Mattia Segù

40 papers A* 11Journal 26Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler.
IEEE Trans. Pattern Anal. Mach. Intell.
Luigi Piccinelli, Christos Sakaridis, Yung-Hsu Yang, Mattia Segù, Siyuan Li, Wim Abbeloos, Luc Van Gool
2025 J jnl
3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection.
CoRR
Yung-Hsu Yang, Luigi Piccinelli, Mattia Segù, Siyuan Li, Rui Huang, Yuqian Fu, Marc Pollefeys, Hermann Blum, Zuria Bauer
2025 J jnl
Lost in Translation? Vocabulary Alignment for Source-Free Adaptation in Open-Vocabulary Semantic Segmentation.
CoRR
Silvio Mazzucco, Carl Persson, Mattia Segù, Pier Luigi Dovesi, Federico Tombari, Luc Van Gool, Matteo Poggi
2025 J jnl
MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning.
CoRR
Mattia Segù, Marta Tintore Gazulla, Yongqin Xian, Luc Van Gool, Federico Tombari
2025 J jnl
Robust Object Detection with Domain-Invariant Training and Continual Test-Time Adaptation.
Int. J. Comput. Vis.
Qi Fan, Mattia Segù, Bernt Schiele, Dengxin Dai, Yu-Wing Tai, Chi-Keung Tang
2025 A* conf
Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking.
ICLR
Mattia Segù, Luigi Piccinelli, Siyuan Li, Yung-Hsu Yang, Luc Van Gool, Bernt Schiele
2025 A* conf
Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation.
CVPR
Reza Qorbani, Gianluca Villani, Theodoros Panagiotakopoulos, Marc Botet Colomer, Linus Härenstam-Nielsen, Mattia Segù, Pier Luigi Dovesi, Jussi Karlgren, Daniel Cremers, Federico Tombari, Matteo Poggi
2025 J jnl
Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation.
CoRR
Reza Qorbani, Gianluca Villani, Theodoros Panagiotakopoulos, Marc Botet Colomer, Linus Härenstam-Nielsen, Mattia Segù, Pier Luigi Dovesi, Jussi Karlgren, Daniel Cremers, Federico Tombari, Matteo Poggi
2025 J jnl
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler.
CoRR
Luigi Piccinelli, Christos Sakaridis, Yung-Hsu Yang, Mattia Segù, Siyuan Li, Wim Abbeloos, Luc Van Gool
2025 A* conf
UniK3D: Universal Camera Monocular 3D Estimation.
CVPR
Luigi Piccinelli, Christos Sakaridis, Mattia Segù, Yung-Hsu Yang, Siyuan Li, Wim Abbeloos, Luc Van Gool
2025 J jnl
UniK3D: Universal Camera Monocular 3D Estimation.
CoRR
Luigi Piccinelli, Christos Sakaridis, Mattia Segù, Yung-Hsu Yang, Siyuan Li, Wim Abbeloos, Luc Van Gool
2024 A* conf
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning.
CVPR
Rui Li, Tobias Fischer, Mattia Segù, Marc Pollefeys, Luc Van Gool, Federico Tombari
2024 J jnl
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning.
CoRR
Rui Li, Tobias Fischer, Mattia Segù, Marc Pollefeys, Luc Van Gool, Federico Tombari
2024 A* conf
Matching Anything by Segmenting Anything.
CVPR
Siyuan Li, Lei Ke, Martin Danelljan, Luigi Piccinelli, Mattia Segù, Luc Van Gool, Fisher Yu
2024 J jnl
Matching Anything by Segmenting Anything.
CoRR
Siyuan Li, Lei Ke, Martin Danelljan, Luigi Piccinelli, Mattia Segù, Luc Van Gool, Fisher Yu
2024 — conf
SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking.
ECCV (27)
Siyuan Li, Lei Ke, Yung-Hsu Yang, Luigi Piccinelli, Mattia Segù, Martin Danelljan, Luc Van Gool
2024 J jnl
SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking.
CoRR
Siyuan Li, Lei Ke, Yung-Hsu Yang, Luigi Piccinelli, Mattia Segù, Martin Danelljan, Luc Van Gool
2024 J jnl
Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking.
CoRR
Mattia Segù, Luigi Piccinelli, Siyuan Li, Yung-Hsu Yang, Bernt Schiele, Luc Van Gool
2024 A* conf
UniDepth: Universal Monocular Metric Depth Estimation.
