Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Tianli Liao"'
Publikováno v:
Applied Sciences, Vol 13, Iss 14, p 8519 (2023)
Automatic program repair has drawn more and more attention since software quality is facing increasing challenges. In existing approaches, the unlimited search space is considered to be the main limitation in finding the correct patch. So how to redu
Externí odkaz:
https://doaj.org/article/8df59ef2eaba4cb4bb662b70909f003b
Publikováno v:
Information Technology and Control. 52:111-127
The graph neural network (GNN) based approaches have attracted more and more attention in session-based recommendation tasks. However, most of the existing methods do not fully take advantage of context information in session when capturing user’s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5343476bec03f9ee60f1d28aabc0a14
https://doi.org/10.5755/j01.itc.52.1.32138
https://doi.org/10.5755/j01.itc.52.1.32138
Publikováno v:
Signal, Image and Video Processing. 13:1199-1206
Seam-driven approaches have been proven effective for handling imperfect image series in image stitching. Generally, seam-driven approach utilizes seam-cutting to find a best stitching seam from one or finite alignment hypotheses based on a predefine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f35175c8f83fe450bbbcecfa0c29b47e
https://doi.org/10.1007/s11760-019-01466-9
https://doi.org/10.1007/s11760-019-01466-9
Publikováno v:
Signal, Image and Video Processing. 12:967-974
Image stitching is still challenging in consumer-level photography due to imperfect image captures. Recent works show that seam-cutting approaches can effectively relieve the artifacts generated by local misalignment. Normally, the seam-cutting appro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6b056b9657d27bb844f68531075105fc
https://doi.org/10.1007/s11760-018-1241-9
https://doi.org/10.1007/s11760-018-1241-9
Publikováno v:
Electronics Letters. 54:1328-1330
Geometric matching is a key step in computer vision tasks. Previous learning-based methods for geometric matching concentrate more on improving alignment quality, while the importance of naturalness issue is argued simultaneously. To this end, a nove
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a714d37eebce048401e59cbe3bfd921b
https://doi.org/10.1049/el.2018.6478
https://doi.org/10.1049/el.2018.6478
Publikováno v:
Electronics Letters (Wiley-Blackwell). 11/15/2018, Vol. 54 Issue 23, p1328-1329. 2p. 2 Diagrams, 3 Charts.