Author: Daniele Lorenzi

66 POSTS0 COMMENTS
Daniele Lorenzi received his M.Sc. in ICT for Internet and Multimedia Engineering in 2021 from the University of Padua, Italy. He is a Ph.D. candidate at the Institute of Information Technology (ITEC) at the Alpen-Adria-Universität (AAU) Klagenfurt. He is currently working in the Christian Doppler Laboratory ATHENA and his research interests include adaptive video streaming, immersive media, machine learning, and QoS/QoE evaluation.

Meet StableSR: A Novel AI Super-Resolution Approach Exploiting the Power of Pre-Trained Diffusion Models

Significant progress has been observed in the development of diffusion models for various image synthesis tasks in the field of computer vision. Prior research...

Meet BLIVA: A Multimodal Large Language Model for Better Handling of Text-Rich Visual Questions

Recently, Large Language Models (LLMs) have played a crucial role in the field of natural language understanding, showcasing remarkable capabilities in generalizing across a...

A New AI Research from Tel Aviv and the University of Copenhagen Introduces a ‘Plug-and-Play’ Approach for Rapidly Fine-Tuning Text-to-Image Diffusion Models by Using...

Text-to-image diffusion models have exhibited impressive success in generating diverse and high-quality images based on input text descriptions. Nevertheless, they encounter challenges when the...

Meet WavJourney: An AI Framework For Compositional Audio Creation With Large Language Models

The emerging field of multi-modal artificial intelligence (AI) converges visual, auditory, and textual data, offering exciting potential in various domains, from personalized entertainment to...

Unveil The Secrets Of Anatomical Segmentation With HybridGNet: An AI Encoder-Decoder For Plausible Anatomical Structures Decoding

Recent advancements in deep neural networks have enabled new approaches to address anatomical segmentation. For instance, state-of-the-art performance in the anatomical segmentation of biomedical...

Meet DenseDiffusion: A Training-free AI Technique To Address Dense Captions and Layout Manipulation In Text-to-Image Generation

Recent advancements in text-to-image models have led to sophisticated systems capable of generating high-quality images based on brief scene descriptions. Nevertheless, these models encounter...

Decoding Emotions: Unveiling Feelings And Mental States with EmoTX, A Novel Transformer-Powered AI Framework

Movies are among the most artistic expressions of stories and feelings. For instance, in "The Pursuit of Happyness," the protagonist goes through a range...

From Words to Worlds: Exploring Video Narration With AI Multi-Modal Fine-grained Video Description

Language is the predominant mode of human interaction, offering more than just supplementary details to other faculties like sight and sound. It also serves...

Beyond the Pen: AI’s Artistry in Handwritten Text Generation from Visual Archetypes

The emerging field of Styled Handwritten Text Generation (HTG) seeks to create handwritten text images that replicate the unique calligraphic style of individual writers....

AI Researchers From Apple And The University Of British Columbia Propose FaceLit: A Novel AI Framework For Neural 3D Relightable Faces

In recent times, there has been a growing fascination with the task of acquiring a 3D generative model from 2D images. With the advent...

Google AI Research Proposes VidLNs: An Annotation Procedure that Obtains Rich Video Descriptions that are Semantically Correct and Densely Grounded with Accurate Spatio-Temporal Localizations

Vision and language research is a dynamically evolving field that has recently witnessed remarkable advancements, particularly in datasets that establish connections between static images...

Detect Anything You Want With UniDetector

Deep learning and AI have made remarkable progress in recent years, especially in detection models. Despite these impressive advancements, the effectiveness of object detection...

Check Out Our Super Cool AI Research Newsletter While It's Still Free

X