In contrast to humans that are
very good in anticipating
the behavior of other objects,
animals, or humans, developing
methods that anticipate
human behavior from video
or other sensor data is
very challenging and has
just recently received
an increase of interest.
In the past, the features
for analyzing, in particular,
visual data like images
or videos were too weak
such that approaches that
predict the future were
unlikely to succeed.
This burden has been overcome
due to recent progress
in this field. The anticipation
of human behavior, however,
is not well defined in
the literature and varies
depending on the task in
terms of granularity and
time horizon. In the context
of driver assistance systems,
the prediction of the trajectory
of a pedestrian needs to
be within centimeter accuracy
but only for a very short
time horizon of one second.
For tracking applications
or motion planning, the
potential destination of
a human and trajectories
of several seconds or minutes
to reach the destination
need to be predicted. In
order to prioritize several
tasks for a service robot
during a day, only the
rough time and location
of an activity is needed.
For instance, when the
robot anticipates that
the owner wants to cook
in one hour, the robot
will be in the kitchen
at the right time.
The purpose of this workshop is
to discuss recent approaches
that anticipate human behavior
from video or other sensor
data, to bring together
researchers from multiple
fields and perspectives,
and to discuss major research
problems and opportunities
and how we should coordinate
efforts to advance the
field.
The workshop will be located in the lecture hall HS1 of the Hörsaalzentrum Campus Poppelsdorf, University of Bonn, Friedrich-Hirzebruch-Allee 5, 53115 Bonn.
The workshop will be located in the lecture hall HS1 of the Hörsaalzentrum Campus Poppelsdorf, University of Bonn, Friedrich-Hirzebruch-Allee 5, 53115 Bonn (Map). Entrance to the workshop is free, but a registration is required. For a late registration, please contact Michaela Musselmann (musselmann@iai.uni-bonn.de).
Speakers
Dominik Bach is Hertz Chair for Artificial Intelligence and Neuroscience at the University of Bonn. His research seeks to exploit the power of artificial intelligence in order to understand biological intelligence, how it is enabled in the central nervous system, and how it fails in neuropsychiatric disorder. His goal is to understand how humans gracefully avoid real threat in their natural environment - and why some humans fear and avoid non-threatening situations.
Sven Behnke is professor for Autonomous Intelligent Systems at the University of Bonn and director of Computer Science - Intelligent Systems and Robotics. His research interests include cognitive robotics, computer vision, and machine learning.
Maren Bennewitz is professor for Computer Science at the University of Bonn and head of the Humanoid Robots Laboratory. The focus of her research lies on robots acting in human environments. Her group develops techniques that allow robots to adapt their behavior to the environment and to the surrounding people thereby exploiting semantic information about objects and information about the activities of users.
Dima Damen is a professor for Computer Vision at the University of Bristol and currently an EPSRC Fellow (2020-2025), focusing her research interests in the automatic understanding of object interactions, actions and activities using wearable visual (and depth) sensors. She has contributed to novel research questions including assessing action completion, skill/expertise determination from video sequences, discovering task-relevant objects, dual-domain and dual-time learning as well as multi-modal fusion using vision, audio and language. She is the project lead for EPIC-KITCHENS, the largest dataset in egocentric vision, with accompanying open challenges.
Anne Driemel is professor for Theoretical Computer Science at the University of Bonn and HCM Bonn Junior Fellow. Her research interests include discrete and computational geometry, algorithms and data structures, and trajectory and time series analysis.
Gianpiero Francesca is AI Technical Manager at Toyota Motor Europe.
Juergen Gall is professor and head of the Computer Vision Group at the University of Bonn. He is spokesperson of the DFG research unit FOR 2535 - Anticipating Human Behavior and his research interests include human pose estimation, video analysis, and forecasting.
Reinhard Klein is professor for Computer Graphics at the University of Bonn and director of the Institute of Computer Science - Visual Computing. The group covers topics in geometry processing, scientific and geospatial visualization, photo-realistic rendering and physics based animation.
Hilde Kuehne is professor and head of the Multimodal Learning Group at the University of Bonn.
Tang Siyu is professor and head of the Computer Vision and Learning Group at ETH Zurich. She studies computational models that enable machines to perceive and analyze human activities from visual input. She leverages machine learning and optimization techniques to build statistical models of humans and their behaviors. Her goal is to advance algorithmic foundations of scalable and reliable human digitalization, enabling a broad class of real-world applications.
Programm
9:00-9:15Welcome9:15-10:15TalksSocial Diffusion: Multiple Human Motion AnticipationJuergen GallReconstruction and Synthesis of 3D Humans in 3D ScenesTang Siyu10:15-10:45Coffee10:45-12:15TalksSpatial-temporal Grounding and Reasoning in Video DataHilde KühneOpportunities in Egocentric VisionDima DamenCloth Dynamics Prediction using Physically-based SimulationReinhard Klein12:15-13:15Lunch13:15-14:45TalksCritical Intelligence: Towards Agent-based Models of Human EscapeDominik BachResearch and Development on Robotics and Computer Vision at Toyota Motor EuropeGianpiero FrancescaForesighted and Personalized Robot NavigationMaren Bennewitz14:45-15:15Coffee15:15-16:15TalksFinding Complex Patterns in Trajectory Data via Geometric Set CoverAnne DriemelFrom Semantic Video Prediction to Anticipative Human-Robot CollaborationSven Behnke16:15-16:30Closing Remarks
Despite careful content control
we assume no liability for
the content of external links.
For the corresponding content
of linked pages, their administrators
are responsible.