Zobrazeno 1 - 10
of 82
pro vyhledávání: '"Bui, Tu"'
Generative AI (GenAI) is transforming creative workflows through the capability to synthesize and manipulate images via high-level prompts. Yet creatives are not well supported to receive recognition or reward for the use of their content in GenAI tr
Externí odkaz:
http://arxiv.org/abs/2403.09914
We present VIXEN - a technique that succinctly summarizes in text the visual differences between a pair of images in order to highlight any content manipulation present. Our proposed network linearly maps image features in a pairwise manner, construc
Externí odkaz:
http://arxiv.org/abs/2402.19119
Data hiding such as steganography and invisible watermarking has important applications in copyright protection, privacy-preserved communication and content provenance. Existing works often fall short in either preserving image quality, or robustness
Externí odkaz:
http://arxiv.org/abs/2304.03400
Autor:
Black, Alexander, Jenni, Simon, Bui, Tu, Tanjim, Md. Mehrab, Petrangeli, Stefano, Sinha, Ritwik, Swaminathan, Viswanathan, Collomosse, John
We propose VADER, a spatio-temporal matching, alignment, and change summarization method to help fight misinformation spread via manipulated videos. VADER matches and coarsely aligns partial video fragments to candidate videos using a robust visual d
Externí odkaz:
http://arxiv.org/abs/2303.13193
We propose PARASOL, a multi-modal synthesis model that enables disentangled, parametric control of the visual style of the image by jointly conditioning synthesis on both content and a fine-grained visual style embedding. We train a latent diffusion
Externí odkaz:
http://arxiv.org/abs/2303.06464
Autor:
Bui, Tu Quyen Thi
Vietnam currently faces a social skills deficit among college graduates. This lack of sufficient social skills significantly affects Vietnam's economy where it is one of the main factors that drives higher unemployment in Vietnam. Research has shown
Externí odkaz:
https://digital.library.unt.edu/ark:/67531/metadc1833541/
Rapid advances in Generative Adversarial Networks (GANs) raise new challenges for image attribution; detecting whether an image is synthetic and, if so, determining which GAN architecture created it. Uniquely, we present a solution to this task capab
Externí odkaz:
http://arxiv.org/abs/2207.02063
Autor:
Black, Alexander, Bui, Tu, Jenni, Simon, Zhang, Zhifei, Swaminanthan, Viswanathan, Collomosse, John
We present SImProv - a scalable image provenance framework to match a query image back to a trusted database of originals and identify possible manipulations on the query. SImProv consists of three stages: a scalable search stage for retrieving top-k
Externí odkaz:
http://arxiv.org/abs/2206.14245
We present CoGS, a novel method for the style-conditioned, sketch-driven synthesis of images. CoGS enables exploration of diverse appearance possibilities for a given sketched object, enabling decoupled control over the structure and the appearance o
Externí odkaz:
http://arxiv.org/abs/2203.09554
Autor:
Andriushchenko, Maksym, Li, Xiaoyang Rebecca, Oxholm, Geoffrey, Gittings, Thomas, Bui, Tu, Flammarion, Nicolas, Collomosse, John
Image attribution -- matching an image back to a trusted source -- is an emerging tool in the fight against online misinformation. Deep visual fingerprinting models have recently been explored for this purpose. However, they are not robust to tiny in
Externí odkaz:
http://arxiv.org/abs/2202.12860