489 citations · 1.9k across the 46 of their papers we have counts for
60 papers
Multi-view Tracking Using Weakly Supervised Human Motion Prediction
Martin Engilberge, Weizhe Liu, Pascal Fua
Multi-view approaches to people-tracking have the potential to better handle occlusions than single-view ones in crowded scenes. They often rely on the tracking-by-detection paradi…
Gravity as a Reference for Estimating a Person's Height from Video
Didier Bieler, Semih Günel, Pascal Fua +1
Estimating the metric height of a person from monocular imagery without additional assumptions is ill-posed. Existing solutions either require manual calibration of ground plane an…
Probabilistic Atlases to Enforce Topological Constraints
Udaranga Wickramasinghe, Graham Knott, Pascal Fua
Probabilistic atlases (PAs) have long been used in standard segmentation approaches and, more recently, in conjunction with Convolutional Neural Networks (CNNs). However, their use…
Motion Capture from Pan-Tilt Cameras with Unknown Orientation
Roman Bachmann, Jörg Spörri, Pascal Fua +1
In sports, such as alpine skiing, coaches would like to know the speed and various biomechanical variables of their athletes and competitors. Existing methods use either body-worn…
Beyond Cartesian Representations for Local Descriptors
Patrick Ebel, Anastasiia Mishchuk, Kwang Moo Yi +2
The dominant approach for learning local patch descriptors relies on small image regions whose scale must be properly estimated a priori by a keypoint detector. In other words, if…
Self-supervised Training of Proposal-based Segmentation via Background Prediction
Isinsu Katircioglu, Helge Rhodin, Victor Constantin +3
While supervised object detection methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained…
Backpropagation-Friendly Eigendecomposition
Wei Wang, Zheng Dang, Yinlin Hu +2
Eigendecomposition (ED) is widely used in deep networks. However, the backpropagation of its results tends to be numerically unstable, whether using ED directly or approximating it…
Recurrent U-Net for Resource-Constrained Segmentation
Wei Wang, Kaicheng Yu, Joachim Hugonot +2
State-of-the-art segmentation methods rely on very deep networks that are not always easy to train without very large training datasets and tend to be relatively slow to run on sta…
Joint Segmentation and Path Classification of Curvilinear Structures
Agata Mosinska, Mateusz Kozinski, Pascal Fua
Detection of curvilinear structures in images has long been of interest. One of the most challenging aspects of this problem is inferring the graph representation of the curvilinea…
Detecting the Unexpected via Image Resynthesis
Krzysztof Lis, Krishna Nakka, Pascal Fua +1
Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we ta…
Neural Scene Decomposition for Multi-Person Motion Capture
Helge Rhodin, Victor Constantin, Isinsu Katircioglu +2
Learning general image representations has proven key to the success of many computer vision tasks. For example, many approaches to image understanding problems rely on deep networ…
NeuralSampler: Euclidean Point Cloud Auto-Encoder and Sampler
Edoardo Remelli, Pierre Baque, Pascal Fua
Most algorithms that rely on deep learning-based approaches to generate 3D point sets can only produce clouds containing fixed number of points. Furthermore, they typically require…
Beyond One Glance: Gated Recurrent Architecture for Hand Segmentation
Wei Wang, Kaicheng Yu, Joachim Hugonot +2
As mixed reality is gaining increased momentum, the development of effective and efficient solutions to egocentric hand segmentation is becoming critical. Traditional segmentation…
Segmentation-driven 6D Object Pose Estimation
Yinlin Hu, Joachim Hugonot, Pascal Fua +1
The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations o…
Eliminating Exposure Bias and Loss-Evaluation Mismatch in Multiple Object Tracking
Andrii Maksai, Pascal Fua
Identity Switching remains one of the main difficulties Multiple Object Tracking (MOT) algorithms have to deal with. Many state-of-the-art approaches now use sequence models to sol…
Tracing in 2D to Reduce the Annotation Effort for 3D Deep Delineation
Mateusz Koziński, Agata Mosinska, Mathieu Salzmann +1
The difficulty of obtaining annotations to build training databases still slows down the adoption of recent deep learning approaches for biomedical image analysis. In this paper, w…
GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping
Erhan Gundogdu, Victor Constantin, Amrollah Seifoddini +3
While Physics-Based Simulation (PBS) can accurately drape a 3D garment on a 3D body, it remains too costly for real-time applications, such as virtual try-on. By contrast, inferenc…
Context-Aware Crowd Counting
Weizhe Liu, Mathieu Salzmann, Pascal Fua
State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. They typically use the same filters over the whole image or over lar…
Discovering General-Purpose Active Learning Strategies
Ksenia Konyushkova, Raphael Sznitman, Pascal Fua
We propose a general-purpose approach to discovering active learning (AL) strategies from data. These strategies are transferable from one domain to another and can be used in conj…
What Face and Body Shapes Can Tell About Height
Semih Günel, Helge Rhodin, Pascal Fua
Recovering a person's height from a single image is important for virtual garment fitting, autonomous driving and surveillance, however, it is also very challenging due to the abse…
LF-Net: Learning Local Features from Images
Yuki Ono, Eduard Trulls, Pascal Fua +1
We present a novel deep architecture and a training strategy to learn a local feature pipeline from scratch, using collections of images without the need for human supervision. To…
FishEyeRecNet: A Multi-Context Collaborative Deep Network for Fisheye Image Rectification
Xiaoqing Yin, Xinchao Wang, Jun Yu +3
Images captured by fisheye lenses violate the pinhole camera assumption and suffer from distortions. Rectification of fisheye images is therefore a crucial preprocessing step for m…
Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation
Helge Rhodin, Mathieu Salzmann, Pascal Fua
Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizi…
Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses
Zheng Dang, Kwang Moo Yi, Yinlin Hu +3
Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector correspond…