Futures
Access hundreds of perpetual contracts
TradFi
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
Launchpad
Be early to the next big token project
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
# AI Technology Empowers Qualcomm and Industry Partners to Advance Video Encoding Technology
Today, various video applications have become widely integrated into people’s daily lives. For example, during the Spring Festival, watching the CCTV New Year’s Gala and sending video greetings have become routine activities. At the same time, the rapid growth of video content has placed significant pressure on network bandwidth and storage space. In this context, video compression technology is becoming increasingly important.
VVC (Versatile Video Coding) is the latest video coding standard. Compared to the previous standard HEVC (High Efficiency Video Coding), VVC can further compress video data by about 50% while maintaining the same video quality. Currently, the industry is still working to advance video coding technology. Recently, Qualcomm Vice President of Technology Marta Karczewicz introduced in a blog post that at the joint Video Experts Group (JVET) meeting held last October, the JVET committee reviewed various responses to the Call for Evidence (CfE), supporting efforts to push video coding technology beyond the capabilities of the VVC standard. CfE is an important process in developing video coding standards, crucial for assessing the improvements and maturity of new tools and methods before formal proposal submissions.
It is noteworthy that this CfE revealed a significant trend: widespread adoption of Enhanced Compression Model (ECM) tools. ECM tools originated from the exploratory phase initiated at the JVET meeting in January 2021. At that time, Qualcomm proposed JVET U0100, which demonstrated an 11.5% improvement in compression efficiency over VVC under random access conditions. This proposal became the foundation for subsequent exploration efforts, and its software was adopted as a reference model for ECM. Additionally, Qualcomm collaborated with several companies actively involved in ECM development to submit a response based on ECM for the CfE. Qualcomm also released an optimized software version that integrates the latest VTM (VVC Test Model) with ECM coding tools (JVET AN0271), providing a more efficient platform for researchers and industry stakeholders to evaluate various coding technologies and jointly promote the development of video coding.
Qualcomm is a leading company in the field of video codec technology, playing a vital role in the development of key video technologies. It is a major contributor and developer of standards such as HEVC and VVC. For example, the development of the VVC standard began with Qualcomm submitting the COM16-C.806 proposal to the ITU-T Video Coding Experts Group (VCEG). This proposal included corresponding software that improved coding efficiency by 10.4% over the HEVC Test Model (HM) in random access configurations. Due to its significance, VCEG adopted this software as the starting point for the Joint Exploration Model (JEM).
In her article, Marta Karczewicz mentioned that JEM played a crucial role in the VVC standard development as a testing platform for new ideas and methods. Many of these validated innovations were ultimately incorporated into the VVC standard. She also noted that the collaborative exploration accelerated the development of next-generation compression technologies. After the completion of the VVC standard, Qualcomm continued to introduce its research成果 and software into standardization forums.
On another note, with the rapid development of artificial intelligence technology, AI-related techniques are also being applied to video encoding. For example, ECM integrates deep learning-based intra-frame prediction and in-loop filtering methods, achieving higher compression efficiency. Marta Karczewicz believes that as video compression technology continues to evolve, neural networks are expected to lead the next major technological revolution by overcoming the limitations of traditional hybrid coding frameworks based on inter- and intra-prediction and transform coding.
Looking ahead, it is believed that with ongoing advancements and applications of video coding and AI technologies, people will enjoy a better experience in the video era. Marta Karczewicz stated that the upcoming Call for Proposals scheduled for January 2027 will provide an opportunity to further promote technological progress. During this process, various innovative ideas and solutions will undergo comprehensive testing and optimization. Qualcomm will continue to play a role by providing relevant technical solutions and software, jointly driving the development of future standards.