Author: Ekrem Çetinkaya

Ekrem Çetinkaya
126 POSTS0 COMMENTS
Ekrem Çetinkaya received his B.Sc. in 2018, and M.Sc. in 2019 from Ozyegin University, Istanbul, Türkiye. He wrote his M.Sc. thesis about image denoising using deep convolutional networks. He received his Ph.D. degree in 2023 from the University of Klagenfurt, Austria, with his dissertation titled "Video Coding Enhancements for HTTP Adaptive Streaming Using Machine Learning." His research interests include deep learning, computer vision, video encoding, and multimedia networking.

Meta AI Researchers Propose Token Merging (ToMe) to Make Vision Transformers Run Faster

Vision transformers (ViT) were introduced to the literature two years ago, and they became a core component of computer vision research. Taking a component...

Meet MagicMix: An AI Model That Brings Semantic Mixing Capability to Image Diffusion Models

Large-scale text-conditioned image generation models have shown impressive results in recent years. They can generate realistic-looking images given a text prompt. These models are...

Meet Prompt-to-Prompt: An Artificial Intelligence AI Model That Brings Image Editing Capabilities to Text-to-Image Models

It is okay to assume everybody has heard about the Stable Diffusion or DALL-E at this point. The huge craze about text-to-image models has...

Researchers from ETH Zurich and Microsoft Propose ‘LaMAR,’ a New Benchmark for Localization and Mapping for Augmented Reality

Augmented reality (AR) is on its way to becoming a part of our daily lives. We can define it as placing a virtual object...

Meet DALL-E-Bot: An Artificial Intelligence (AI) Based Robotics System That Gives Web-Scale Diffusion Models An Embodiment To Realise The Scenes That They Imagine

Nowadays, it is difficult to pass a day without reading/hearing about a new application of diffusion models if you are following the news about...

Google AI Research Proposes A Deep Learning Based Video Compression Method Using GANs For Detail Synthesis and Propagation

The development in display technologies and the never stopping increase in video content popularity have resulted in a significant demand for video compression to...

Google Researchers Propose a Perceptual Image Quality Assessment Method for Compressed Images Using Deep Learning

Image compression plays a crucial role in the multimedia domain. The increasing number of visual content on the internet is served by scaling data...

Latest Machine Learning Research at UC Berkeley Proposes a Way to Design a Learned Optimizer Using Generative Models of Neural Network Checkpoints

Deep learning methods have been a game-changer in lots of applications. They have been the core components of field advancements in the last decades,...

Researchers from MIT and Microsoft Propose a Practical and Robust Video Conferencing Method Called Gemino That Uses Neural Compression System

We all saw the importance of good-quality video conferencing tools during COVID lockdowns. Education, entertainment, work meetings, and family visits became video conferences, and...

Bonum Commune Communitatis: Standardization of Machine Learning-Based Video Coding Solutions (How Machine Learning ML is used in Video Encoding Part 6)

At this point of the series, I think we can all agree machine learning will play a key role in the future of video...

Solus Ipse?: The Status of End-to-End Video Encoding with Machine Learning (How Machine Learning ML is used in Video Encoding Part 5)

We saw machine learning is used to improve individual components of video codecs. You could get quite an improvement when you replace standard codec...

Semper Maior: Improving Video Decoding with Machine Learning (How Machine Learning ML is used in Video Encoding Part 4)

Encoding the source video to a compressed representation is the first part of the video encoding pipeline. The other part is getting that encoded...

🐝 🐝 Join the Fastest Growing AI Research Newsletter Read by Researchers from Google + NVIDIA + Meta + Stanford + MIT + Microsoft and many others...

X