Inventor

WANG ZHAOWEN

US88 patents

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

WANG ZHAOWEN

ADOBE INC

Font recognition using text localization

Training text recognition systems

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

Preserving document design using font synthesis

Hierarchical scale matching and patch estimation for image style transfer with arbitrary resolution

Font replacement based on visual similarity

High resolution style transfer

Transferring motion between consecutive frames to a digital image

Font replacement based on visual similarity

Ambient audio generation based on visual information

Generating visually-aware item recommendations using a personalized preference ranking network

Tag-based font recognition by utilizing an implicit font classification attention neural network

Performing tag-based font retrieval using combined font tag recognition and tag-based font retrieval neural networks

Font attributes for font recognition and similarity

Training text recognition systems

Extracting textures from text based images

Preserving document design using font synthesis

Super-resolution with reference images

Image upscaling with controllable noise reduction using a neural network

Recognizing unseen fonts based on visual similarity

Font recognition by dynamically weighting multiple deep learning neural networks

Font recognition using triplet loss neural network training

Deep high-resolution style synthesis

Image alignment for burst mode images

Generating a compact video feature representation in a digital medium environment

Multi-style texture synthesis

Training neural networks to perform tag-based font recognition utilizing font classification

Texture hallucination for large-scale image super-resolution

Deep learning tag-based font recognition utilizing font classification

Image captioning utilizing semantic text modeling and adversarial learning

Video inpainting with deep internal learning

Font recognition using text localization

Multi-modal image ranking using neural networks

Music driven human dancing video synthesis

Automatically pairing fonts using asymmetric metric learning

Generating user-customized items using a visually-aware image generation network

Non-resident font preview

Text refinement network

ADOBE SYSTEMS INC

Font attributes for font recognition and similarity

Image captioning with weak supervision

Font recognition using text localization

Font replacement based on visual similarity

Determination of font similarity

Image tagging

Semantic natural language vector space

Distributed similarity learning for high-dimensional image features

Learning image representation by distilling from multi-task networks

Smoothing images using machine learning

UNIV COLUMBIA

Circuits and methods for multi-phase clock generators and phase interpolators

WANG JINJUN

Substructure and boundary modeling for continuous action recognition