CVPR
Luigi Piccinelli, Yung-Hsu Yang, Christos Sakaridis, Mattia Segù, Siyuan Li, Luc Van Gool, Fisher Yu
2024 J jnl
UniDepth: Universal Monocular Metric Depth Estimation.
CoRR
Luigi Piccinelli, Yung-Hsu Yang, Christos Sakaridis, Mattia Segù, Siyuan Li, Luc Van Gool, Fisher Yu
2024 — conf
Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Appearance Graphs.
ECCV (8)
Mattia Segù, Luigi Piccinelli, Siyuan Li, Luc Van Gool, Fisher Yu, Bernt Schiele
2024 J jnl
Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Appearance Graphs.
CoRR
Mattia Segù, Luigi Piccinelli, Siyuan Li, Luc Van Gool, Fisher Yu, Bernt Schiele
2023 J jnl
Batch normalization embeddings for deep domain generalization.
Pattern Recognit.
Mattia Segù, Alessio Tonioni, Federico Tombari
2023 — conf
COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking.
DAGM
Zhizheng Liu, Mattia Segù, Fisher Yu
2023 J jnl
COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking.
CoRR
Zhizheng Liu, Mattia Segù, Fisher Yu
2023 A* conf
DARTH: Holistic Test-time Adaptation for Multiple Object Tracking.
ICCV
Mattia Segù, Bernt Schiele, Fisher Yu
2023 J jnl
DARTH: Holistic Test-time Adaptation for Multiple Object Tracking.
CoRR
Mattia Segù, Bernt Schiele, Fisher Yu
2023 A* conf
Towards Robust Object Detection Invariant to Real-World Domain Shifts.
ICLR
Qi Fan, Mattia Segù, Yu-Wing Tai, Fisher Yu, Chi-Keung Tang, Bernt Schiele, Dengxin Dai
2022 A* conf
Generative Cooperative Learning for Unsupervised Video Anomaly Detection.
CVPR
Muhammad Zaigham Zaheer, Arif Mahmood, Muhammad Haris Khan, Mattia Segù, Fisher Yu, Seung-Ik Lee
2022 J jnl
Generative Cooperative Learning for Unsupervised Video Anomaly Detection.
CoRR
Muhammad Zaigham Zaheer, Arif Mahmood, Muhammad Haris Khan, Mattia Segù, Fisher Yu, Seung-Ik Lee
2022 J jnl
Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts.
CoRR
Qi Fan, Mattia Segù, Yu-Wing Tai, Fisher Yu, Chi-Keung Tang, Bernt Schiele, Dengxin Dai
2022 A* conf
On the Practicality of Deterministic Epistemic Uncertainty.
ICML
Janis Postels, Mattia Segù, Tao Sun, Luca Daniel Sieber, Luc Van Gool, Fisher Yu, Federico Tombari
2022 A* conf
SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation.
CVPR
Tao Sun, Mattia Segù, Janis Postels, Yuxuan Wang, Luc Van Gool, Bernt Schiele, Federico Tombari, Fisher Yu
2022 J jnl
SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation.
CoRR
Tao Sun, Mattia Segù, Janis Postels, Yuxuan Wang, Luc Van Gool, Bernt Schiele, Federico Tombari, Fisher Yu
2021 J jnl
On the Practicality of Deterministic Epistemic Uncertainty.
CoRR
Janis Postels, Mattia Segù, Tao Sun, Luc Van Gool, Fisher Yu, Federico Tombari
2020 J jnl
3DSNet: Unsupervised Shape-to-Shape 3D Style Transfer.
CoRR
Mattia Segù, Margarita Grinvald, Roland Siegwart, Federico Tombari
2020 J jnl
A General Framework for Uncertainty Estimation in Deep Learning.
IEEE Robotics Autom. Lett.
Antonio Loquercio, Mattia Segù, Davide Scaramuzza
2020 J jnl
Batch Normalization Embeddings for Deep Domain Generalization.
CoRR
Mattia Segù, Alessio Tonioni, Federico Tombari
2020 J jnl
Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps.
CoRR
Mattia Segù, Federico Pirovano, Gianmario Fumagalli, Amedeo Fabris
2019 J jnl
A General Framework for Uncertainty Estimation in Deep Learning.
CoRR
Mattia Segù, Antonio Loquercio, Davide Scaramuzza