Search

Departments Computer Vision and Machine Learning Research Gaze-Based Human-Computer Interaction Gaze-Based Human-Computer Interaction Forecasting User Attention During Everyday Mobile Interactions Using D [...] human-computer interaction, attentive user interfaces, and eye-based user modelling. However, current mobile eye trackers are still obtrusive, which not only makes them uncomfortable to wear and socially [...] egrated sensors and body-worn cameras to encode rich information on device usage and users’ visual scene. We demonstrate that our method can forecast bidirectional attention shifts and predict whether

r benchmark metrics and the established image segmentation metrics of SC, PRI and VI computed on video volumes. Learning Must-Link Constraints for Video Segmentation Clustering and segmentation methods [...] in terms of the normalized cut and of its spectral clustering relaxation. The proposed method reduces runtime and memory consumption and yields on par results in image and video segmentation. Further, it [...] segmentation and that is large enough to avoid overfitting. Consequently, there is little analysis of video segmentation which generalizes across subtasks, and it is not yet clear which and how video s

for five datasets, i.e. CUB, SUN, AWA and ImageNet, and establish a new state-of-the-art in any-shot learning, i.e. inductive and transductive (generalized) zero- and few-shot learning settings. We also [...] from image level labels and bounding box annotations. In this paper we take this one step further and propose zero-and few-label learning for semantic segmentation as a new task and propose a benchmark on [...] consuming words and characters. Our proposed models train end-to-end to align with the fine-grained and category-specific content of images. Natural language provides a flexible and compact way of encoding

Research Departments Computer Vision and Machine Learning Research Weakly Supervised Learning Weakly Supervised Learning Weakly Supervised Object Boundaries State-of-the-art learning based boundary detection [...] make both the training more affordable and to extend the amount of training data. In this paper we propose a technique to generate weakly supervised annotations and show that bounding box annotations alone [...] supervised state-of-the-art methods. Simple does it: Weakly Supervised Instance and Semantic Segmentation Semantic labelling and instance segmentation are two tasks that require particularly costly annotations

Research Departments Computer Vision and Machine Learning Research Vision and Language Vision and Language Xplore-M-Ego: Contextual Media Retrieval Using Natural Language Queries The widespread integration [...] of cameras in hand-held and head-worn devices as well as the ability to share content online enables a large and diverse visual capture of the world. We envision these images and associated meta information [...] to recognize scenes, human activities, and participating objects and achieve encouraging results in video description on this new challenging dataset. Grounded and Co-Referenced Characters In this work

to have significant potential for activity recognition and computational behaviour analysis but previous works focused on supervisedmethods and recognition of predefined activity classes basedon short-term [...] annotations for eight sample activity classes: outdoor, social interaction, concentrated work, mobile, reading, computer work, watching media, and eating. In addition, we include periods with no specific activity [...] Research Departments Computer Vision and Machine Learning Research Human Activity Recognition Human Activity Recognition Discovery of Everyday Human Activities From Long-term Visual Behaviour Using Topic

of D4. This and all previous full reports are available here . Research Areas HDR Imaging, Perception, and Advanced Displays Sensorimotor Interaction Artificial Intelligence aided Design and Manufacturing [...] ing Sampling and Rendering High Performance Digital Geometry Processing Image Synthesis and Machine Learning [...] Research Departments Computer Graphics Research Research Scientific Activities The 15th Biennial Report 2019-2021 is a survey over the scientific activities of the Max Planck Institute for Informatics

QA, heterogeneous QA, and conversational QA. Topics will also include addressing key dimensions like user feedback, interpretability, unanswerability, and efficiency. Lectures and assignments There will [...] information retrieval, natural language processing, and machine learning will be helpful. Additional knowledge of probability and statistics, linear algebra, and optimization techniques is reocmmended, but not [...] Question Answering Systems (Summer Semester 2020) and Information Retrieval and Data Mining (Winter Semester 2019/20) are recommended but not mandatory. Schedule and topics Lecture Date Topic Slides Videos 01

Departments Computer Vision and Machine Learning Research Research People Detection, Pose Estimation and Tracking Visual Privacy Adversarial Robustness Zero-Shot Learning Generative Models Vision and Language [...] Knowledge Transfer and Semi-supervised Learning Weakly Supervised Learning Image Segmentation Video Segmentation Object Recognition and Scene Understanding Gaze-Based Human-Computer Interaction 3D Reconstruction [...] Reconstruction and Perception of People Generative Models of 3D People Human Pose Estimation from Video and IMU

Visual Computing, Interaction and Artificial Intelligence (VIA)” at the MPI for Informatics. more Max Planck Center for Visual Computing and Communication The Max Planck Center for Visual Computing and Co [...] (MPG) and Stanford University in October 2003 recognizing the high potential of a mutually beneficial cooperation between Stanford and MPG in the field of Visual Computing and Communication and recognizing [...] dependable, secure, and usable computing systems, as well as their interaction with the physical and social context in which they operate. more Max Planck Institute for Informatics German Center for Artificial