no code implementations • 2 Oct 2024 • Mattia Segu, Luigi Piccinelli, Siyuan Li, Yung-Hsu Yang, Bernt Schiele, Luc van Gool
Multiple object tracking in complex scenarios - such as coordinated dance performances, team sports, or dynamic animal groups - presents unique challenges.
no code implementations • 25 Sep 2024 • Mattia Segu, Luigi Piccinelli, Siyuan Li, Luc van Gool, Fisher Yu, Bernt Schiele
The supervision of state-of-the-art multiple object tracking (MOT) methods requires enormous annotation efforts to provide bounding boxes for all frames of all videos, and instance IDs to associate them through time.
1 code implementation • CVPR 2024 • Siyuan Li, Lei Ke, Martin Danelljan, Luigi Piccinelli, Mattia Segu, Luc van Gool, Fisher Yu
The robust association of the same objects across video frames in complex scenes is crucial for many applications, especially Multiple Object Tracking (MOT).
1 code implementation • CVPR 2024 • Rui Li, Tobias Fischer, Mattia Segu, Marc Pollefeys, Luc van Gool, Federico Tombari
We propose KYN, a novel method for single-view scene reconstruction that reasons about semantic and spatial context to predict each point's density.
3 code implementations • CVPR 2024 • Luigi Piccinelli, Yung-Hsu Yang, Christos Sakaridis, Mattia Segu, Siyuan Li, Luc van Gool, Fisher Yu
However, the remarkable accuracy of recent MMDE methods is confined to their training domains.
Ranked #5 on Monocular Depth Estimation on KITTI Eigen split (using extra training data)
1 code implementation • 4 Oct 2023 • Zhizheng Liu, Mattia Segu, Fisher Yu
Continual learning allows a model to learn multiple tasks sequentially while retaining the old knowledge without the training data of the preceding tasks.
1 code implementation • ICCV 2023 • Mattia Segu, Bernt Schiele, Fisher Yu
However, the nature of a MOT system is manifold - requiring object detection and instance association - and adapting all its components is non-trivial.
no code implementations • 8 Nov 2022 • Qi Fan, Mattia Segu, Yu-Wing Tai, Fisher Yu, Chi-Keung Tang, Bernt Schiele, Dengxin Dai
Thus, we propose to perturb the channel statistics of source domain features to synthesize various latent styles, so that the trained deep model can perceive diverse potential domains and generalizes well even without observations of target domain data in training.
1 code implementation • CVPR 2022 • Tao Sun, Mattia Segu, Janis Postels, Yuxuan Wang, Luc van Gool, Bernt Schiele, Federico Tombari, Fisher Yu
Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous driving systems.
no code implementations • CVPR 2022 • Muhammad Zaigham Zaheer, Arif Mahmood, Muhammad Haris Khan, Mattia Segu, Fisher Yu, Seung-Ik Lee
Video anomaly detection is well investigated in weakly-supervised and one-class classification (OCC) settings.
2 code implementations • 1 Jul 2021 • Janis Postels, Mattia Segu, Tao Sun, Luca Sieber, Luc van Gool, Fisher Yu, Federico Tombari
We find that, while DUMs scale to realistic vision tasks and perform well on OOD detection, the practicality of current methods is undermined by poor calibration under distributional shifts.
Out of Distribution (OOD) Detection Semantic Segmentation +1
no code implementations • 26 Nov 2020 • Mattia Segu, Federico Pirovano, Gianmario Fumagalli, Amedeo Fabris
The key component of our method is the Depth-Aware Pose Motion representation (DA-PoTion), a new video descriptor that encodes the 3D movement of semantic keypoints of the human body.
1 code implementation • 26 Nov 2020 • Mattia Segu, Margarita Grinvald, Roland Siegwart, Federico Tombari
Transferring the style from one image onto another is a popular and widely studied task in computer vision.
no code implementations • 25 Nov 2020 • Mattia Segu, Alessio Tonioni, Federico Tombari
Several recent methods use multiple datasets to train models to extract domain-invariant features, hoping to generalize to unseen domains.
Ranked #73 on Domain Generalization on PACS