and time consuming. Further, richer models often require richer labelings of the data, that are typically even more difficult to obtain. In this talk I will focus on two models that make use of different forms of supervision for two different vision tasks.   In the first part of this talk I will focus on object detection. The appearance of an object changes profoundly with pose, camera view and interactions of the ...

Perceiving Systems Talk 04-09-2014 Hands and Dolphins: Modelling Non-Rigid Shape with Subdivision Surfaces Abstract: I will present a general framework for modelling and recovering 3D shape and pose using subdivision surfaces. To demonstrate this frameworks generality, I will show how to recover both a personalized rigged hand model from a sequence of depth images and a blend shape model of dolphin pose from a collection of 2D dolphin images. The core requirement is the formulation of a generative model in which the control vertices of a smooth subdivision surface are parameterized (e.g. with joint angles or blend weights) by a differentiable deformation function. The energy function that fal...

Perceiving Systems Talk 29-08-2014 Discovering Object Classes from Activities In order to avoid an expensive manual labeling process or to learn object classes autonomously without human intervention, object discovery techniques have been proposed that extract visual similar objects from weakly labelled videos. However, the problem of discovering small or medium sized objects is largely unexplored. We observe that videos with activities involving human-object interactions can serve as weakly labelled data for such cases. Since neither object appearance nor motion is distinct enough to discover objects in these videos, we propose a framework that samples from a s...

Empirical Inference IS Colloquium 11-08-2014 Examples of Machine Learning and Data Science at Facebook Facebook serves close to a billion people every day, who are only able to consume a small subset of the information available to them. In this talk I will give some examples of how machine learning is used to personalize people’s Facebook experience. I will also present some data science experiments with fairly counter-intuitive results.

Perceiving Systems Talk 22-07-2014 Reconstructing the Pascal VOC Dataset and Non-Rigid Structure from Motion: Two sides of the same problem? In this talk I will discuss two related problems in 3D reconstruction: (i) recovering the 3D shape of a temporally varying non-rigid 3D surface given a single video sequence and (ii) reconstructing different instances of the same object class category given a large collection of images from that category. In both cases we extract dense 3D shape information by analysing shape variation -- in one case of the same object instance over time and in the other across different instances of objects that belong to the same class. First I will discuss the problem of dense capture of 3D ...

Empirical Inference IS Colloquium 15-07-2014 Approximate inference for stochastic differential equations Stochastic differential equations (SDEs) arise naturally as descriptions of continuous time dynamical systems. My talk addresses the problem of inferring the dynamical state and parameters of such systems from observations taken at discrete times. I will discuss the application of approximate inference methods such as the variational method and expectation propagation and show how higher dimensional systems can be treated by a mean field approximation. In the second part of my talk I will discuss the nonparametric estimation of the drift (i.e. the deterministic part of the ‘force’ whi... Philipp Hennig Michel Besserve

Perceiving Systems IS Colloquium 14-07-2014 4D reconstruction in complex scenes, inverse rendering, advanced video editing Even though many challenges remain unsolved, in recent years computer graphics algorithms to render photo-realistic imagery have seen tremendous progress. An important prerequisite for high-quality renderings is the availability of good models of the scenes to be rendered, namely models of shape, motion and appearance. Unfortunately, the technology to create such models has not kept pace with the technology to render the imagery. In fact, we observe a content creation bottleneck, as it often takes man months of tedious manual work by a animation artists to craft models of moving virtual sce... Gerard Pons-Moll

Empirical Inference IS Colloquium 23-06-2014 Compressive Sensing and Beyond The recent theory of compressive sensing predicts that (approximately) sparse vectors can be recovered from vastly incomplete linear measurements using efficient algorithms. This principle has a large number of potential applications in signal and image processing, machine learning and more. Optimal measurement matrices in this context known so far are based on randomness. Recovery algorithms include convex optimization approaches (l1-minimization) as well as greedy methods. Gaussian and Bernoulli random matrices are provably optimal in the sense that the smallest possible number of... Michel Besserve

Event 16-06-2014 - 20-06-2014 Summer School: Research Network on Learning Systems (at ETH Zurich) The inaugural summer school of the joint ETH/MPI Research Network on Learning Systems will feature tutorial lectures and practicals on various topics related to Learning Systems. In particular, researchers from the Max Planck Institute for Intelligent Systems and ETH Zurich will present introductory and advanced topics in areas such as Statistical Machine Learning, Robotics / Control and Computer Vision.

