Multimedia and Human Understanding Group

university

http://mhug.disi.unitn.it/#/research

Activity Feed Request to join this org

AI & ML interests

Multimedia and Human Understanding Group, DISI @ UNITN, Trento, Italy

Recent Activity

marco-garosi submitted a paper about 6 hours ago

Large Multimodal Models as General In-Context Classifiers

s-angheben submitted a paper 1 day ago

Specificity-aware reinforcement learning for fine-grained open-world classification

s-angheben authored a paper 1 day ago

Specificity-aware reinforcement learning for fine-grained open-world classification

View all activity

Papers

Specificity-aware reinforcement learning for fine-grained open-world classification

Large Multimodal Models as General In-Context Classifiers

View all Papers

submitted a paper to Daily Papers about 6 hours ago

Large Multimodal Models as General In-Context Classifiers

Paper • 2602.23229 • Published 8 days ago • 10

submitted a paper to Daily Papers 1 day ago

Specificity-aware reinforcement learning for fine-grained open-world classification

Paper • 2603.03197 • Published 3 days ago • 9

authored a paper 1 day ago

Specificity-aware reinforcement learning for fine-grained open-world classification

Paper • 2603.03197 • Published 3 days ago • 9

authored a paper 3 days ago

Compositional Caching for Training-free Open-vocabulary Attribute Detection

Paper • 2503.19145 • Published Mar 24, 2025 • 2

Markus-Pobitzer

authored a paper 3 months ago

Loomis Painter: Reconstructing the Painting Process

Paper • 2511.17344 • Published Nov 21, 2025 • 17

Markus-Pobitzer

authored a paper 9 months ago

Outline-Guided Object Inpainting with Diffusion Models

Paper • 2402.16421 • Published Feb 26, 2024 • 1

authored a paper 9 months ago

EarthMind: Towards Multi-Granular and Multi-Sensor Earth Observation with Large Multimodal Models

Paper • 2506.01667 • Published Jun 2, 2025 • 21

authored a paper 11 months ago

On Large Multimodal Models as Open-World Image Classifiers

Paper • 2503.21851 • Published Mar 27, 2025 • 6

authored 2 papers 11 months ago

On Large Multimodal Models as Open-World Image Classifiers

Paper • 2503.21851 • Published Mar 27, 2025 • 6

Compositional Caching for Training-free Open-vocabulary Attribute Detection

Paper • 2503.19145 • Published Mar 24, 2025 • 2

authored a paper over 1 year ago

Automatic benchmarking of large multimodal models via iterative experiment programming

Paper • 2406.12321 • Published Jun 18, 2024

authored 3 papers almost 2 years ago

Vocabulary-free Image Classification and Semantic Segmentation

Paper • 2404.10864 • Published Apr 16, 2024

Test-Time Zero-Shot Temporal Action Localization

Paper • 2404.05426 • Published Apr 8, 2024

Socially Pertinent Robots in Gerontological Healthcare

Paper • 2404.07560 • Published Apr 11, 2024

authored 2 papers over 2 years ago

The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation

Paper • 2308.09139 • Published Aug 17, 2023

Multimodal Emotion Recognition with Modality-Pairwise Unsupervised Contrastive Loss

Paper • 2207.11482 • Published Jul 23, 2022

authored a paper almost 3 years ago

Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition

Paper • 2210.05246 • Published Oct 11, 2022

authored 2 papers almost 3 years ago

Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition

Paper • 2210.05246 • Published Oct 11, 2022

Vocabulary-free Image Classification

Paper • 2306.00917 • Published Jun 1, 2023 • 1