Tiberio Uricchio
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tiberio Uricchio has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Alberto Del Bimbo
University of Florence, Florence, Italy
11 shared publications - Marco Bertini
MICC, University of Florence, Florence, Italy
8 shared publications - Lorenzo Seidenari
University of Florence
3 shared publications - Simone Ricci
University of Florence
3 shared publications - Alberto Baldrati
University of Florence, Firenze, Italy and University of Pisa, Pisa, Italy
2 shared publications - Lamberto Ballan
University of Padova
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9774-9782
NeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal Conditioning
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9774-9782
Open AccessNeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal Conditioning
- 2 January 2026
- Published by Springer Nature
- p. 546-558
Prompt-Based Consistent Video Colorization
- 3 June 2025
- Published by Springer Nature
- p. 27-35
Enhancing Universal Access to QoL Assessments: Integrating WHODAS 2.0 and Chatbots
- 3 June 2025
- Published by Springer Nature
- p. 27-35
Enhancing Universal Access to QoL Assessments: Integrating WHODAS 2.0 and Chatbots
- Open Access
- 23 October 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (3) , 1-24
Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
Given a query composed of a reference image and a relative caption, the Composed Image Retrieval goal is to retrieve images visually similar to the reference one that integrates the modifications expressed by the caption. Given that recent research has demonstrated the efficacy of large-scale vision and language pre-trained (VLP) models in various tasks, we rely on features from the OpenAI CLIP model to tackle the considered task. We initially perform a task-oriented fine-tuning of both CLIP encoders using the element-wise sum of visual and textual features. Then, in the second stage, we train a Combiner network that learns to combine the image-text features integrating the bimodal information and providing combined features used to perform the retrieval. We use contrastive learning in both stages of training. Starting from the bare CLIP features as a baseline, experimental results show that the task-oriented fine-tuning and the carefully crafted Combiner network are highly effective and outperform more complex state-of-the-art approaches on FashionIQ and CIRR, two popular and challenging datasets for composed image retrieval. Code and pre-trained models are available at https://github.com/ABaldrati/CLIP4Cir .
- 23 October 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 20 (3) , 1-24
Open AccessComposed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features
Given a query composed of a reference image and a relative caption, the Composed Image Retrieval goal is to retrieve images visually similar to the reference one that integrates the modifications expressed by the caption. Given that recent research has demonstrated the efficacy of large-scale vision and language pre-trained (VLP) models in various tasks, we rely on features from the OpenAI CLIP model to tackle the considered task. We initially perform a task-oriented fine-tuning of both CLIP encoders using the element-wise sum of visual and textual features. Then, in the second stage, we train a Combiner network that learns to combine the image-text features integrating the bimodal information and providing combined features used to perform the retrieval. We use contrastive learning in both stages of training. Starting from the bare CLIP features as a baseline, experimental results show that the task-oriented fine-tuning and the carefully crafted Combiner network are highly effective and outperform more complex state-of-the-art approaches on FashionIQ and CIRR, two popular and challenging datasets for composed image retrieval. Code and pre-trained models are available at https://github.com/ABaldrati/CLIP4Cir .
- 5 September 2023
- Published by Springer Nature
- p. 450-462
Smoothing and Transition Matrices Estimation to Learn with Noisy Labels
- 5 September 2023
- Published by Springer Nature
- p. 450-462
Smoothing and Transition Matrices Estimation to Learn with Noisy Labels
- Open Access
- 7 June 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (5s) , 1-23
Meta-learning Advisor Networks for Long-tail and Noisy Labels in Social Image Classification
Deep neural networks (DNNs)for social image classification are prone to performance reduction and overfitting when trained on datasets plagued by noisy or imbalanced labels. Weight loss methods tend to ignore the influence of noisy or frequent category examples during the training, resulting in a reduction of final accuracy and, in the presence of extreme noise, even a failure of the learning process. A new advisor network is introduced to address both imbalance and noise problems, and is able to pilot learning of a main network by adjusting the visual features and the gradient with a meta-learning strategy. In a curriculum learning fashion, the impact of redundant data is reduced while recognizable noisy label images are downplayed or redirected.Meta Feature Re-Weighting (MFRW)andMeta Equalization Softmax (MES)methods are introduced to let the main network focus only on the information in an image deemed relevant by the advisor network and to adjust the training gradient to reduce the adverse effects of frequent or noisy categories. The proposed method is first tested on synthetic versions of CIFAR10 and CIFAR100, and then on the more realistic ImageNet-LT, Places-LT, and Clothing1M datasets, reporting state-of-the-art results.
- 7 June 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 19 (5s) , 1-23
Open AccessMeta-learning Advisor Networks for Long-tail and Noisy Labels in Social Image Classification
Deep neural networks (DNNs)for social image classification are prone to performance reduction and overfitting when trained on datasets plagued by noisy or imbalanced labels. Weight loss methods tend to ignore the influence of noisy or frequent category examples during the training, resulting in a reduction of final accuracy and, in the presence of extreme noise, even a failure of the learning process. A new advisor network is introduced to address both imbalance and noise problems, and is able to pilot learning of a main network by adjusting the visual features and the gradient with a meta-learning strategy. In a curriculum learning fashion, the impact of redundant data is reduced while recognizable noisy label images are downplayed or redirected.Meta Feature Re-Weighting (MFRW)andMeta Equalization Softmax (MES)methods are introduced to let the main network focus only on the information in an image deemed relevant by the advisor network and to adjust the training gradient to reduce the adverse effects of frequent or noisy categories. The proposed method is first tested on synthetic versions of CIFAR10 and CIFAR100, and then on the more realistic ImageNet-LT, Places-LT, and Clothing1M datasets, reporting state-of-the-art results.
- Open Access
- 1 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 13
Message from the General Co-Chairs
Presents the conference keynote speech, welcome speech, plenary speech, or messages from conference chairs.
- 1 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 13
Open AccessMessage from the General Co-Chairs
Presents the conference keynote speech, welcome speech, plenary speech, or messages from conference chairs.
- 30 October 2022
- Published by Springer Nature
- p. 140-149
Exploiting CLIP-Based Multi-modal Approach for Artwork Classification and Retrieval
- 30 October 2022
- Published by Springer Nature
- p. 140-149
Exploiting CLIP-Based Multi-modal Approach for Artwork Classification and Retrieval
- 17 May 2022
- Published by Springer Nature
- p. 442-453
Learning Advisor Networks for Noisy Image Classification
- 17 May 2022
- Published by Springer Nature
- p. 442-453
Learning Advisor Networks for Noisy Image Classification
- 6 January 2022
- Published by Springer Nature in Machine Vision and Applications
- Vol. 33 (1) , 1-13
Effective triplet mining improves training of multi-scale pooled CNN for image retrieval
- 6 January 2022
- Published by Springer Nature in Machine Vision and Applications
- Vol. 33 (1) , 1-13
Effective triplet mining improves training of multi-scale pooled CNN for image retrieval