Inventor

ZHANG JIANMING

US147 patents

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

ZHANG JIANMING

ADOBE INC

System for automatic video reframing

Deep salient content neural networks for efficient digital object segmentation

Systems and methods for hierarchical webly supervised training for recognizing emotions in images

Utilizing a two-stream encoder neural network to generate composite digital images

Utilizing a neural network having a two-stream encoder architecture to generate composite digital images

Enhanced semantic segmentation of images

Generating refined segmentations masks via meticulous object segmentation

Joint visual-semantic embedding and grounding via multi-task training for image searching

Generating an image mask for a digital image by utilizing a multi-branch masking pipeline with neural networks

Automatically generating a trimap segmentation for a digital image by utilizing a trimap generation neural network

Robust training of large-scale object detectors with a noisy dataset

Object detection in images

Image crop suggestion and evaluation using deep-learning

Iteratively applying neural networks to automatically identify pixels of salient objects portrayed in digital images

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

Guided up-sampling for image inpainting

Texture-preserving shadow removal in digital images utilizing generating inpainting models

Object class inpainting in digital images utilizing class-specific inpainting neural networks

Human inpainting utilizing a segmentation branch for generating an infill segmentation map

Visual-semantic representation learning via multi-modal contrastive training

Learning parameters for generative inpainting neural networks utilizing object-aware training and masked regularization

Generating deep harmonized digital images

Generating depth images utilizing a machine-learning model built from mixed digital image sources and multiple loss function sets

Generating digital images utilizing high-resolution sparse attention and semantic layout manipulation neural networks

Generating a modified digital image utilizing a human inpainting model

Neural network architecture pruning

Semantic class localization digital environment

Generalizable robot approach control techniques

Iterative image inpainting with confidence feedback

System for automatic object mask and hotspot tracking

ADOBE SYSTEMS INC

Generating image features based on robust feature-learning

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

Semantic class localization in images

Image cropping suggestion using multiple saliency maps

Accurate tag relevance prediction for image search

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

Generating image features based on robust feature-learning

Saliency map computation

DANA FARBER CANCER INST INC

Fused 2-aminothiazole compounds

Type II RAF kinase inhibitors

Type II raf kinase inhibitors

GRAY NATHANAEL

Soluble mTOR complexes and modulators thereof

Small molecule myristate inhibitors of BCR-ABL and methods of use

WHITEHEAD BIOMEDICAL INST

Soluble mTOR complexes and modulators thereof

CHOI HWAN GEUN

Fused 2-aminothiazole compounds

GRAY NATHANAEL S

Type II Raf kinase inhibitors

IBM

Short message gateway, system and method of providing information service for mobile telephones

SPLUNK INC

Retrieving data identifiers from queue for search of external data system

COMSTOCK SAMUEL J

Universal ordering for manufacturing customized print products

DONGGUAN LUXSHARE TECH CO LTD

Terminal group