Zobrazeno 1 - 10
of 3 063
pro vyhledávání: '"Lienhart, A"'
The basic body shape of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly different body shape for each video frame, which results in inconsistent body shapes for the same person.
Externí odkaz:
http://arxiv.org/abs/2409.17671
In this paper we introduce a new dataset containing instance segmentation masks for ten different categories of winter sports equipment, called WSESeg (Winter Sports Equipment Segmentation). Furthermore, we carry out interactive segmentation experime
Externí odkaz:
http://arxiv.org/abs/2407.09288
In panoptic scene graph generation (PSGG), models retrieve interactions between objects in an image which are grounded by panoptic segmentation masks. Previous evaluations on panoptic scene graphs have been subject to an erroneous evaluation protocol
Externí odkaz:
http://arxiv.org/abs/2407.09216
Utilizing transformer architectures for semantic segmentation of high-resolution images is hindered by the attention's quadratic computational complexity in the number of tokens. A solution to this challenge involves decreasing the number of tokens t
Externí odkaz:
http://arxiv.org/abs/2405.14467
Scene graph generation has emerged as a prominent research field in computer vision, witnessing significant advancements in the recent years. However, despite these strides, precise and thorough definitions for the metrics used to evaluate scene grap
Externí odkaz:
http://arxiv.org/abs/2404.09616
The interactive segmentation task consists in the creation of object segmentation masks based on user interactions. The most common way to guide a model towards producing a correct segmentation consists in clicks on the object and background. The rec
Externí odkaz:
http://arxiv.org/abs/2404.08421
We present a novel method for precise 3D object localization in single images from a single calibrated camera using only 2D labels. No expensive 3D labels are needed. Thus, instead of using 3D labels, our model is trained with easy-to-annotate 2D lab
Externí odkaz:
http://arxiv.org/abs/2310.17462
Current scene graph datasets suffer from strong long-tail distributions of their predicate classes. Due to a very low number of some predicate classes in the test sets, no reliable metrics can be retrieved for the rarest classes. We construct a new p
Externí odkaz:
http://arxiv.org/abs/2309.02286
Autor:
Wilksen, Steffen, Lohof, Frederik, Willmann, Isabell, Bopp, Frederik, Lienhart, Michelle, Thalacker, Christopher, Finley, Jonathan, Florian, Matthias, Gies, Christopher
Electrically controllable quantum-dot molecules (QDMs) are a promising platform for deterministic entanglement generation and, as such, a resource for quantum-repeater networks. We develop a microscopic open-quantum-systems approach based on a time-d
Externí odkaz:
http://arxiv.org/abs/2308.14563
Autor:
Boulogne, Luuk H., Lorenz, Julian, Kienzle, Daniel, Schon, Robin, Ludwig, Katja, Lienhart, Rainer, Jegou, Simon, Li, Guang, Chen, Cong, Wang, Qi, Shi, Derik, Maniparambil, Mayug, Muller, Dominik, Mertes, Silvan, Schroter, Niklas, Hellmann, Fabio, Elia, Miriam, Dirks, Ine, Bossa, Matias Nicolas, Berenguer, Abel Diaz, Mukherjee, Tanmoy, Vandemeulebroucke, Jef, Sahli, Hichem, Deligiannis, Nikos, Gonidakis, Panagiotis, Huynh, Ngoc Dung, Razzak, Imran, Bouadjenek, Reda, Verdicchio, Mario, Borrelli, Pasquale, Aiello, Marco, Meakin, James A., Lemm, Alexander, Russ, Christoph, Ionasec, Razvan, Paragios, Nikos, van Ginneken, Bram, Dubois, Marie-Pierre Revel
Challenges drive the state-of-the-art of automated medical image analysis. The quantity of public training data that they provide can limit the performance of their solutions. Public access to the training methodology for these solutions remains abse
Externí odkaz:
http://arxiv.org/abs/2306.10484