Related papers: Understanding image motion with group representati…
Activity analysis in which multiple people interact across a large space is challenging due to the interplay of individual actions and collective group dynamics. We propose an end-to-end approach for learning person trajectory…
Standard methods for video recognition use large CNNs designed to capture spatio-temporal data. However, training these models requires a large amount of labeled training data, containing a wide variety of actions, scenes, settings and…
Isolating different types of motion in video data is a highly relevant problem in video analysis. Applications can be found, for example, in dynamic medical or biological imaging, where the analysis and further processing of the dynamics of…
Visual change detection, aiming at segmentation of video frames into foreground and background regions, is one of the elementary tasks in computer vision and video analytics. The applications of change detection include anomaly detection,…
This work presents an approach for modelling and tracking previously unseen objects for robotic grasping tasks. Using the motion of objects in a scene, our approach segments rigid entities from the scene and continuously tracks them to…
A major challenge of the long measurement times in magnetic resonance imaging (MRI), an important medical imaging technology, is that patients may move during data acquisition. This leads to severe motion artifacts in the reconstructed…
This paper presents a novel Learning from Demonstration (LfD) method that uses neural fields to learn new skills efficiently and accurately. It achieves this by utilizing a shared embedding to learn both scene and motion representations in…
We present a parameterized synthetic dataset called Moving Symbols to support the objective study of video prediction networks. Using several instantiations of the dataset in which variation is explicitly controlled, we highlight issues in…
Today's autonomous vehicles rely extensively on high-definition 3D maps to navigate the environment. While this approach works well when these maps are completely up-to-date, safe autonomous vehicles must be able to corroborate the map's…
If a robot is supposed to roam an environment and interact with objects, it is often necessary to know all possible objects in advance, so that a database with models of all objects can be generated for visual identification. However, this…
Robot navigation in crowded pedestrian environments is a well-known challenge and we explore the practical deployment of group-based representations in this setting. Pedestrian groups have been empirically shown to enable a mobile robot's…
We introduce a novel framework to build a model that can learn how to segment objects from a collection of images without any human annotation. Our method builds on the observation that the location of object segments can be perturbed…
A key challenge in scaling up robot learning to many skills and environments is removing the need for human supervision, so that robots can collect their own data and improve their own performance without being limited by the cost of…
In vision-based action recognition, spatio-temporal features from different modalities are used for recognizing activities. Temporal modeling is a long challenge of action recognition. However, there are limited methods such as pre-computed…
We design a new approach that allows robot learning of new activities from unlabeled human example videos. Given videos of humans executing the same activity from a human's viewpoint (i.e., first-person videos), our objective is to make the…
The paper proposes a novel technique for representing templates and instances of concept classes. A template representation refers to the generic representation that captures the characteristics of an entire class. The proposed technique…
Video prediction, forecasting the future frames from a sequence of input frames, is a challenging task since the view changes are influenced by various factors, such as the global context surrounding the scene and local motion dynamics. In…
A key challenge for an agent learning to interact with the world is to reason about physical properties of objects and to foresee their dynamics under the effect of applied forces. In order to scale learning through interaction to many…
We introduce a new method for learning a generative model of articulated 3D animal motions from raw, unlabeled online videos. Unlike existing approaches for 3D motion synthesis, our model requires no pose annotations or parametric shape…
Predicting diverse object motions from a single static image remains challenging, as current video generation models often entangle object movement with camera motion and other scene changes. While recent methods can predict specific…