I
Ingo Bax
Researcher at University of Münster
Publications - 20
Citations - 1418
Ingo Bax is an academic researcher from University of Münster. The author has contributed to research in topics: Gesture recognition & Gesture. The author has an hindex of 8, co-authored 19 publications receiving 798 citations. Previous affiliations of Ingo Bax include Bielefeld University.
Papers
More filters
Proceedings ArticleDOI
The “Something Something” Video Database for Learning and Evaluating Visual Common Sense
Raghav Goyal,Samira Ebrahimi Kahou,Vincent Michalski,Joanna Materzynska,Susanne Westphal,Heuna Kim,Valentin Haenel,Ingo Fruend,Peter N. Yianilos,Moritz Mueller-Freitag,Florian Hoppe,Christian Thurau,Ingo Bax,Roland Memisevic +13 more
TL;DR: This work describes the ongoing collection of the “something-something” database of video prediction tasks whose solutions require a common sense understanding of the depicted situation, and describes the challenges in crowd-sourcing this data at scale.
Proceedings ArticleDOI
The Jester Dataset: A Large-Scale Video Dataset of Human Gestures
TL;DR: This work introduces the largest collection of short clips of videos of humans performing gestures in front of the camera, and describes how a baseline achieving over 93% recognition accuracy can be obtained with a simple 3D convolutional neural network.
Proceedings ArticleDOI
Multimodal interaction in an augmented reality scenario
TL;DR: An augmented reality system designed for online acquisition of visual knowledge and retrieval of memorized objects is described, including modules for pointing gesture recognition, menu control based on gesture and speech, and control strategies to cope with situations when vision becomes unreliable and has to be re-adapted by speech.
Book ChapterDOI
Adaptive Computer Vision: Online Learning for Object Recognition
TL;DR: In this article, an appearance-based vision system for object recognition which can be adapted online, both to acquire visual knowledge about new objects and to correct erroneous classification is proposed, which works in an office scenario, acquisition of object knowledge is triggered by hand gestures.
Book ChapterDOI
Integrating context-free and context-dependent attentional mechanisms for gestural object reference
TL;DR: To evaluate hand movements for pointing gestures to objects and to recognise object reference, an approach relying on the integration of bottom-up generated feature maps and top-down propagated recognition results is introduced.