Media Integration and Communication Center

MICC-UniFi's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

ABaldrati 

authored a paper 3 months ago

Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

Paper • 2502.04263 • Published Feb 6 • 1

marcomistretta 

authored a paper 5 months ago

Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

Paper • 2502.04263 • Published Feb 6 • 1

emanuelevivoli 

authored 2 papers 5 months ago

HoloMine: A Synthetic Dataset for Buried Landmines Recognition using Microwave Holographic Imaging

Paper • 2502.21054 • Published Feb 28

ComicsPAP: understanding comic strips by picking the correct panel

Paper • 2503.08561 • Published Mar 11 • 2

LorenzoAgnolucci 

authored 8 papers 5 months ago

Restoration of Analog Videos Using Swin-UNet

Paper • 2311.04261 • Published Nov 7, 2023

ARNIQA: Learning Distortion Manifold for Image Quality Assessment

Paper • 2310.14918 • Published Oct 20, 2023

Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution

Paper • 2502.06476 • Published Feb 10

UHD-IQA Benchmark Database: Pushing the Boundaries of Blind Photo Quality Assessment

Paper • 2406.17472 • Published Jun 25, 2024

AIM 2024 Challenge on UHD Blind Photo Quality Assessment

Paper • 2409.16271 • Published Sep 24, 2024

Perceptual Quality Improvement in Videoconferencing using Keyframes-based GAN

Paper • 2311.04263 • Published Nov 7, 2023

Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

Paper • 2502.04263 • Published Feb 6 • 1

Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment

Paper • 2403.11176 • Published Mar 17, 2024

emanuelevivoli 

authored 2 papers 10 months ago

ComiCap: A VLMs pipeline for dense captioning of Comic Panels

Paper • 2409.16159 • Published Sep 24, 2024 • 1

Towards Generative Class Prompt Learning for Fine-grained Visual Recognition

Paper • 2409.01835 • Published Sep 3, 2024

marcomistretta 

authored a paper 11 months ago

Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation

Paper • 2407.03056 • Published Jul 3, 2024 • 1

MarcoBertini 

authored 5 papers 11 months ago

Reference-based Restoration of Digitized Analog Videotapes

Paper • 2310.14926 • Published Oct 20, 2023

Multimodal-Conditioned Latent Diffusion Models for Fashion Image Editing

Paper • 2403.14828 • Published Mar 21, 2024

Comics Datasets Framework: Mix of Comics datasets for detection benchmarking

Paper • 2407.03540 • Published Jul 3, 2024 • 3

CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding

Paper • 2407.03550 • Published Jul 4, 2024 • 2

Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation

Paper • 2407.03056 • Published Jul 3, 2024 • 1