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 Proposes a Novel System for Text-to-4D (3D+time) Generation by Combining the Benefits of Video and 3D Generative Models

The last quarter of 2022 was the era of text-to-image models. We have seen numerous successful examples that could generate realistic images from text...

Did ChatGPT Write This? This AI Technique Can Help You Identify AI Written Text

You probably heard about or even used ChatGPT at this point. OpenAI’s new magical tool is there to answer your questions, help you write...

Welcome to the New Saga Introduced by MusicLM: This AI Model can Generate Music from Text Descriptions

There has been an explosion of generative AI models in the last couple of months. We’ve seen models that could generate realistic images from...

Is it Possible to Detect Images Generated by Stable Diffusion? This AI Paper Searches for the Answer

Stable diffusion. If you are interested in the AI domain, there is an extremely high chance that you heard about it. It was everywhere...

Meet NIRVANA: An AI Model That Uses Neural Implicit Representations to Compress Videos Efficiently

Video has become the dominant information propagation tool in the online world nowadays. The majority of the Internet traffic consists of video content, and...

Researchers from MIT Propose an AI Model that Knows How to Generate Line Drawings from Photographs

If you have ever seen an artist working on a drawing, you probably noticed they start with the line drawing. They draw the outlines...

Meet ConvNeXt V2: An AI Model That Improves the Performance and Scaling Capability of ConvNets Using Masked Autoencoders

The computer vision domain has seen significant advancement in the last decade, and this advancement can be mainly attributed to the emergence of convolutional...

Check out this new Diffusion Probabilistic Model for Video Data that Provides a Unique Implicit Condition Paradigm for Modeling Continuous Spatial-Temporal Changing of Videos

Another day and another blog post about diffusion models. Diffusion models were probably one of the hottest, if not the hottest, topics in the...

This Artificial Intelligence (AI) Research Examines the Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing

In the last decade, convolutional neural networks (CNNs) have been the backbone of computer vision applications. Traditionally, computer vision tasks have been tackled using...

Researchers From the University of Chicago Introduce 3D Highlighter: An Artificial Intelligence (AI) Method for Localizing Regions on 3D Shapes Using Text Descriptions

3D computer graphics have come a long way since their inception in the 1950s. From simple wireframe models to photorealistic renderings, 3D graphics have...

This Lightweight Artificial Intelligence (AI) Model is a Robust Visual Object Tracker that Can Run on Mobile Devices

You probably remember a scene from a movie where we see lots of large screens in a dark room that are tracking cars, people,...

Meet MOAT: An Artificial Intelligence (AI) Model that Combines Convolution and Attention Operations to Achieve Powerful Vision Models

The computer vision domain has seen significant advancement in recent years thanks to the prevalence of self-attention. Self-attention modules have proved to be extremely...

🐝 FREE AI WEBINAR: A Synthetic Data Deep Dive (July 30 2024)

X