85 citations · 105 across the 14 of their papers we have counts for
16 papers
On Large Multimodal Models as Open-World Image Classifiers
Alessandro Conti, Massimiliano Mancini, Enrico Fini +3
Traditional image classification requires a predefined list of semantic categories. In contrast, Large Multimodal Models (LMMs) can sidestep this requirement by classifying images…
Text-Enhanced Zero-Shot Action Recognition: A training-free approach
Massimo Bosetti, Shibingfeng Zhang, Benedetta Liberatori +3
Vision-language models (VLMs) have demonstrated remarkable performance across various visual tasks, leveraging joint learning of visual and textual representations. While these mod…
Test-Time Zero-Shot Temporal Action Localization
Benedetta Liberatori, Alessandro Conti, Paolo Rota +2
Zero-Shot Temporal Action Localization (ZS-TAL) seeks to identify and locate actions in untrimmed videos unseen during training. Existing ZS-TAL methods involve fine-tuning a model…
The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain Adaptation
Giacomo Zara, Alessandro Conti, Subhankar Roy +3
Source-Free Video Unsupervised Domain Adaptation (SFVUDA) task consists in adapting an action recognition model, trained on a labelled source dataset, to an unlabelled target datas…
Vocabulary-free Image Classification
Alessandro Conti, Enrico Fini, Massimiliano Mancini +3
Recent advances in large vision-language models have revolutionized the image classification paradigm. Despite showing impressive zero-shot capabilities, a pre-defined set of categ…
Rotation Synchronization via Deep Matrix Factorization
Gk Tejus, Giacomo Zara, Paolo Rota +3
In this paper we address the rotation synchronization problem, where the objective is to recover absolute rotations starting from pairwise ones, where the unknowns and the measures…
Deep Unsupervised Key Frame Extraction for Efficient Video Classification
Hao Tang, Lei Ding, Songsong Wu +3
Video processing and analysis have become an urgent task since a huge amount of videos (e.g., Youtube, Hulu) are uploaded online every day. The extraction of representative key fra…
Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition
Alessandro Conti, Paolo Rota, Yiming Wang +1
Automatically understanding emotions from visual data is a fundamental task for human behaviour understanding. While models devised for Facial Expression Recognition (FER) have dem…
Unsupervised Domain Adaptation for Video Transformers in Action Recognition
Victor G. Turrisi da Costa, Giacomo Zara, Paolo Rota +4
Over the last few years, Unsupervised Domain Adaptation (UDA) techniques have acquired remarkable importance and popularity in computer vision. However, when compared to the extens…
Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation
Guanglei Yang, Enrico Fini, Dan Xu +5
A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e. the tendency of neural networks to fail to preserve the knowledge acquired from old tasks wh…
Continual Attentive Fusion for Incremental Learning in Semantic Segmentation
Guanglei Yang, Enrico Fini, Dan Xu +5
Over the past years, semantic segmentation, as many other tasks in computer vision, benefited from the progress in deep neural networks, resulting in significantly improved perform…
Variational Structured Attention Networks for Deep Visual Representation Learning
Guanglei Yang, Paolo Rota, Xavier Alameda-Pineda +3
Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction an…
Curriculum Learning: A Survey
Petru Soviany, Radu Tudor Ionescu, Paolo Rota +1
Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard tra…
Low-Budget Label Query through Domain Alignment Enforcement
Jurandy Almeida, Cristiano Saltori, Paolo Rota +1
Deep learning revolution happened thanks to the availability of a massive amount of labelled data which have contributed to the development of models with extraordinary inference c…
Curriculum Self-Paced Learning for Cross-Domain Object Detection
Petru Soviany, Radu Tudor Ionescu, Paolo Rota +1
Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed…
Indirect Match Highlights Detection with Deep Convolutional Neural Networks
Marco Godi, Paolo Rota, Francesco Setti
Highlights in a sport video are usually referred as actions that stimulate excitement or attract attention of the audience. A big effort is spent in designing techniques which find…