Two weeks countdown! Preview of highlights of Shenzhen Station Conference

From data to large model application, on November 25th, Hangzhou Yuanchuang Conference was held to share development tips.

How to choose the keynote speech content for the audio and video technology conference? This is a crucial question.

First of all, it must be "high" enough, as a leader and a benchmark for innovative technology, and the content it shares can represent the new trends in the industry. Secondly, it must be "broad" enough, not only capable of in-depth technical details vertically, but also showing the differences in development at home and abroad and revealing future opportunities. Finally, the keynote speech should be "deep" enough to avoid general talk, but instead bring in-depth systematic knowledge from experts.

On the morning of November 24th, LiveVideoStackCon Shenzhen Station will usher in exciting keynote speeches.

Let's explore the charm of audio and video technology together and listen to insights from industry leaders and experts.

01 Tencent Cloud Audio and Video’s innovative technologies and diverse scenarios

and overseas insights

In the past two years, Tencent Cloud Audio and Video has continued to make breakthroughs and innovations in the field of audio and video technology. From collection, encoding, transmission acceleration, cloud media processing, distribution to decoding, Tencent Cloud Audio and Video continues to explore cutting-edge technologies and widely applies them to diversified scenarios. At the same time, in the practice of overseas markets, Tencent Cloud Audio and Video has accumulated rich experience and profound insights into the market. These insights not only bring valuable experience to the company, but also provide the industry with new thinking about going overseas.

General Manager of Tencent Cloud Audio and Video

Li Zhicheng

Speech content:

In recent years, audio and video technology has continued to make breakthroughs in aspects such as collection, encoding, transmission acceleration, cloud media processing, distribution and decoding. Audio and video innovative technologies and multi-scenario applications have gradually become industry hot spots. This sharing will comprehensively explain the innovation highlights from an end-to-end perspective and share the current hot innovation scenarios, including barrage interactive games, VAST advertising, multi-language real-time subtitles, and AIGC model applications. , real-time audio and video quality assessment and application innovations in low-latency live broadcast.

As the trend of globalization advances, more and more companies are focusing on overseas markets. In this sharing, we will delve into the differences in development habits and concerns between overseas and domestic countries, industry standards, vertical industry ecological cooperation models, and multi-cloud integration development strategies, and jointly discuss overseas technology ecology and development trends.

02 Overview of AVM’s encoding tools

Innovation in audio and video technology drives the industry forward. As the first generation of royalty-free video standards launched by the Open Media Alliance, AV1 has made significant progress in the industry, bringing us higher quality and more efficient video encoding solutions. Against this background, AVM is being actively developed as a next-generation video encoding standard. Paying attention to AVM is not only an insight into future technology trends, but also injects new strength into its own technical strength and competitiveness.

Google Senior Engineer

Chen Cheng

Speech content:

The growing consumption of video content is causing Internet data traffic to increase rapidly. This massive amount of data increases the demand for advanced video codecs and the appeal of royalty-free video standards. In the past few years, the industry has witnessed the rapid growth of AV1, the first-generation royalty-free video standard launched by the Alliance for Open Media.

AVM is a next-generation video coding standard under development based on the success of AV1. In this talk, the speaker will briefly introduce the goals of AVM, current project progress, and specific coding tools that have been considered. Participants can learn about the latest progress of AV1 and AVM through this lecture.

03 3D point cloud compression technology and standardization evolution

The high precision and rich information of 3D point cloud provide a more realistic and realistic experience for immersive communication, bringing users into a more engaging virtual world. In the field of autonomous driving, 3D point cloud technology can accurately perceive the surrounding environment and provide key data support for intelligent driving systems. In the future, 3D point cloud compression technology will play a key role in more fields. With the standardization and popularization of technology, it will bring broad market opportunities and bring users a richer and more diverse audio and video experience.

Beijing University

Assistant Professor & Doctoral Supervisor

Gao Wei

Speech content:

3D point cloud can express the geometric structure and color attributes of 3D objects and scenes with high precision, and has broad application prospects in immersive communications, autonomous driving and other fields. 3D cameras or radar acquisition equipment can generate high-precision point cloud data at levels of millions or even tens of millions per second. Storage/transmission bottlenecks and specific application scenario characteristics have put forward high-performance and specialized requirements for compression performance. At the same time, point cloud compression has been standardized. Research has become a hot topic among domestic and foreign standards working groups.

This sharing will be divided into three parts: the first part introduces point cloud compression technology based on hybrid coding framework, including projection video-based and geometry-based point cloud coding technology, focusing on how to achieve high compression performance and low complexity; second part The first part introduces AI-based point cloud compression technology, including octree-based, voxel-based and other intelligent coding methods, focusing on the design method of deep learning encoding and decoding tools; the third part introduces the current domestic and foreign standard working groups (including MPEG, AVS etc.) progress in point cloud compression standards. Through the above three parts, we will systematically introduce the relevant background and latest progress of point cloud compression technology and standardization.

"LiveVideoStack Multimedia Technology Development Report" first released

After a period of in-depth investigation and research, we have completed a comprehensive audio and video research report. This report focuses on the latest developments in current audio and video technology, as well as possible future development trends.

On the morning of November 24, we will hold a report launch ceremony at the main venue of the Shenzhen Station Conference. We invite you to follow, download and read the report when it is released. We hope that our report can help you obtain valuable information and help you gain an in-depth understanding of the latest trends in audio and video technology.

schedule poster

The schedule poster has been updated. You can check the disclosure status of PPT and speech videos of all speeches at this conference, helping you to arrange your participation time more reasonably and not missing what you want to listen and learn.

Publicly available information will be available to all attendees after the conference. Within two weeks after the conference, the download address of the materials will be sent to your registration email address by email.

Participate in the conference

●Time: November 24-25, 2023

●Location: Shenzhen Sentosa Hotel (Jade Branch)

WeChat Doujin｜ 13520771810

[email protected]