Publication
Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation
Related publications (32)
Topologically Better Delineation of Curvilinear Structures
Curvilinear structures are frequently observed in a variety of domains and are essential for comprehending neural circuits, detecting fractures in materials, and determining road and irrigation canal networks. It can be costly and time-consuming to manuall ...
EPFL2023Confidence Matters: Applications to Semantic Segmentation
The successes of deep learning for semantic segmentation can in be, in part, attributed to its scale: a notion that encapsulates the largeness of these computational architectures and the labeled datasets they are trained on. These resource requirements hi ...
EPFL2023Essays in Empirical Asset Pricing
This thesis consists of three applications of machine learning techniques to empirical asset pricing.In the first part, which is co-authored work with Oksana Bashchenko, we develop a new method that detects jumps nonparametrically in financial time series ...
EPFL2022Image Denoising with Control over Deep Network Hallucination
Sabine Süsstrunk, Majed El Helou, Qiyuan Liang
Deep image denoisers achieve state-of-the-art results but with a hidden cost. As witnessed in recent literature, these deep networks are capable of overfitting their training distributions, causing inaccurate hallucinations to be added to the output and ge ...
Society for Imaging Science and Technology (IS&T)2022Robustness and invariance properties of image classifiers
Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when deployed in noisy envi ...
EPFL2022Learning to Align Sequential Actions in the Wild
Pascal Fua, Bugra Tekin, Weizhe Liu
State-of-the-art methods for self-supervised sequential action alignment rely on deep networks that find correspon- dences across videos in time. They either learn frame-to- frame mapping across sequences, which does not leverage temporal information, or a ...
IEEE2022Leveraging Self-Supervision for Cross-Domain Crowd Counting
Pascal Fua, Nikita Durasov, Weizhe Liu
State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. While effective, these data-driven approaches rely on large amount of data annotation to achieve good performance, which stops these models from ...
IEEE COMPUTER SOC2022BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration
Sabine Süsstrunk, Majed El Helou
Classic image-restoration algorithms use a variety of priors, either implicitly or explicitly. Their priors are hand-designed and their corresponding weights are heuristically assigned. Hence, deep learning methods often produce superior image restoration ...
2022Counting People by Estimating People Flows
Pascal Fua, Mathieu Salzmann, Weizhe Liu
Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness co ...
2021Human-Centered Scene Understanding via Crowd Counting
Human-centered scene understanding is the process of perceiving and analysing a dynamic scene observed through a network of sensors with emphasis on human-related activities. It includes the visual perception of human-related activities from either single ...
EPFL2021