Perceiving Systems Talk 11-06-2014 Getting the People Right: A Physical Anthropologist's View of Digital Human Modeling for Virtual Environments A goal in virtual reality is for the user to experience a synthetic environment as if it were real. Engagement with virtual actors is a big part of the sensory context, thus getting the people "right" is critical for success. Size, shape, gender, ethnicity, clothing, color, texture, movement, among other attributes must be layered and nuanced to provide an accurate encounter between an actor and a user. In this talk, I discuss the development of digital human models and how they may be improved to obtain the high realism for successful engagement in a virtual world.

Perceiving Systems Talk 10-06-2014 Convex Methods for Dense Semantic 3D Reconstruction Volumetric 3D modeling has attracted a lot of attention in the past. In this talk I will explain how the standard volumetric formulation can be extended to include semantic information by using a convex multi-label formulation. One of the strengths of our formulation is that it allows us to directly account for the expected surface orientations. I will focus on two applications. Firstly, I will introduce a method that allows for joint volumetric reconstruction and class segmentation. This is achieved by taking into account the expected orientations of object classes such as ground and build...

Empirical Inference Symposium 04-06-2014 - 06-06-2014 IEEE Conference on Pattern Recognition in Neuroimaging, Tübingen 2014 Multivariate analysis of neuroimaging data has gained ground very rapidly in the community over the past few years, leading to impressive results in cognitive and clinical neuroscience. Pattern recognition and machine learning conferences regularly feature a neuroimaging workshop, while neuroscientific meetings dedicate sessions to new approaches to neural data analysis. Thus, a rich two-way flow has been established between disciplines. It is the goal of the PRNI workshop series to continue facilitating exchange of ideas between scientific communities, with a particular interest in new app... Moritz Grosse-Wentrup

Empirical Inference IS Colloquium 26-05-2014 Low-rank dynamics This talk reviews differential equations on manifolds of matrices or tensors of low rank. They serve to approximate, in a low-rank format, large time-dependent matrices and tensors that are either given explicitly via their increments or are unknown solutions of differential equations. Furthermore, low-rank differential equations are used in novel algorithms for eigenvalue optimisation, for instance in robust-stability problems. Philipp Hennig

Max Planck Lecture 22-05-2014 The Glassy State properties and applications exploiting non-crystallinity: golf, frozen frogs, memory Glasses, lacking the order of crystals, are in many ways still regarded as poorly understood. Yet glasses, lacking the complications of different crystallographic symmetries, also show some remarkable correlations of diverse properties.

Autonomous Motion IS Colloquium 19-05-2014 Embedded Optimization for Nonlinear Model Predictive Control This talk shows how embedded optimization - i.e. autonomous optimization algorithms receiving data, solving problems, and sending answers continuously - are able to address challenging control problems. When nonlinear differential equation models are used to predict and optimize future system behaviour, one speaks of Nonlinear Model Predictive Control (NMPC).The talk presents experimental applications of NMPC to time and energy optimal control of mechatronic systems and discusses some of the algorithmic tricks that make NMPC optimization rates up to 1 MHz possible. Finally, we present on pa... Sebastian Trimpe

Perceiving Systems IS Colloquium 12-05-2014 Towards Lifelong Learning for Visual Scene Understanding The goal of lifelong visual learning is to develop techniques that continuously and autonomously learn from visual data, potentially for years or decades. During this time the system should build an ever-improving base of generic visual information, and use it as background knowledge and context for solving specific computer vision tasks. In my talk, I will highlight two recent results from our group on the road towards lifelong visual scene understanding: the derivation of theoretical guarantees for lifelong learning systems and the development of practical methods for object categori... Gerard Pons-Moll

Perceiving Systems Talk 06-05-2014 Depth ambiguity and perceptual biases in biological motion perception Point-light walkers and stick figures rendered orthographically and without self-occlusion do not contain any information as to their depth. For instance, a frontoparallel projection could depict a walker from the front or from the back. Nevertheless, observers show a strong bias towards seeing the walker as facing the viewer. A related stimulus, the silhouette of a human figure, does not seem to show such a bias. We develop these observations into a tool to study the cause of the facing the viewer bias observed for biological motion displays. I will give a short overview ab...

Research

Departments

Research Groups

People

Contact

Our Institute

Our History

Career

Doctoral Programs

Training

Service Units

Central Scientific Facilities

Workshops

Campus Services

Impact

Cooperation

Partners and Initiatives