CVPR 2021, maadaa.ai will organize a short video parse competition

  • Posted by maadaa.ai
  • March 1, 2021
  • Updated 9:50 am

On January 18, the CVPR2021 reviews were released. According to Georgia Gkioxari, chair of the CVPR2021 program and FAIR research scientist, on Twitter today, there were 7,015 valid submissions this year. Each submission had a minimum of 3 reviews, for a total of 21,603 reviews, an increase of 19.6% from last year.

After successfully sponsoring NEURIPS 2020 last year, maadaa.ai is actively preparing to provide data support for CVPR2021, one of the world’s top annual events.

In the past year, due to COVID-19, short video social networking, E-commerce, and videoconferencing apps have exploded in popularity worldwide. Each day there are more than 2 million videos watched on Twitter and YouTube, there are more than 2 billion viewers of short videos each month. In China, the number of short video viewers has grown significantly, exceeding 700 million in 2020 and is expected to increase to 809 million in 2021. In terms of market size, China’s short video market reached 140.83 billion yuan in 2020, maintaining a high growth trend, and is expected to reach nearly 200 billion yuan in 2021.

As one of the earliest and most professional video data service providers, maadaa.ai possesses industry-leading video data collection, processing, and annotation capabilities.

During this year’s CVPR conference, we will provide well-annotated short video data sets based on typical short video application scenarios and promote the comprehensive research of computer vision technology in short videos. Research directions include: Object Detection based on computer vision, Gesture/Action Detection, Instance/Semantic Segmentation, Visual Relationship Detection, etc.

As the sponsor and data provider of the competition on short video application at this CVPR Conference, we sincerely invite experts in the AI industry who are interested in the discussion and promotion of computer vision technology research in the field of short videos.

Leave a Reply

Your email address will not be published. Required fields are marked *

Hair Semantic Segmentation Dataset maadaa
#AI #AIfuture #ecommerce #fashion #datasets #maadaaAs AI enters into every industry, the development of AI has taken the Fashion and
fashion datasets maadaa
Keywords: clothing classification, clothing pattern classification, clothing fabric classification, clothing key point detection, clothing & human body semantic, segmentation, scarf
Clothing Classification Dataset
#OpenDatasets   #fashion    #Ecommerce   #AI   #Trend1. Open DatasetsMost of the deep learning models adopt the data-driven way to conduct supervised
talk to sales