Microsoft Technology Licensing, LLC

Tsinghua University

Baidu Online Network Technology (beijing) Co., Ltd.

Chinese Academy of Agricultural Sciences

Han Hu

Ji Li

Qi Dai

Adit Krishnan

Yixuan Wei

Xiao Lin Sun

Errui Ding

Amit Srivastava

Jie Zhou

Junyu Han

Chengquan Zhang

Bin Han

Yu Fang

Yue Cao

Yuxuan Luo

Xiaozhi Yu

Mao Feng

Lifeng Meng

Chuan Ma

Jianke Li

Dingrui Wan

Si Chen

Qiaohong Wei

A data processing system implements a dynamic knowledge distillation process including dividing training data into a plurality of batches of samples and distilling a student model from a teacher model using an iterative knowledge distillation. The process includes instantiating an instance of the teacher model and the student model in a memory of the data processing system and obtaining a respective batch of training data from the plurality of batches of samples in the memory. The process includes training the teacher and student models using each of the samples in the respective batch of the training data, evaluating the performance of the student model compared with the performance of the teacher model, and providing feedback to student model to adjust the behavior of the student model based on the performance of the student model.

Scalable knowledge distillation techniques for machine learning

A system and method and for retrieving one or more visual assets includes receiving a search query for the one or more visual assets, the search query including textual data, encoding the textual data into one or more text embedding representations via a trained text representation machine-learning (ML) model, transmitting the one or more text embedding representations to a matching and selection unit, providing visual embedding representations of one or more visual assets to the matching and selection unit, comparing, by the matching and selection unit, the one or more text embedding representations to the visual embedding representations to identify one or more visual asset search results, and providing the one or more visual asset search results for display.

Method and system of content retrieval for visual data

A scheme for modifying an image is disclosed, which includes receiving a source image having a first image configuration; determining a second image configuration for a target image; providing the received source image to an AI engine trained to identify, based on a set of rules related to visual features, candidate regions from the source image; generating proposal images based on the candidate regions, respectively; determining, based on prior aesthetical evaluation data, an aesthetical value of each regional proposal image; and selecting, based on the determined aesthetical value of each regional proposal image, one of the regional proposal images as the target image; extracting, from the AI engine, the target image; and causing the target image to be displayed via a display of a user device.

AI-based aesthetical image modification

Match-paired monoclonal antibodies against major royal jelly protein 4 (MRJP4) are secreted by hybridoma cell lines having microbial deposit numbers of CGMCC No. 17294 and CGMCC No. 17295, which are used in an ELISA kit and a colloidal gold immunoassay strip for detecting the MRJP4. The positive and MRJP4-specific cell lines are obtained by cell fusion using an antigen of MRJP4 recombinant protein and a cross-reaction with other major royal jelly proteins. The MRJP4 recombinant protein is used as an antigen to obtain several positive cell lines by cell fusion and two MRJP4-specific fusion cell lines are obtained by a cross-reaction with other major royal jelly proteins. Primary screening of a matched antibody pair is performed according to antibody pairing for recognizing different epitopes.

Match-paired monoclonal antibodies against MRJP4, ELISA kit and colloidal gold immunoassay test strip for detecting MRJP4

Disclosed embodiments relate to a character detection method and apparatus. In some embodiments, the method includes: using an image including an annotated word as an input to a machine learning model; selecting, based on a predicted result of characters inside an annotation region of the annotated word predicted and annotation information of the annotated word, characters for training the machine learning model from the characters inside the annotation region of the annotated word predicted; and training the machine learning model based on features of the selected characters. This implementation manner implements the full training of a machine learning model by using existing word level annotated images, to obtain a machine learning model capable of detecting characters in images, thereby reducing the costs for the training of a machine learning model capable of detecting characters in images.

Character detection method and apparatus

The present invention discloses a video stabilizing method. The method may comprising the steps of: capturing a low-spatial-resolution image Iby a first camera and a high-spatial-resolution image Iby a second camera which is synchronous with the first camera for capturing an image of a moving target; determining a target region Iincluding the moving target in the low-spatial-resolution image I, and obtaining an output image Iof the high-spatial-resolution image Icorresponding to the target region I; generating a registration model Mbetween the low-spatial-resolution image Iand the high-spatial-resolution image I; and inpainting the output image Ibased on the registration model Mand the high-spatial-resolution image Ito complete the output image I. The present invention further discloses a video stabilizing system using a dual-camera system.

Video stabilizing method and system using dual-camera system

Growing community of inventors

Beijing, China

Han Hu