Hadi
,

Patent approval for: Perceptually-aware Online Per-title Encoding for Live Video Streaming

Perceptually-aware Online Per-title Encoding for Live Video Streaming – US Patent

PDF

Vignesh Menon (Alpen-Adria-Universität Klagenfurt, Austria), Hadi Amirpour (Alpen-Adria-Universität Klagenfurt, Austria), and Christian Timmerer (Alpen-Adria-Universität Klagenfurt, Austria)

Abstract: Techniques for implementing perceptually aware per-title encoding may include receiving an input video, a set of resolutions, a maximum target bitrate and a minimum target bitrate, extracting content aware features for each segment of the input video, predicting a perceptually aware bitrate-resolution pair for each segment using a model configured to optimize for a quality metric using constants trained for each of the set of resolutions, generating a target encoding set including a set of perceptually aware bitrate-resolution pairs, and encoding the target encoding set. The content aware features may include a spatial energy feature and an average temporal energy. According to these methods only a subset of bitrates and resolutions, less than a full set of bitrates and resolutions, are encoded to provide high quality video content for streaming.

,

“Magic Academy” on 14 January, 2025

On 14 January, Dr Felix Schniz and GSE Student Peter Miklautz organised the “Magic Academy.” The event took place in the library’s Unruhezone and introduced GSE and other students to the concept of Trading Card Games. It served as an introductory event for a series of follow-up “Magic Academies”, which are scheduled for the end of this semester and over the course of next semester. The series concludes in June with a three-day event on academic perspectives on Trading Card Games, featuring international guest speakers, workshops on the mechanics, stochastics, and analytical observations on different card game systems, and an analogue game design mini-game jam.

With over 30 students attending, this kick-off was a magical success!

Mathias Lux
, ,

First Game Creators Barcamp Held at the University of Klagenfurt

Local game developers and researchers gathered for the inaugural Game Creators Barcamp on Friday, December 6th, at the University of Klagenfurt. The event featured discussions on game development, educational technologies, and industry funding opportunities.

The first Barcamp drew a small but engaged group of participants who explored various game design and development topics. Discussions covered diverse areas, including the story behind the game Electric Alps, potential improvements in language learning through gamification, particularly for teaching irregular German verbs, and an examination of game theory in puzzle game design. The attendees also provided an overview of funding schemes available for game studios. Plans are underway for the next Barcamp, scheduled for spring, hoping to increase participant numbers.

Hadi
,

Patent Approval for “Scalable Per-Title Encoding”

Scalable Per-Title Encoding – US Patent

[PDF]

Hadi Amirpour (Alpen-Adria-Universität Klagenfurt, Austria) and Christian Timmerer (Alpen-Adria-Universität Klagenfurt, Austria)

Abstract: A scalable per-title encoding technique may include detecting scene cuts in an input video received by an encoding network or system, generating segments of the input video, performing per-title encoding of a segment of the input video, training a deep neural network (DNN) for each representation of the segment, thereby generating a trained DNN, compressing the trained DNN, thereby generating a compressed trained DNN, and generating an enhanced bitrate ladder including metadata comprising the compressed trained DNN. In some embodiments, the method may also include generating a base layer bitrate ladder for CPU devices and providing the enhanced bitrate ladder for GPU-available devices.

,

Kseniia and Tom @ CHI PLAY 2024

Kseniia and Tom participated in the annual symposium CHI PLAY (Computer-Human Interaction in Play) from October 14–17/online.
They both took part in the doctoral consortium, where they presented their works and built connections with fellow doctoral students and experienced researchers in the field.
Kseniia presented her topic, “Developing a Virtual-Reality Game for Empathy Enhancement and Perspective-Taking in the Context of Forced Migration Experiences”, and Tom presented his topic, “Enhancing Empathy Through Personalized AI-Driven Experiences and Conversations with Digital Humans in Video Games”.
Proceedings are published under Companion Proceedings of the Annual Symposium on Computer-Human Interaction in Play (CHI PLAY Companion ’24), October 14–17, 2024, Tampere, Finland.

,

Kseniia Harshina @ FROG Conference, Vienna (Future and Reality of Gaming 2024)

Kseniia participated in the annual FROG conference from 11 to 13 October, which had the topic of “Gaming the Apocalypse”. Her talk, “Unraveling the Romanticization of Colonial, Imperial and Authoritarian Narratives in Modern Video Games”, showcased a trend in video games to cutefy serious topics like historical power dynamics through aesthetics, and explained the potential issues caused by this phenomenon.

