2025 Cycle 2 IEEE SPS Chapter Initiative on Multimedia Signal Processing
The 2025 Cycle 2 Chapter Initiative on Multimedia Signal Processing is a one-day event organized by the IEEE Signal Processing Society Student Branch Chapter of the Polytechnic of Leiria, in collaboration with the IEEE SPS Chapter Portugal, and sponsored through a Membership Driven Initiative of the Signal Processing Society.
The event aims to bring together the Signal Processing community in Portugal and beyond, fostering the exchange of research activities, discussion of recent advances, and the creation of new collaboration opportunities in the field of Multimedia Signal Processing.
The program features a dynamic lineup that includes two keynote talks by invited international speakers, spotlight presentations by PhD students, and discussion panels, exploring the current research trends and challenges.
The invited keynote speakers are:
- João Magalhães (NOVA University of Lisbon, Portugal) – AMALIA: An Open Source Large Language Model for European Portuguese
- Yiyi Liao (Zhejiang University, China) – Towards Efficient Volumetric Video: Compression and Standardization of Gaussian Splats
Master’s and PhD students are encouraged to bring a poster presenting their recent research work, offering an opportunity to share ideas and engage in technical discussions with researchers and members of the community.
The event will take place on January 30, 2025, at Campus 2 of the Polytechnic of Leiria, Building B, Auditorium 2.
Participation is free of charge, but prior registration is required.
Additional information and the (continuously updated) program are available at: https://www.mmspleiria2025.pt/
Registration is available at: https://forms.gle/yi7dATLuWKtAopz46
The event is open to the entire community, and participants are encouraged to share this invitation with colleagues and students who may be interested.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- ESTG - Polytechnic of Leiria
- Campus 2 Morro da Lena - Alto do Vieiro
- Leiria, Centro
- Portugal 2400-822
- Building: B
- Room Number: Auditorium 2
- Click here for Map
Speakers
João Magalhães of Universidade NOVA de Lisboa
AMALIA: An Open Source Large Language Model for European Portuguese
Despite rapid progress in open large language models (LLMs), European Portuguese (pt-PT) remains underrepresented in both training data and native evaluation, with machine-translated benchmarks likely missing the variant's linguistic and cultural nuances. We introduce AMALIA a fully open LLM that prioritizes pt-PT by using more high-quality pt-PT data during both the mid- and post-training stages. To evaluate pt-PT more faithfully, we release a suite of pt-PT benchmarks that includes translated standard tasks and four new datasets targeting pt-PT generation, linguistic competence, and pt-PT/pt-BR bias. Experiments show that AMALIA matches strong baselines on translated benchmarks while substantially improving performance on pt-PT-specific evaluations, supporting the case for targeted training and native benchmarking for European Portuguese.
Address:Portugal
Yiyi Liao of Zhejiang University
Towards Efficient Volumetric Video: Compression and Standardization of Gaussian Splats
Recent advances in novel view synthesis have enabled high-quality volumetric video from real-world imagery, bringing photorealistic immersive media closer to practical deployment. 3D Gaussian Splatting achieves real-time rendering, but at the cost of significantly higher memory usage, exposing a key trade-off between speed and storage. Efficient compression is therefore essential to reduce memory footprints while preserving real-time performance. This talk will introduce GSCodec Studio, a toolbox integrating modular compression techniques for Gaussian Splats, followed by an exploration of 4D scene representations and corresponding compression methods for volumetric video. Finally, I will discuss recent exploration efforts within MPEG toward standardizing Gaussian Splatting codecs to enable broad industry adoption.
Address:China