Performance metrics are a key component of machine learning systems, and are ideally constructed to reflect real world tradeoffs. In contrast, much of the literature simply focuses on algorithms for maximizing accuracy. With the increasing integration of machine learning into real systems, it is clear that accuracy is an insufficient measure of performance for many problems of interest. Unfortunately, unlike accuracy, many real world performance metrics are non-decomposable i.e. cannot be computed as a sum of losses for each instance. Thus, known algorithms and associated analysis are not trivially extended, and direct approaches require expensive combinatorial optimization. I will outline recent results characterizing population optimal classifiers for large families of binary and multilabel classification metrics, including such nonlinear metrics as F-measure and Jaccard measure. Perhaps surprisingly, the prediction which maximizes the utility for a range of such metrics takes a simple form. This results in simple and scalable procedures for optimizing complex metrics in practice. I will also outline how the same analysis gives optimal procedures for selecting point estimates from complex posterior distributions for structured objects such as graphs. Joint work with Nagarajan Natarajan, Bowei Yan, Kai Zhong, Pradeep Ravikumar and Inderjit Dhillon.
Organizers: Mijung Park
Creating convincing human facial animation is challenging. Face animation is often hand-crafted by artists separately from body motion. Alternatively, if the face animation is derived from motion capture, it is typically performed while the actor is relatively still. Recombining the isolated face animation with body motion is non-trivial and often results in uncanny results if the body dynamics are not properly reflected on the face (e.g. cheeks wiggling when running). In this talk, I will discuss the challenges of human soft tissue simulation and control. I will then present our method for adding physical effects to facial blendshape animation. Unlike previous methods that try to add physics to face rigs, our method can combine facial animation and rigid body motion consistently while preserving the original animation as closely as possible. Our novel simulation framework uses the original animation as per-frame rest-poses without adding spurious forces. We also propose the concept of blendmaterials to give artists an intuitive means to control the changing material properties due to muscle activation.
Organizers: Timo Bolkart
I'll present my master thesis "Biquadratic Forms and Semi-Definite Relaxations". It is about biquadratic optimization programs (which are NP-hard generally) and examines a condition under which there exists an algorithm that finds a solution to every instance of the problem in polynomial time. I'll present a counterexample for which this is not possible generally and face the question of what happens if further knowledge about the variables over which we optimise is applied.
Organizers: Fatma Güney
A large part of image analysis is about breaking things into pieces. Decompositions of a graph are a mathematical abstraction of the possible outcomes. This talk is about optimization problems whose feasible solutions define decompositions of a graph. One example is the correlation clustering problem whose feasible solutions relate one-to-one to the decompositions of a graph, and whose objective function puts a cost or reward on neighboring nodes ending up in distinct components. This talk shows applications of this problem and proposed generalizations to diverse image analysis tasks. It sketches algorithms for finding feasible solutions for large instances in practice, solutions that are often superior in the metrics of application-specific benchmarks. It also sketches algorithms for finding lower bounds and points to new findings and open problems of polyhedral geometry in this context.
Organizers: Christoph Lassner
Colloquium on haptics: Two guests of the department "Haptic Intelligence" (Dept. Kuchenbecker), will each give a short talk this Friday (May 5) in Tübingen. The talks will be broadcasted to Stuttgart, room 2 P4.
Estimating human pose, shape, and motion from images and video are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of manually-labeled training data for learning convolutional neural networks (CNNs). Such data is time consuming to acquire and difficult to extend. Moreover, manual labeling of 3D pose, depth and motion is impractical. In this work we present SURREAL: a new large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data. We generate more than 6 million frames together with ground truth pose, depth maps, and segmentation masks. We show that CNNs trained on our synthetic dataset allow for accurate human depth estimation and human part segmentation in real RGB images. Our results and the new dataset open up new possibilities for advancing person analysis using cheap and large-scale synthetic data.
Organizers: Dimitris Tzionas
Human-centric robotic applications often require the robots to learn new skills by interacting with the end-users. From a machine learning perspective, the challenge is to acquire skills from only few interactions, with strong generalization demands. It requires: 1) the development of intuitive active learning interfaces to acquire meaningful demonstrations; 2) the development of models that can exploit the structure and geometry of the acquired data in an efficient way; 3) the development of adaptive control techniques that can exploit the learned task variations and coordination patterns. The developed models often need to serve several purposes (recognition, prediction, online synthesis), and be compatible with different learning strategies (imitation, emulation, exploration). For the reproduction of skills, these models need to be enriched with force and impedance information to enable human-robot collaboration and to generate safe and natural movements. I will present an approach combining model predictive control and statistical learning of movement primitives in multiple coordinate systems. The proposed approach will be illustrated in various applications, with robots either close to us (robot for dressing assistance), part of us (prosthetic hand with EMG and tactile sensing), or far from us (teleoperation of bimanual robot in deep water).
