Zobrazeno 1 - 10
of 817
pro vyhledávání: '"Luc van Gool"'
Autor:
Xue-Jing Luo, Shuo Wang, Zongwei Wu, Christos Sakaridis, Yun Cheng, Deng-Ping Fan, Luc Van Gool
Publikováno v:
CAAI Artificial Intelligence Research, Vol 2, p 9150021 (2023)
The burgeoning field of Camouflaged Object Detection (COD) seeks to identify objects that blend into their surroundings. Despite the impressive performance of recent learning-based models, their robustness is limited, as existing methods may misclass
Externí odkaz:
https://doaj.org/article/5966deb5917549129e6d95826b979ed9
Autor:
Radek Zenkl, Radu Timofte, Norbert Kirchgessner, Lukas Roth, Andreas Hund, Luc Van Gool, Achim Walter, Helge Aasen
Publikováno v:
Frontiers in Plant Science, Vol 12 (2022)
Robust and automated segmentation of leaves and other backgrounds is a core prerequisite of most approaches in high-throughput field phenotyping. So far, the possibilities of deep learning approaches for this purpose have not been explored adequately
Externí odkaz:
https://doaj.org/article/44196e1a9887437c94a170bb7ea74547
Publikováno v:
Computers, Vol 10, Iss 9, p 105 (2021)
In this paper, we target the tasks of fine-grained image–text alignment and cross-modal retrieval in the cultural heritage domain as follows: (1) given an image fragment of an artwork, we retrieve the noun phrases that describe it; (2) given a noun
Externí odkaz:
https://doaj.org/article/d1c6fd618ea3413391dad2cdfd4fa457
Autor:
Rossella Suma, Georgia Stavropoulou, Elisavet K. Stathopoulou, Luc van Gool, Andreas Georgopoulos, Alan Chalmers
Publikováno v:
Virtual Archaeology Review, Vol 7, Iss 15, Pp 54-66 (2016)
The ability of High Dynamic Range (HDR) imaging to capture the full range of lighting in a scene has meant that it is being increasingly used for Cultural Heritage (CH) applications. Photogrammetric techniques allow the semi-automatic production of 3
Externí odkaz:
https://doaj.org/article/7ce0751fd4ef469abb8a3bc9ffdde216
Publikováno v:
EURASIP Journal on Image and Video Processing, Vol 2009 (2009)
Externí odkaz:
https://doaj.org/article/3d32816edf8f4a61a57761d28750a59e
Publikováno v:
EURASIP Journal on Image and Video Processing, Vol 2009 (2009)
The rapid development of computer graphics and imaging provides the modern archeologist with several tools to realistically model and visualize archeological sites in 3D. This, however, creates a tension between veridical and realistic modeling. Visu
Externí odkaz:
https://doaj.org/article/4dcea5b4854b4eff911b6ed8e518b52d
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 33:2410-2423
Recent years have witnessed an increasing interest in end-to-end learned video compression. Most previous works explore temporal redundancy by detecting and compressing a motion map to warp the reference frame towards the target frame. Yet, it failed
Publikováno v:
Machine Intelligence Research, 20 (3)
We present a masked vision-language transformer (MVLT) for fashion-specific multi-modal representation. Technically, we simply utilize the vision transformer architecture for replacing the bidirectional encoder representations from Transformers (BERT
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-18
Establishing robust and accurate correspondences between a pair of images is a long-standing computer vision problem with numerous applications. While classically dominated by sparse methods, emerging dense approaches offer a compelling alternative p
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-16