Her talk can be seen on YouTube (https://www.youtube.com/watch?v=37-sqVJrMoY), and proceedings will follow in the summer of 2025.

,

Keynote talk @ 21st EAI International Conference on Mobile and Ubiquitous Systems (MobiQuitous 2024)

Radu Prodan is invited to give a keynote talk at the 21st EAI International Conference on Mobile and Ubiquitous Systems (MobiQuitous 2024), which will be held from November 12-14,2024, in Oslo, Norway.

Abstract:

The presentation starts by reviewing the convergence of two historically disconnected AI branches: symbolic AI of explicit deductive reasoning owning mathematical rigor and interpretability, and connectionist AI of implicit inductive reasoning lacking readability and explainability.
Afterward, it makes a case of neuro-symbolic data processing in knowledge graph representation approached by the Graph-Massivizer Horizon Europe project and applied for anomaly prediction in data centers using graph neural networks. Machine learning-driven graph sampling algorithms support its training and inference on resource-constrained Edge devices. The presentation concludes with an outlook into future projects targeting Edge large language models fine-tuned and contextualized using symbolic knowledge representation for regulatory AI compliance, job market, and medicine.

,

Felix Schniz @ FROG Conference, Vienna (Future and Reality of Gaming 2024)

From 11 to 13 October, ITEC’s Felix Schniz participated in the annual FROG (Future and Reality of Gaming) conference in Vienna. It is Austria’s biggest, (video) game dedicated academic conference, which attracted 50 speakers from 12 countries this year. Under this year’s topic of “Gaming the Apocalypse”, Felix delivered the talk “Scales of Apocalypse: Space and Affect in Dystopian Video Games between Sacred and Profane”.

Also presenting at the conference were AAU’s Kseniia Harshina and the Game Studies and Engineering master students Tim Sanders and Elli Chraibi, showcasing the diverse research interest and academic expertise produced by Game Studies and Engineering staff and students in the field.

The conference proceedings are expected to be published next year Summer.

,

Tom Tuček and Felix Schniz visited the Kwadrat youth centre in Klagenfurt

On Friday, July 5 2024, Tom Tuček and Felix Schniz visited the Kwadrat youth centre in Klagenfurt for a workshop on computer role-playing games. Together with a group of highly motivated youngsters (and Kwadrat staff members!), they analysed the opening sequence of the best-selling game Baldur’s Gate 3 together. Afterwards, they introduced the audience to the pen-and-paper roots of modern role-playing games and invited everybody tomjoin a session of the classic Dungeons and Dragons, wonderfully hosted by Tom.

The workshop was well visited and received. Further events to introduce the Klagenfurt youth to the wonders of computer game design are already in the planning.

 

 

, ,

Klaus Schöffmann gave a Keynote Talk about “The Use of AI in Image and Video Retrieval Over the last Decade” at the MVRMLM 2024 Workshop, co-located with ACM ICMR 2024

Together with Cathal Gurrin from DCU, Ireland, on June 14, 2024, Klaus Schöffmann gave a keynote talk about “From Concepts to Embeddings. Charting the Use of AI in Digital Video and Lifelog Search Over the Last Decade” at the International Workshop on Multimodal Video Retrieval and Multimodal Language Modelling (MVRMLM’24), co-located with the ACM ICMR 2024 conference in Phuket, Thailand.

Link: https://mvrmlm2024.ecit.qub.ac.uk

Here is the abstract of the talk:

In the past decade, the field of interactive multimedia retrieval has undergone a transformative evolution driven by the advances in artificial intelligence (AI). This keynote talk will explore the journey from early concept-based retrieval systems to the sophisticated embedding-based techniques that dominate the landscape today. By examining the progression of such AI-driven approaches at both the VBS (Video Browser Showdown) and the LSC (Lifelog Search Challenge), we will highlight the pivotal role of comparative benchmarking in accelerating innovation and establishing performance standards. We will also forward at the potential future developments in interactive multimedia retrieval benchmarking, including emerging trends, the integration of multimodal data, and the future comparative benchmarking challenges within our community.