Datatang – Medium

4 days ago

Natural Scenes OCR: Use High-quality Training Data to Optimize AI Model

Optical character recognition (OCR) is the task of electronic devices such as scanners or digital cameras examining characters in an image and then translating the shapes into computer text using character recognition methods. OCR application scenarios are relatively rich, including natural scenes, handwriting scenes, document recognition, etc. Natural scenario OCR…

Ocr

4 min read

Natural Scenes OCR: Use High-quality Training Data to Optimize AI Model

Jul 28

How to Improve the Face Reenactment Performance? In View of Training Datasets

Recently, the paper Face2Faceρ: Real-Time High-Resolution One-Shot Face Reenactment, co-authored by Netease AI Lab and Tsinghua University, was selected for ECCV 2022, the top international conference on computer vision. This paper innovatively proposes a new method of face reenactment, which can increase the algorithm speed up to 9 times while…

3 min read

How to Improve the Face Reenactment Performance? In View of Training Datasets

Jul 24

Face Recognition: Large-Scale Datasets For Face Anti-spoofing

As face recognition technology matures and its commercial application becomes more and more extensive, however, faces can be easily copied by means of photos and videos. Therefore, the counterfeiting of legitimate user faces is an important threat to the security of face recognition and authentication systems. At present, some progress…

Face Recognition

4 min read

Jul 15

How Data Labeling Tools Empower Bone Age Assessment

Bone age is the main method for evaluating the biological age of adolescents and children. Bone age and actual age are not consistent. Bone age examination can understand the development of bones, determine whether bone age is stunted or too fast, and understand the causes and prognosis of short stature…

Data Labeling

5 min read

Jul 14

What’s the Challenge of In-Vehicle Behavior Recognition?

The in-vehicle behavior recognition task aims to identify the behavior of drivers and passengers in the vehicle, and provide technical support for improving the experience of drivers and passengers. For different cockpit behaviors, the objects to be recognized are different, so the annotation methods are different. Typical annotation methods include…

Computer Vision

3 min read

What’s the Challenge of In-Vehicle Behavior Recognition?

Jun 22

Datatang at CVPR2022

Today marks the start of the 2022 Conference on Computer Vision and Pattern Recognition (CVPR 2022), it’s a knowledge festival exclusively made for professionals and researchers in CV domains, the premier event has been started on June 21 and will be ended in June 24, you can join the conference…

Cvpr

4 min read

Jun 18

Build Personalized Speech Synthesis With High-quality Training Data

Speech synthesis, commonly known as Text To Speech (TTS), is a technology that can convert any input text into corresponding speech, and is one of the indispensable modules in human-computer voice interaction. Traditional Speech Synthesis Traditional speech synthesis systems usually include two modules: front-end and back-end. The front-end module mainly…

Tts

4 min read

Build Personalized Speech Synthesis With High-quality Training Data

Jun 13

AI Solutions For Machine Learning

We live in the world of global market struggle and competitive advantage. Thus many companies strive to balance the growing competition with the automation and smart analysis offered by artificial intelligence. However, businesses are not always ready to have artificial intelligence shoved into their processes without preparation or careful planning…

10 min read

Jun 13

Privacy Policy of Datatang

Datatang operates the https://www.datatang.ai website, which provides the SERVICE. This page is used to inform website visitors regarding our policies with the collection, use, and disclosure of Personal Information if anyone decided to use our Service, the Datatang.ai website. If you choose to use our Service, then you agree to…

3 min read

Jun 12

10 Open Source Multimodal Emotion Recognition Datasets

In recent years, multimodal emotion recognition has become one of the research hotspots in human-computer interaction. How to analyze sentiment in multimodal data is an opportunity and challenge for the current sentiment analysis field. In this paper, I introduce datasets commonly used in the field of multimodal sentiment analysis. 1…

Open Source

5 min read