VASC Seminar
Gemma Roig
Assistant Professor
Department of Computer Science, Goethe University Frankfurt

Task-specific Vision DNN Models and Their Relation for Explaining Different Areas of the Visual Cortex

Virtual VASC Seminar:  https://cmu.zoom.us/j/249106600   Abstract:  Deep Neural Networks (DNNs) are state-of-the-art models for many vision tasks. We propose an approach to assess the relationship between visual tasks and their task-specific models. Our method uses Representation Similarity Analysis (RSA), which is commonly used to find a correlation between neuronal responses from brain data and models. [...]

PhD Speaking Qualifier
Robotics Institute,
Carnegie Mellon University

A Theory of Fermat Paths for Non-line-of-sight Shape Reconstruction

Zoom Link Abstract: Traditionally, computer vision systems and algorithms, such as stereo vision, and shape from shading, have been developed to mimic human vision. As a consequence, a lot of these systems operate under constraints that we take for granted in human vision. An example of such a constraint is that the scene of interest [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Learning Contextual Actions for Heuristic Search-Based Motion Planning

Zoom Link Abstract: Heuristic search-based motion planning can be computationally costly in large state and action spaces. In this work we explore the use of generative models to learn contextual actions for successor generation in heuristic search. We focus on cases where the robot operates in similar environments, i.e. environments drawn from some underlying distribution. [...]

VASC Seminar
Cristian Sminchisescu
Research Scientist / Professor
Google / Lund University

End-to-end Generative 3D Human Shape and Pose Models and Active Human Sensing

Virtual VASC Seminar:  https://cmu.zoom.us/j/249106600 Title:  End-to-end Generative 3D Human Shape and Pose Models and Active Human Sensing Abstract:  I will review some of our recent work in 3d human modeling, synthesis, and active vision. I will present our new, end-to-end trainable nonlinear statistical 3d human shape and pose models of different resolutions (GHUM and GHUMLite) as [...]

PhD Thesis Proposal
Robotics Institute,
Carnegie Mellon University

Safe and Resilient Multi-Robot Systems: Heterogeneity and Human Presence

Zoom Link Abstract: In the mission of a multi-robot team, the large number of robots behave like a system that relies on networking to enable smooth information propagation and inter-robot interaction as the mission evolves in a collective fashion. Key to the success of mission operation demands for safe and reliable robot interactions within the [...]

MSR Speaking Qualifier
Robotics Institute,
Carnegie Mellon University

Michael Tatum – MSR Thesis Talk

Archived Zoom Video Password: 1u%i4YO%   Title: Communications Coverage in Unknown Underground Environments   Abstract:In field robotics, maintaining communications between the user at a stationary basestation and all deployed robots is essential.  This task's difficulty increases when the test environment is underground and the environment is unknown to the operator and robots.  A common approach [...]

MSR Speaking Qualifier
Robotics Institute,
Carnegie Mellon University

Brendan Miller – MSR Thesis Talk

NSH 4305

Zoom Link: https://cmu.zoom.us/j/96617143856 Title: IBB-Net: Fast Iterative Bounding Box Regression for Point Clouds Abstract: Currently, most point cloud based detection pipelines are focused on producing high accuracy results while requiring significant computational resources and a high-end GPU. Our research explores how to reduce the computational overhead by improving a key element of detection: bounding box regression. We [...]

PhD Speaking Qualifier
Robotics Institute,
Carnegie Mellon University

Interactive Weak Supervision – Learning Useful Heuristics for Data Labeling

Zoom Link Abstract: Obtaining large annotated datasets is critical for training successful machine learning models and it is frequently a bottleneck in practice. Weak supervision offers a promising alternative for producing labeled datasets without ground truth annotations by generating probabilistic labels using multiple noisy heuristics. This process can scale to large amounts of data and [...]

PhD Thesis Defense
Robotics Institute,
Carnegie Mellon University

Automated Action Selection and Embodied Simulation for Socially Assistive Robots using Standardized Interactions

Zoom Link Abstract: Robots have the tremendous potential of assisting people in their lives, allowing them to achieve goals that they would not be able to achieve by themselves. In particular, socially assistive robots provide assistance primarily through social interaction, in healthcare, therapy, and education contexts. Despite their potential, current socially assistive robots still lack [...]