Mattia Segu
15 papers · 2022–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (37) 🤝 Dynamic Duo (10)
🗃️
Keyword Collector
(83)
💎
Century Club · Bronze
⚡
Prolific Year · Productive
Top co-authors
Research topics
Computer Vision
(13)
Machine Learning
(10)
Analysis
(10)
Deep Learning
(8)
Learning Types · Machine Learning
(7)
Application Areas
(6)
Artificial Intelligence
(4)
Learning Types · Deep Learning
(4)
Core AI · Computer Vision
(3)
Core AI · Artificial Intelligence
(3)
Processing
(3)
Architectures
(2)
Learning Paradigms
(2)
Techniques
(2)
Computer Science
(1)
Keywords
domain adaptation
(4)
3d reconstruction
(3)
depth estimation
(3)
test-time adaptation
(2)
monocular depth estimation
(2)
zero-shot learning
(2)
instance segmentation
(2)
multiple object tracking
(2)
metric 3d reconstruction
(2)
multi-task learning
(1)
object detection
(1)
epistemic uncertainty
(1)
self-supervised learning
(1)
knowledge distillation
(1)
metric learning
(1)
uncertainty quantification
(1)
scene understanding
(1)
semantic segmentation
(1)
trajectory prediction
(1)
autonomous driving
(1)
Papers
3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection
ICCV 2025
MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning
ICCV 2025
Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking
ICLR 2025
Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation
CVPR 2025
UniK3D: Universal Camera Monocular 3D Estimation
CVPR 2025
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning
CVPR 2024
Matching Anything by Segmenting Anything
CVPR 2024
"SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking"
ECCV 2024
UniDepth: Universal Monocular Metric Depth Estimation
CVPR 2024
Walker: Self-supervised Multiple Object Tracking by Walking on Temporal Object Appearance Graphs
ECCV 2024
DARTH: Holistic Test-time Adaptation for Multiple Object Tracking
ICCV 2023
Towards Robust Object Detection Invariant to Real-World Domain Shifts
ICLR 2023
Generative Cooperative Learning for Unsupervised Video Anomaly Detection
CVPR 2022
On the Practicality of Deterministic Epistemic Uncertainty
ICML 2022
SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation
CVPR 2022