755 citations · 1.1k across the 14 of their papers we have counts for
14 papers
UNIGEOCLIP: Unified Geospatial Contrastive Learning
Guillaume Astruc, Eduard Trulls, Jan Hosang +2
The growing availability of co-located geospatial data spanning aerial imagery, street-level views, elevation models, text, and geographic coordinates offers a unique opportunity f…
Scaling Image Geo-Localization to Continent Level
Philipp Lindenberger, Paul-Edouard Sarlin, Jan Hosang +4
Determining the precise geographic location of an image at a global scale remains an unsolved challenge. Standard image retrieval techniques are inefficient due to the sheer volume…
SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding
Paul-Edouard Sarlin, Eduard Trulls, Marc Pollefeys +2
Semantic 2D maps are commonly used by humans and machines for navigation purposes, whether it's walking or driving. However, these maps have limitations: they lack detail, often co…
TUSK: Task-Agnostic Unsupervised Keypoints
Yuhe Jin, Weiwei Sun, Jan Hosang +2
Existing unsupervised methods for keypoint learning rely heavily on the assumption that a specific keypoint type (e.g. elbow, digit, abstract geometric shape) appears only once in…
Efficient Large Scale Inlier Voting for Geometric Vision Problems
Dror Aiger, Simon Lynen, Jan Hosang +1
Outlier rejection and equivalently inlier set optimization is a key ingredient in numerous applications in computer vision such as filtering point-matches in camera pose estimation…
COTR: Correspondence Transformer for Matching Across Images
Wei Jiang, Eduard Trulls, Jan Hosang +2
We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence…
Learning non-maximum suppression
Jan Hosang, Rodrigo Benenson, Bernt Schiele
Object detectors have hugely profited from moving towards an end-to-end learning paradigm: proposals, features, and the classifier becoming one neural network improved results two-…
Simple Does It: Weakly Supervised Instance and Semantic Segmentation
Anna Khoreva, Rodrigo Benenson, Jan Hosang +2
Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annota…
How Far are We from Solving Pedestrian Detection?
Shanshan Zhang, Rodrigo Benenson, Mohamed Omran +2
Encouraged by the recent progress in pedestrian detection, we investigate the gap between current state-of-the-art methods and the "perfect single frame detector". We enable our an…
A convnet for non-maximum suppression
Jan Hosang, Rodrigo Benenson, Bernt Schiele
Non-maximum suppression (NMS) is used in virtually all state-of-the-art object detection pipelines. While essential object detection ingredients such as features, classifiers, and…
What makes for effective detection proposals?
Jan Hosang, Rodrigo Benenson, Piotr Dollár +1
Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images. Despite the pop…
Taking a Deeper Look at Pedestrians
Jan Hosang, Mohamed Omran, Rodrigo Benenson +1
In this paper we study the use of convolutional neural networks (convnets) for the task of pedestrian detection. Despite their recent diverse successes, convnets historically under…
Ten Years of Pedestrian Detection, What Have We Learned?
Rodrigo Benenson, Mohamed Omran, Jan Hosang +1
Paper-by-paper results make it easy to miss the forest for the trees.We analyse the remarkable progress of the last decade by discussing the main ideas explored in the 40+ detector…
How good are detection proposals, really?
Jan Hosang, Rodrigo Benenson, Bernt Schiele
Current top performing Pascal VOC object detectors employ detection proposals to guide the search for objects thereby avoiding exhaustive sliding window search across images. Despi…