Organizers: Ludovic Righetti
This talk will survey recent work to achieve multi-contact locomotion control of humanoid and legged robots. I will start by presenting some results on robust optimization-based control. We exploited robust optimization techniques, either stochastic or worst-case, to improve the robustness of Task-Space Inverse Dynamics (TSID), a well-known control framework for legged robots. We modeled uncertainties in the joint torques, and we immunized the constraints of the system to any of the realizations of these uncertainties. We also applied the same methodology to ensure the balance of the robot despite bounded errors in the its inertial parameters. Extensive simulations in a realistic environment show that the proposed robust controllers greatly outperform the classic one. Then I will present preliminary results on a new capturability criterion for legged robots in multi-contact. "N-step capturability" is the ability of a system to come to a stop by taking N or fewer steps. Simplified models to compute N-step capturability already exist and are widely used, but they are limited to locomotion on flat terrains. We propose a new efficient algorithm to compute 0-step capturability for a robot in arbitrary contact scenarios. Finally, I will present our recent efforts to transfer the above-mentioned techniques to the real humanoid robot HRP-2, on which we recently implemented joint torque control.
Organizers: Ludovic Righetti
The retina in the eye performs complex computations, to transmit only behaviourally relevant information about our visual environment to the brain. These computations are implemented by numerous different cell types that form complex circuits. New experimental and computational methods make it possible to study the cellular diversity of the retina in detail – the goal of obtaining a complete list of all the cell types in the retina and, thus, its “building blocks”, is within reach. I will review our recent contributions in this area, showing how analyzing multimodal datasets from electron microscopy and functional imaging can yield insights into the cellular organization of retinal circuits.
Organizers: Philipp Hennig
From gait, dance to martial art, human movements provide rich, complex yet coherent spatiotemporal patterns reflecting characteristics of a group or an individual. We develop computer algorithms to automatically learn such quality discriminative features from multimodal data. In this talk, I present a trilogy on learning from human movements: (1) Gait analysis from video data: based on frieze patterns (7 frieze groups), a video sequence of silhouettes is mapped into a pair of spatiotemporal patterns that are near-periodic along the time axis. A group theoretical analysis of periodic patterns allows us to determine the dynamic time warping and affine scaling that aligns two gait sequences from similar viewpoints for human identification. (2) Dance analysis and synthesis (mocap, music, ratings from Mechanical Turks): we explore the complex relationship between perceived dance quality/dancer's gender and dance movements respectively. As a feasibility study, we construct a computational framework for an analysis-synthesis-feedback loop using a novel multimedia dance-texture representation for joint angular displacement, velocity and acceleration. Furthermore, we integrate crowd sourcing, music and motion-capture data, and machine learning-based methods for dance segmentation, analysis and synthesis of new dancers. A quantitative validation of this framework on a motion-capture dataset of 172 dancers evaluated by more than 400 independent on-line raters demonstrates significant correlation between human perception and the algorithmically intended dance quality or gender of the synthesized dancers. (3) Tai Chi performance evaluation (mocap + video): I shall also discuss the feasibility of utilizing spatiotemporal synchronization and, ultimately, machine learning to evaluate Tai Chi routines performed by different subjects in our current project of “Tai Chi + Advanced Technology for Smart Health”.
There has been significant prior work on learning realistic, articulated, 3D statistical shape models of the human body. In contrast, there are few such models for animals, despite their many applications in biology, neuroscience, agriculture, and entertainment. The main challenge is that animals are much less cooperative subjects than humans: the best human body models are learned from thousands of 3D scans of people in specific poses, which is infeasible with live animals. In the talk I will illustrate how we extend a state-of-the-art articulated 3D human body model (SMPL) to animals learning from toys a multi-family shape space that can represent lions, cats, dogs, horses, cows and hippos. The generalization of the model is illustrated by fitting it to images of real animals, where it captures realistic animal shapes, even for new species not seen in training.
Moritz Hardt will review some progress and challenges towards preventing discrimination based on sensitive attributes in supervised learning.