Search Results for author: Mattia Segu

Found 14 papers, 8 papers with code

Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking

no code implementations2 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.

Multiple Object Tracking

Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Appearance Graphs

no code implementations25 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.

Multiple Object Tracking

Matching Anything by Segmenting Anything

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).

Domain Generalization Multiple Object Tracking +2

COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking

1 code implementation4 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.

class-incremental learning Class Incremental Learning +3

DARTH: Holistic Test-time Adaptation for Multiple Object Tracking

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.

Autonomous Driving Multiple Object Tracking +4

Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts

no code implementations8 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.

Autonomous Driving Domain Generalization

On the Practicality of Deterministic Epistemic Uncertainty

2 code implementations1 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

Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps

no code implementations26 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.

Action Classification Action Recognition

3DSNet: Unsupervised Shape-to-Shape 3D Style Transfer

1 code implementation26 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.

Style Transfer

Batch Normalization Embeddings for Deep Domain Generalization

no code implementations25 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.

Domain Generalization

Cannot find the paper you are looking for? You can Submit a new open access paper.