Aspera CEO Michelle Munson discusses the core principles, performance characteristics, and use cases of the FASPStream software at Video @Scale.

In this talk we’ll discuss improvements made to our Dynamic Streaming system.

Creating spatial audio experiences and playing them back at scale requires new technologies. We recently launched new user tools and rendering methods that make high-quality spatial audio possible for large-scale consumption on Facebook. Both of these advancements will enable video producers to re-create reality across a wide range of devices and platforms. In this talk, we'll explore the technical details behind what we've built and how our rendering engine can be incorporated into other production and consumption pipelines, with a brief overview of the history of spatial audio.

In this talk, we'll discuss the progression of VP9 (its benefits, software optimizations, hardware development, battery life concerns) and the use of codec splicing in the YouTube player to employ vp9 when feasible.

In this talk we will cover end-to-end considerations for delivering low-latency live steams for Facebook Live.

In this talk we will cover end-to-end considerations for delivering low-latency live steams for Facebook Live.

Last year Netflix launched globally, reaching many new members in 130 countries. In many of these countries, people access the internet primarily using cellular networks or still-developing broadband infrastructure. In this talk we discuss our efforts to improve video quality over low-bandwidth unreliable networks: new codec profiles (VP9 and H.264/AVC High), per-chunk bitrate optimization, and tuning the video quality metric VMAF for mobile viewing scenarios.

The evolution from a set-top box to bring your own device, managed networks and satellites to IP and OTT. The journey from proof-of-concept to production and lessons learned as AT&T Entertainment builds a cloud-native Video API to support growing demand and the future of their business.

Video understanding at scale is a challenging AI problem. As video creation, sharing and consumption experiences increase radically, the algorithms and systems required to understand and enrich the user experience need to keep pace. This talk will touch on the current landscape of video understanding, highlight various challenges, go through some of Facebook's recent efforts and promising results in this area and also give a longer-term perspective on a few exciting directions we want to push forward. In all, we are in an exciting time and place; Manohar hopes to convince the audience of the same.