Search results
Enter terms
342 results found.
Section: Publications & Resources
Publication: IEEE Signal Processing Magazine
Abstract: Continual learning refers to the problem of learning multiple tasks presented sequentially to the learner without forgetting previously learned tasks. Recently, many deep learning-based approaches have been proposed for continual learning; however, the mathematical foundations behind existing continual learning methods remain underdeveloped. On the other hand, adaptive filtering is a classic subject in signal processing with a rich history of mathematically principled methods. However, its role in understanding the foundations of continual learning has been underappreciated.
Section: Publications & Resources
Publication: IEEE Signal Processing Magazine
You may have noticed that our magazine covers have been venturing beyond the customary look of a technical publication. I hope this shift has been enjoyable for you to see. I confess that I’ve been enjoying it myself, particularly the process of selecting the images and shaping the final composition. It has been an engaging experience exploring the possibilities and connections between the ideas we wish to highlight and images drawn from the natural world.
Section: Community & Involvement
IEEE Signal Processing Cup at IEEE ICASSP 2026AV Zoom: Real-Time Audio-Visual Zooming on SmartphonesIEEE ICASSP 2026 Website | 4-8 May 2026 | 2026 SP Cup Official Document[Sponsored by the MathWorks and IEEE Signal Processing Society]
Section: Events
Date: 28 September - 1 October 2026
Location: Atlanta, GA, USA
Conference Paper Submission Deadline: 12 June 2026
Website: https://mlsp26.ieeesps.org/
Section: Events
Date: 26-June-2026
Time: 1:00 PM ET (New York Time)
Presenter: Dr. Candace Fleischer
Website link: Join Webinar Link
Section: Events
Date: 11 July 2026
Location: Bangalore, Karnataka, India
Website: https://sps.ieeebangalore.org/sps-forum-2026/
Issue Date:
Section: Publications & Resources
The Nominations and Appointments Subcommittee of each Technical Committee is currently accepting nominations for new Members, and, where applicable, the Vice Chair position. Nominations should be submitted directly to the respective Technical Committee’s Nominations and Appointments Subcommittee by 15 September 2026.
This talk is about conversational AI and how far are we from being able to talk to AI in natural languages. The talk will touch upon modelling and implementation of the AI embodiment in a photorealistic manner. It will explain machine learning, computer vision and Generative AI methods developed to this end and used for photorealistic AI Buddies generation. The talk will end in discussion of possible applications and misuses of this technology, including Deep Fakes.
The demand for high-quality, low-latency, high-density live streaming is rapidly growing, driven by content such as sports, gaming, and real-time events. This talk focuses on GPU-based, AI-driven video compression solutions, particularly for infrastructures already utilizing NVIDIA’s NVENC hardware (HW) encoder, which offers high density and low compute cost for live transcoding.
GPU-based HW encoding outperforms CPU-based software solutions w.r.t. density and latency. However, it often falls short in visual quality and bitrate efficiency.
In this industry keynote talk, Dr. Yuri Resnik, founder and CTO of Streaming Labs, presents a retrospective and forward-looking analysis of the evolution of video and video delivery technologies. He traces the history of video from the ancient camera obscura to modern AI-generated content, detailing how critical inventions like the fast Fourier transform (FFT) boosted digital image processing and how the strategic addition of delay made internet streaming viable.
