Inventor

SHEN XIAOHUI

CN119 patents

⚠️ This page may combine multiple inventors who share the name “SHEN XIAOHUI”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

SHEN XIAOHUI

ADOBE INC

Deep salient content neural networks for efficient digital object segmentation

Frame selection based on a trained neural network

Harmonizing composite images using deep learning

Training and utilizing an image exposure transformation neural network to generate a long-exposure image from a single short-exposure image

Digital image completion using deep learning

Robust tracking of objects in videos

Digital image completion by learning generation and patch matching jointly

Object detection in images

Image crop suggestion and evaluation using deep-learning

Automatically segmenting images based on natural language phrases

Image depth inference from semantic labels

Utilizing deep learning to rate attributes of digital images

Illumination estimation from a single image

Utilizing deep learning for boundary-aware image segmentation

Utilizing deep learning to rate attributes of digital images

Aesthetics-guided image enhancement

Utilizing a deep neural network-based model to identify visually similar digital images based on user-selected visual attributes

Semantic class localization digital environment

Digital image completion by learning generation and patch matching jointly

Object detection in images

Digital image completion using deep learning

Recurrent neural network architectures which provide text describing images

Facilitating preservation of regions of interest in automatic image cropping

Joint training technique for depth map generation

User-guided image completion with image completion neural networks

Digital image defect identification and correction

ADOBE SYSTEMS INC

Generating image features based on robust feature-learning

Object detection using cascaded convolutional neural networks

Large-scale image tagging using image-to-topic embedding

Semantic class localization in images

Automatically selecting example stylized images for image stylization operations based on semantic content

Convolutional neural network using a binarized convolution layer

Utilizing deep learning for rating aesthetics of digital images

Utilizing deep learning for boundary-aware image segmentation

Object detection using cascaded convolutional neural networks

Image cropping suggestion using multiple saliency maps

Accurate tag relevance prediction for image search

Joint depth estimation and semantic segmentation from a single image

Image color and tone style transfer

Method for using deep learning for facilitating real-time view switching and video editing on computing devices

Automatically segmenting images based on natural language phrases

Recognizing unknown person instances in an image gallery

Generating image features based on robust feature-learning

Planar region guided 3D geometry estimation from a single image

Object segmentation, including sky segmentation

Neural network image curation control

Accelerating object detection

Saliency map computation

LIN ZHE

Object retrieval and localization using a spatially-constrained similarity model

HUAWEI TECH CO LTD

Blind-mate integrated connector