[HTML][HTML] Comparative genetic analysis of the novel coronavirus (2019-nCoV/SARS-CoV-2) receptor ACE2 in different populations
Y Cao, L Li, Z Feng, S Wan, P Huang, X Sun, F Wen… - Cell discovery, 2020 - nature.com
The ACE2 gene encodes the angiotensin-converting enzyme-2, which has been proved to
be the receptor for both the SARS-coronavirus (SARS-CoV) and the human respiratory …
be the receptor for both the SARS-coronavirus (SARS-CoV) and the human respiratory …
Geodesic saliency using background priors
Generic object level saliency detection is important for many vision tasks. Previous approaches
are mostly built on the prior that “appearance contrast between objects and backgrounds …
are mostly built on the prior that “appearance contrast between objects and backgrounds …
Face alignment by explicit shape regression
We present a very efficient, highly accurate, “Explicit Shape Regression” approach for face
alignment. Unlike previous regression-based approaches, we directly learn a vectorial …
alignment. Unlike previous regression-based approaches, we directly learn a vectorial …
Sugar-based aggregation-induced emission luminogens: design, structures, and applications
Y Wang, J Nie, W Fang, L Yang, Q Hu, Z Wang… - Chemical …, 2020 - ACS Publications
Sugars are abundant natural sources existing in biological systems, and bioactive saccharides
have attracted much more attention in the field of biochemistry and biomaterials. For …
have attracted much more attention in the field of biochemistry and biomaterials. For …
Ag-based semiconductor photocatalysts in environmental purification
J Li, W Fang, C Yu, W Zhou, Y Xie - Applied Surface Science, 2015 - Elsevier
Over the past decades, with the fast development of global industrial development, various
organic pollutants discharged in water have become a major source of environmental …
organic pollutants discharged in water have become a major source of environmental …
Vector quantized diffusion model for text-to-image synthesis
We present the vector quantized diffusion (VQ-Diffusion) model for text-to-image generation.
This method is based on a vector quantized variational autoencoder (VQ-VAE) whose latent …
This method is based on a vector quantized variational autoencoder (VQ-VAE) whose latent …
Paint by example: Exemplar-based image editing with diffusion models
Abstract Language-guided image editing has achieved great success recently. In this paper,
we investigate exemplar-guided image editing for more precise control. We achieve this …
we investigate exemplar-guided image editing for more precise control. We achieve this …
Rodin: A generative model for sculpting 3d digital avatars using diffusion
This paper presents a 3D diffusion model that automatically generates 3D digital avatars
represented as neural radiance fields (NeRFs). A significant challenge for 3D diffusion is that …
represented as neural radiance fields (NeRFs). A significant challenge for 3D diffusion is that …
Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation
Self-training is a competitive approach in domain adaptive segmentation, which trains the
network with the pseudo labels on the target domain. However inevitably, the pseudo labels …
network with the pseudo labels on the target domain. However inevitably, the pseudo labels …
Blessing of dimensionality: High-dimensional feature and its efficient compression for face verification
Making a high-dimensional (eg, 100K-dim) feature for face recognition seems not a good
idea because it will bring difficulties on consequent training, computation, and storage. This …
idea because it will bring difficulties on consequent training, computation, and storage. This …