Zobrazeno 1 - 10
of 94
pro vyhledávání: '"Coskun, Huseyin"'
Direct Preference Optimization (DPO) has emerged as a powerful approach to align text-to-image (T2I) models with human feedback. Unfortunately, successful application of DPO to T2I models requires a huge amount of resources to collect and label large
Externí odkaz:
http://arxiv.org/abs/2410.18013
Clustering is a ubiquitous tool in unsupervised learning. Most of the existing self-supervised representation learning methods typically cluster samples based on visually dominant features. While this works well for image-based self-supervision, it o
Externí odkaz:
http://arxiv.org/abs/2207.10158
The video action segmentation task is regularly explored under weaker forms of supervision, such as transcript supervision, where a list of actions is easier to obtain than dense frame-wise labels. In this formulation, the task presents various chall
Externí odkaz:
http://arxiv.org/abs/2201.05675
State-of-the-art methods for self-supervised sequential action alignment rely on deep networks that find correspondences across videos in time. They either learn frame-to-frame mapping across sequences, which does not leverage temporal information, o
Externí odkaz:
http://arxiv.org/abs/2111.09301
Autor:
Haresh, Sanjay, Kumar, Sateesh, Coskun, Huseyin, Syed, Shahram Najam, Konin, Andrey, Zia, Muhammad Zeeshan, Tran, Quoc-Huy
We present a self-supervised approach for learning video representations using temporal video alignment as a pretext task, while exploiting both frame-level and video-level information. We leverage a novel combination of temporal alignment loss and t
Externí odkaz:
http://arxiv.org/abs/2103.17260
Autor:
Coskun, Husna Betul, Coskun, Huseyin
The indirect transactions between sectors of an economic system has been a long-standing open problem. There have been numerous attempts to conceptually define and mathematically formulate this notion in various other scientific fields in literature
Externí odkaz:
http://arxiv.org/abs/1911.11569
We present a sampling-free approach for computing the epistemic uncertainty of a neural network. Epistemic uncertainty is an important quantity for the deployment of deep neural networks in safety-critical applications, since it represents how much o
Externí odkaz:
http://arxiv.org/abs/1908.00598
Autor:
Coskun, Huseyin, Zia, Zeeshan, Tekin, Bugra, Bogo, Federica, Navab, Nassir, Tombari, Federico, Sawhney, Harpreet
Publikováno v:
year = {5555}, volume = {}, number = {01}, issn = {1939-3539}, pages = {1-1}
The lack of large-scale real datasets with annotations makes transfer learning a necessity for video activity understanding. We aim to develop an effective method for few-shot transfer learning for first-person action classification. We leverage inde
Externí odkaz:
http://arxiv.org/abs/1907.09382
Autor:
Coskun, Huseyin
Publikováno v:
Heliyon 5 (2019)
This article develops a new mathematical method for holistic analysis of nonlinear dynamic compartmental systems through the system decomposition theory. The method is based on the novel dynamic system and subsystem partitioning methodologies through
Externí odkaz:
http://arxiv.org/abs/1812.00750
Nonlinear Decomposition Principle and Fundamental Matrix Solutions for Dynamic Compartmental Systems
Autor:
Coskun, Huseyin
Publikováno v:
Discrete & Continuous Dynamical Systems - B (2019)
A decomposition principle for nonlinear dynamic compartmental systems is introduced in the present paper. This theory is based on the mutually exclusive and exhaustive, analytical and dynamic, novel system and subsystem partitioning methodologies. A
Externí odkaz:
http://arxiv.org/abs/1811.11885