Related papers: Predicting the intended action using internal simu…
Deep neural networks based purely on attention have been successful across several domains, relying on minimal architectural priors from the designer. In Human Action Recognition (HAR), attention mechanisms have been primarily adopted on…
Understanding people's actions and interactions typically depends on seeing them. Automating the process of action recognition from visual data has been the topic of much research in the computer vision community. But what if it is too…
Among the abilities that autonomous mobile robots should exhibit, map building and localization are definitely recognized as fundamental. Consequently, countless algorithms for solving the Simultaneous Localization And Mapping (SLAM)…
Human Activity Recognition (HAR) is a challenging problem that needs advanced solutions than using handcrafted features to achieve a desirable performance. Deep learning has been proposed as a solution to obtain more accurate HAR systems…
Neural Architecture Search methods are effective but often use complex algorithms to come up with the best architecture. We propose an approach with three basic steps that is conceptually much simpler. First we train N random architectures…
Predicting driver intentions is a difficult and crucial task for advanced driver assistance systems. Traditional confidence measures on predictions often ignore the way predicted trajectories affect downstream decisions for safe driving. In…
We propose an online spatiotemporal articulation model estimation framework that estimates both articulated structure as well as a temporal prediction model solely using passive observations. The resulting model can predict future mo- tions…
Derived from rapid advances in computer vision and machine learning, video analysis tasks have been moving from inferring the present state to predicting the future state. Vision-based action recognition and prediction from videos are such…
We develop an approach for active semantic perception which refers to using the semantics of the scene for tasks such as exploration. We build a compact, hierarchical multi-layer scene graph that can represent large, complex indoor…
We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video. Active learning starts with a limited initial training…
Autonomous cars have to navigate in dynamic environment which can be full of uncertainties. The uncertainties can come either from sensor limitations such as occlusions and limited sensor range, or from probabilistic prediction of other…
Implicit neural representations have shown compelling results in offline 3D reconstruction and also recently demonstrated the potential for online SLAM systems. However, applying them to autonomous 3D reconstruction, where a robot is…
In this paper, we present foundations of the Socio-physical Model of Activities (SOMA). SOMA represents both the physical as well as the social context of everyday activities. Such tasks seem to be trivial for humans, however, they pose…
This paper presents the self-organized neuromorphic architecture named SOMA. The objective is to study neural-based self-organization in computing systems and to prove the feasibility of a self-organizing hardware structure. Considering…
This project explores the use of non-volatile synapses in neuromorphic computing for pattern recognition tasks through a comprehensive simulation-based approach. The main approach is through spintronic synapses, which leverage the…
In order to explore and act autonomously in an environment, an agent needs to learn from the sensorimotor information that is captured while acting. By extracting the regularities in this sensorimotor stream, it can learn a model of the…
Training and education in human-centered fields require authentic practice, yet realistic simulations of human behavior have remained limited. We present a multi-agent psychological simulation system that models internal cognitive-affective…
Manipulating an articulated object requires perceiving itskinematic hierarchy: its parts, how each can move, and howthose motions are coupled. Previous work has explored per-ception for kinematics, but none infers a complete…
Shared control can help in teleoperated object manipulation by assisting with the execution of the user's intention. To this end, robust and prompt intention estimation is needed, which relies on behavioral observations. Here, an intention…
We propose a new family of neural networks to predict the behaviors of physical systems by learning their underpinning constraints. A neural projection operator lies at the heart of our approach, composed of a lightweight network with an…