Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Chen, Cangxiong"'
CLIP is a widely used foundational vision-language model that is used for zero-shot image recognition and other image-text alignment tasks. We demonstrate that CLIP is vulnerable to change in image quality under compression. This surprising result is
Externí odkaz:
http://arxiv.org/abs/2311.14029
Autor:
Chen, Cangxiong, Campbell, Neill D. F.
Recent works have demonstrated that it is possible to reconstruct training images and their labels from gradients of an image-classification model when its architecture is known. Unfortunately, there is still an incomplete theoretical understanding o
Externí odkaz:
http://arxiv.org/abs/2210.13231
Autor:
Chen, Cangxiong, Campbell, Neill D. F.
Federated learning of deep learning models for supervised tasks, e.g. image classification and segmentation, has found many applications: for example in human-in-the-loop tasks such as film post-production where it enables sharing of domain expertise
Externí odkaz:
http://arxiv.org/abs/2111.10178
Autor:
Chen, Cangxiong
Kronecker’s first limit formula describes the constant term in the Laurent expansion of a non-holomorphic Eisenstein series at one of its poles. Asai generalised the limit formula to Eisenstein series of level one defined for a number field with cl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::150c198d195e4333aac39cded501984a
Autor:
Smith LGE; Department of Psychology, University of Bath., Piwek L; School of Management, University of Bath., Hinds J; School of Management, University of Bath., Brown O; School of Management, University of Bath., Chen C; University of Bath, Bath Institute for Mathematical Innovation., Joinson A; School of Management, University of Bath.
Publikováno v:
Journal of personality and social psychology [J Pers Soc Psychol] 2023 Sep; Vol. 125 (3), pp. 496-518. Date of Electronic Publication: 2023 Feb 13.